2026-06-17T08:46:23Z https://jurnal.fikom.umi.ac.id/index.php/ILKOM/oai

oai:ojs.103.2:article/2088 2024-05-30T23:18:37Z BUSITI:ART

oai:ojs.103.2:article/1554 2023-03-25T04:24:33Z ILKOMAS:ART

oai:ojs.103.2:article/782 2021-09-28T23:00:38Z ILKOMAS:ART

oai:ojs.103.2:article/2469 2025-07-06T12:09:46Z ILKOMAS:ART

oai:ojs.103.2:article/1939 2023-09-29T16:05:33Z BUSITI:ART

oai:ojs.103.2:article/1207 2022-06-01T02:58:08Z BUSITI:ART

oai:ojs.103.2:article/2495 2025-01-01T13:56:54Z LINIER:ART

oai:ojs.103.2:article/1668 2023-11-29T22:30:19Z ILKOMAS:ART

oai:ojs.103.2:article/994 2022-02-28T20:07:53Z BUSITI:ART

oai:ojs.103.2:article/1982 2024-03-20T05:53:47Z ILKOMAS:ART

oai:ojs.103.2:article/548 2022-08-31T00:48:55Z BUSITI:ART

oai:ojs.jurnal.fikom.umi.ac.id:article/25 2016-05-23T23:14:28Z umi:ART

oai:ojs.103.2:article/2060 2024-04-18T05:45:20Z BUSITI:ART

oai:ojs.103.2:article/569 2022-08-31T00:50:46Z BUSITI:ART

oai:ojs.103.2:article/457 2026-04-20T06:12:56Z ILKOM:ART driver

ANALISIS IMPLEMENTASI PREPROCESSING DENGAN OTSU-GAUSSIAN PADA PENGENALAN WAJAH Riadi, Annahl Sulaehani, Ruhmi Expression; Face; Customer; otsu-gaussian In this research, we will focus on facial expressions to detect customer satisfaction in mini markets where the service level is less than optimal. To find out the level of custome satisfaction can be seen through facial recognition tahen through CCTV in the mini market. The problems that occur are many customers who do not directly convey the impression that is felt when shopping, while minimarkets and shopping conters must know the level of customer satisfaction to improve sales strategies. Research to solve the problem is still rerely done, therefore one of the roles of intelligent computing is to solve the problem using Support Vector machine (SVM). The purpose of this study is to improve the accuracy of facial expressions of mini market customers through improved preprocessing. The results of the application of the otsu method and the gaussian function can be used for the preprocessing stage through a threshold image that has good image quality. The otsu-gaussian method is not effectively used for preprocessing data sourced from video or images with poor image quality, making it difficult to recognize faces. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2019-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/457 10.33096/ilkom.v11i3.457.200-205 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 200-205 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 200-205 2548-7779 2087-1716 10.33096/ilkom.v11i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/457/193 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/457/116 Copyright (c) 2019 Annahl Riadi, Ruhmi Sulaehani https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/113 2026-04-20T06:18:23Z ILKOM:ART driver

PENGENDALIAN PARABOLA BERGERAK MENGGUNAKAN MIKROKONTROLER Matalangi, Matalangi switch; Parabola; Mikrokontroler; Aktuator; Sinyal Audio Penelitian bertujuan merancang pengendalian parabola bergerak menggunakan Mikrokontroler, Aktuator sebagai penggerak untuk menggerakan parabola kearah timur dan kebarat dan switch sebagai titik tempu pada parabola sehingga dapat berbalik arah timur dan barat, program merumuskan untuk dapat menggerakkan parabola kearah barat dan timur hingga mendapatkan sinyal dan mencapai kemiringan dari 70 derajat ke barat  hingga 120 derajat kearah timur.Hasil penelitian ini adalah perancangan dan pembuatan Pengendali Parabola Bergerak. Pengendalian parabola bergeraka ini terbuat dari bahan aluminium berbentuk lingkaran. Dengan ukuran Linkaran 170cm dan tinggi 150cm. Desain Pengendalian Parabola Bergerak ini terdiri dari 4 komponen utama, dimana komponen pertama sebagai Tiang penopang payung, komponen kedua digunakan sebagai penerima sinyal, komponen ketiga sebagai penerima yang menerima sinyal dari LNB, komponen yang keempat digunakan sebagai pengontrol dari parabola yang menggerakkan Payung parabola ke titik focus satelit yang di kendalikan dan control oleh mikrokontroler. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/113 10.33096/ilkom.v9i1.113.78-85 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 78-85 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 78-85 2548-7779 2087-1716 10.33096/ilkom.v9i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/113/70 Copyright (c) 2017 Matalangi Matalangi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1700 2026-04-20T05:57:29Z ILKOM:ART driver

Machine Learning and Internet of Things (IoT): A Bibliometric Analysis of Publications Between 2012 and 2022 Gani, Hamdan Damayanti, Annisa Dwi Nurani, Nurani Zuhriyah, Sitti Jabir, St. Nurhayati Gani, Helmy Zhipeng, Feng Rejeki, Aisyah Sri Bibliometric Analysis, IoT, Machine Learning, Web of Science. The implementation between machine learning and the Internet of Things (IoT) has been scientifically investigated in many studies. However, not many bibliometric studies categorize the output in this area. By keeping an eye on the publications posted on the Web of Science (WoS) platform, this study aims to give a bibliometric analysis of research on Machine Learning and IoT, identifying the state of the art, trends, and other indicators. 6.170 different articles made up the sample. The VOS viewer software was used to process the data and graphically display the results. The study examined the concurrent occurrence of publications by year, keyword trends, co-citations, bibliographic coupling, and analysis of co-authorship, countries, and institutions. several prolific authors are discovered. However, the body of literature on machine learning and IoT issues is expanding quickly; only five papers accounted for more than 2193 citations. Then, 40.34 percent of the articles from the 694 sources reviewed were published as the most important paper. At the same time, the USA is the top nation for research on this subject area. In addition to identifying gaps and promising areas for future research, this study offers insight into the current state of the art and the field of machine learning and IoT. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1700 10.33096/ilkom.v16i1.1700.27-37 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 27-37 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 27-37 2548-7779 2087-1716 10.33096/ilkom.v16i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1700/pdf Copyright (c) 2024 Hamdan Gani, Annisa Dwi Damayanti, Nurani, Sitti Zuhriyah, St. Nurhayati Jabir, Helmy Gani, Feng Zhipeng, Aisyah Sri Rejeki. https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/526 2026-04-20T06:12:26Z ILKOM:ART driver

Identifikasi Hama Kelapa Sawit menggunakan Metode Certainty Factor Widians, Joan Angelina Rizkyani, Farahdina Nur The pests of palm oil; Expert system; Certainty Factor; Forward Chaining The lack of knowledge of palm oil farmers and general public about pests in palm oil plants will result in a lack of crop yields on these plants. The resulted in the impact of many palm oil farmers who cut down trees as an effort to eradicate of pests. The limitations of an experts makes handling palm oil plan pests difficult so it is necessary to have an experts system that is able to identify pests of palm oil and how to control them based on knowledge given directly by human experts. The inference is Forward chaining by tracing the rules based on the answers of users. And then calculated by Certainty Factor method. The result of calculation is in the form of a percentage value of confidence and user can immediately find out the type of pests identified and how to control it. This research found 7 (seven) types of pests that attack palm oil are fire caterpillar Setothosea asigna, caterpillars Dasychira inclusa, bag caterpillar Metisa plana, horn beetle Oryctes rhinoceros, termite Coptotermes curvignathus, wild rat Rattus tiomanicus, dan wild pig Sus crofa. The biggest pest attact on palm oil is Termite Coptotermes Curvignathus is 88,8% Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/526 10.33096/ilkom.v12i1.526.58-63 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 58-63 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 58-63 2548-7779 2087-1716 10.33096/ilkom.v12i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/526/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/526/155 Copyright (c) 2020 Joan Angelina Widians, Farahdina Nur Rizkyani https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/854 2026-04-20T06:04:10Z ILKOM:ART driver

A Correlation Method for Meteorological Factors and Air pollution in association to covid-19 pandemic in the most affected city in Indonesia Wardhani, Nurilmiyanti Gani, Hamdan Zuhriyah, Sitti Gani, Helmy Vidyarini, Etika Covid-19; Meteorological Factors; Air Pollution; Tropical Climate; Indonesia This study aims to validate the correlation between meteorological factors and air pollution with the spread of Covid-19 in Jakarta, Indonesia. This study examined the Covid-19 cases of Jakarta and its five municipalities. The secondary data of Covid-19 cases, includes Daily Positive Cases (DPC) and Total Daily Positive Cases (TDPC), were retrieved from the Health Office of DKI Jakarta Province, while the meteorological and air pollution parameters were obtained from the online database archives. Kendall and Spearman rank correlation tests were used to analyze correlation between DPC and TDPC with meteorological and air pollution parameters. This study found that Air Quality Index and PM10 showed a significant positive correlation with DPC in municipalities of Jakarta. Also, the average air temperature was positively correlated to TDPC in all region of Jakarta. Average air temperature, Air Quality Index, and PM10 were the factors that take into account for the spread of Covid-19 pandemic in Jakarta, Indonesia. The warmer temperature associated to the higher number of case. Thus, there are no indications that the spread of Covid-19 in subtropical or temperate country may decrease when entering a warmer season that resembles the climatic characteristics in tropical region. Additionally, the significance of air pollutant factors implies that reducing air pollution should be promoted as it might reduce the spread of Covid-19. The findings of this study would be useful to support the strategy and policy in preventing the spread of Covid-19 in the country. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-08-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/854 10.33096/ilkom.v13i3.854.195-205 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 195-205 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 195-205 2548-7779 2087-1716 10.33096/ilkom.v13i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/854/pdf Copyright (c) 2021 Nurilmiyanti Wardhani, Hamdan Gani, Sitti Zuhriyah, Helmy Gani, Etika Vidyarini https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/139 2026-04-20T06:18:00Z ILKOM:ART driver

K-NEAREST NEIGHBOR DENGAN FEATURE SELECTION MENGGUNAKAN BACKWARD ELIMINATION UNTUK PREDIKSI HARGA KOMODITI KOPI ARABIKA Bode, Andi Prediksi; K-Nearest Neighbor; Backward Elimination; Time Series Kopi arabika tergolong salah satu komoditas unggulan didalam subsektor perkebunan di Indonesia karena memiliki peluang pasar yang baik di dalam negeri maupun luar negeri. Dalam penelitian ini akan dilakukan peramalan harga komoditi kopi arabika. Metode Time series adalah metode yang digunakan untuk peramalan dimasa lalu dan mengetahui nilai di masa yang akan datang. Seleksi fitur digunakan sebagai tujuan untuk memilih variabel-variabel yang signifikan dalam melakukan prediksi harga komoditi kopi arabika menggunakan K-Nearest Neighbor (KNN) dengan Backward Elimination (BE). Hasil eksperimen penelitian ini menunjukan dimana algoritma KNN dengan Backward Elimination dapat memperkecil nilai error, dibandingkan dengan KNN tanpa seleksi fitur dan BPNN, BPNN dengan Backward Elimination. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/139 10.33096/ilkom.v9i2.139.188-195 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 188-195 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 188-195 2548-7779 2087-1716 10.33096/ilkom.v9i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/139/93 Copyright (c) 2017 Andi Bode https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2005 2026-04-20T05:56:05Z ILKOM:ART driver

Ensemble Techniques Based Risk Classification for Maternal Health During Pregnancy Mustamin, Nurul Fathanah Buang, Ariyani Aziz, Firman Nur, Nur Hamdani Classification; Ensemble; Health Risk; Machine Learning; Maternal This research focuses on the critical aspect of maternal health during pregnancy, emphasizing the need for early detection and intervention to address potential risks to both mothers and infants. Leveraging various classification methods, including Naïve Bayes, decision trees, and ensemble learning techniques, the study investigates the prediction of childbirth potential and pregnancy risks. The research begins with data collection, followed by preprocessing to clean and prepare the data, including handling missing values and normalization. Next, cross-validation is performed to ensure model robustness. Five ensemble techniques are used for risk classification: Ensemble Boosted Trees, which enhances the performance of decision trees; Ensemble Bagged Trees, which combines predictions from decision trees trained on different subsets of data; Ensemble Subspace Discriminant, which applies discriminant analysis on random subspaces; Ensemble Subspace KNN, which uses K-Nearest Neighbors (KNN) within random subspaces; and Ensemble RUS Boosted Trees. Key variables such as maternal age, height, Hb levels, blood pressure, and previous pregnancy history are considered in these analyses. Additionally, the study introduces Ensemble Learning based on Classification Trees, revealing significant improvements in accuracy compared to cost-sensitive learning approaches. The comparison of methods, including Naïve Bayes and K-Nearest Neighbor, provides insights into their respective performances, with ensemble techniques demonstrating their potential. The proposed ensemble learning techniques, namely Ensemble Boosted Trees, Ensemble Bagging Trees, Ensemble Subspace Discriminant, Ensemble Subspace KNN, and Ensemble RUS Boosted Trees, are systematically evaluated in classifying pregnancy risks based on a comprehensive dataset of 1014 records. The results showcase Ensemble Bagging Trees as a standout performer, with an accuracy of 85.6%, indicating robust generalization and effectiveness in clinical risk assessment compared to traditional methods such as Decision Tree (61.54% accuracy), K-Nearest Neighbor (74.48%), Ensemble Learning based on Cost-Sensitive Learning (73%), Ensemble Learning based on Classification Tree (76%), Gaussian Naïve Bayes (82.6%), Multinomial Naïve Bayes (84.8%), and Bernoulli Naïve Bayes (84.8%). Ensemble Bagging Trees achieved the highest accuracy proving to be more effective than the other methods. However, the study emphasizes the need for continuous refinement and adaptation of ensemble methods, considering both accuracy and interpretability, for successful deployment in healthcare decision-making. These findings contribute valuable insights into optimizing pregnancy risk classification models, paving the way for improved maternal and infant healthcare outcomes. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-08-27 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2005 10.33096/ilkom.v16i2.2005.190-197 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 190-197 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 190-197 2548-7779 2087-1716 10.33096/ilkom.v16i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2005/pdf Copyright (c) 2024 Nurul Fathanah Mustamin, Ariyani Buang, Firman Aziz, Nur Hamdani Nur https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/607 2026-04-20T06:05:19Z ILKOM:ART driver

Metode Double Exponential Smoothing pada Sistem Peramalan Tingkat Kemiskinan Kabupaten Pangkep Atussaliha, Nur Almar' Purnawansyah, Purnawansyah Darwis, Herdianti Peramalan; Kemiskinan; Double Exponential Smoothing; Mean Absolute Percentage Error Peramalan adalah kegiatan memperkirakan kejadian yang akan terjadi berdasarkan historical data kuantitatif suatu kejadian. Peramalan sering digunakan oleh pemerintah dalam membuat suatu kebijakan. Salah satu kebijakan pemerintah adalah menurunkan angka kemiskinan setiap tahunnya. Penelitian ini bertujuan untuk membangun sistem Peramalan Tingkat Kemiskinan Kabupaten Pangkep berbasis desktop untuk memberikan gambaran jumlah tingkat kemiskinan periode selanjutnya. Dalam penelitian ini, metode peramalan yang digunakan adalah Double Exponential Smoothing dengan nilai alpha 0.001, 0.01, 0.2, 0.3, 0.5, 0.7, 0.8, 0.99, dan 0.999. Dengan menggunakan data angka kemiskinan dari tahun 2010 sampai 2019, diperoleh bahwa dari 9 nilai alpha yang digunakan, tingkat kesalahan terkecil yaitu 1.2% diberikan oleh alpha 0.5 yang diukur menggunakan metode Mean Absolute Percentage Error (MAPE). Adapun tingkat akurasi peramalan yang didapatkan jumlah kesalahan tiap alpha sebesar 95.394%. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/607 10.33096/ilkom.v12i3.607.183-190 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 183-190 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 183-190 2548-7779 2087-1716 10.33096/ilkom.v12i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/607/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/607/181 Copyright (c) 2020 Nur Almar' Atussaliha, Purnawansyah Purnawansyah, Herdianti Darwis https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1025 2026-04-20T06:04:10Z ILKOM:ART driver

Influence of gray level co-occurrence matrix for texture feature extraction on identification of batik motifs using k-nearest neighbor Lamasigi, Zulfrianto Yusrin Bode, Andi Gray Level Co-Occurrence Matrix; K-Nearest Neighbour; Confusion Matrix; Feature Extraction; Identification of batik motif Batik is one type of fabric that is unique because it has a special motif, in Indonesia itself batik is unique because it has certain motifs that are made based on the culture from which batik was made. This study aims to examine the effect of the texture feature extraction method on the identification of batik motifs from five major islands in Indonesia. The method used in this study is the Gray Level Co-occurrence Matrix as the texture feature extraction of batik motifs to obtain good batik motif identification accuracy results and to determine the value of the proximity of the training data and image testing of batik motifs, the K-Nearest Neighbor classification method will be used based on texture feature extraction value obtained. In this experiment, 5 experiments will be carried out based on angles 0degrees, 45degrees, 90degrees, 135degrees, and 180degreesusing the values of k is1, 3, 5, and 7. The confusion matrix will be used to calculate the accuracy level of the K-Nearest Neighbor classification. From the results of experiments carried out using training data as many as 607 images and testing as many as 344 images in five classes used with angles of 0 degrees, 45degrees, 90degrees, 135degrees, 180degrees, and values of k are 1, 3, 5, and 7, getting the highest accuracy results is at an angle of 135degreesand 180degreeswith a value of k is 1 of 89.24% and the lowest is at an angle of 90degreeswith a value of k is 3 of 67.44%. This shows that the Gray level co-occurrence matrix method is good for extracting the texture features of batik motifs from five major islands in Indonesia, it is evidenced by the results of the average accuracy of the classification obtained. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-12-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1025 10.33096/ilkom.v13i3.1025.322-333 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 322-333 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 322-333 2548-7779 2087-1716 10.33096/ilkom.v13i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1025/pdf Copyright (c) 2021 Zulfrianto Yusrin Lamasigi, Andi Bode https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/162 2026-04-20T06:17:39Z ILKOM:ART driver

PENERAPAN METODE CERTAINTY FACTOR UNTUK SISTEM PAKAR DIAGNOSA PENYAKIT DIABETES MELITUS PADA RSUD BUMI PANUA KABUPATEN POHUWATO Riadi, Annahl Sistem Pakar; Diebetes Melitus; Certainty factor Diabetes Melitus (DM) atau biasa disebut diabetes merupakan penyakit gangguan metabolik menahun akibat pankreas tidak memproduksi cukup insulin atau tubuh tidak dapat menggunakan insulin yang diproduksi secara efektif. Penderita Diabetes Melitus di Kabupaten Pohuwato mengalami peningkatan sebanyak 8,5% setiap Tahun. Sistem pakar adalah program komputer yang menirukan penalaran seorang pakar dengan keahlian  pada suatu wilayah pengetahuan tertentu. Sistem pakar mencoba mencari solusi, memberikan saran atau kesimpulan yang konsisten terhadap permasalahan yang ditemukannya. Penelitian ini akan dirancang menggunakan Aplikasi Dreamweaver dan bahasa pemrograman PHP, serta database MySQL. Harapan penulis, sistem ini dapat membantu masyarakat dalam mendiagnosa penyakit Diabetes Melitus. Melalui aplikasi ini, pengguna dapat melakukan konsultasi dengan sistem layaknya berkonsultasi dengan seorang pakar untuk mendiagnosa gejala yang terjadi pada pengguna serta menemukan solusi atas permasalahan yang dihadapi. Hasil pengujian sistem diperoleh nilai  Cylomatic complexity = 5 dengan jumlah Region (R)= 5, Node (N)= 10, Edge (E)=13  Predicate Node (P) = 4. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/162 10.33096/ilkom.v9i3.162.309-316 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 309-316 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 309-316 2548-7779 2087-1716 10.33096/ilkom.v9i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/162/110 Copyright (c) 2017 Annahl Riadi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2050 2026-04-20T05:54:17Z ILKOM:ART driver

An AI-integrated IoT-based Self-Service Laundry Kiosk with Mobile Application Kusrini, Kusrini Muhammad, Alva Hendi Fauzi, Moch Farid Kuswanto, Jeki Bernadhed, Bernadhed Widayani, Wiwi Pramono, Eko Muktafin, Elik Hari Ariyanto, Yossy Gradient Boosting; IoT; Laundry Automation; Self-Service Kiosk; Smart Laundry Kiosk. This paper proposes KILAO, an IoT-based self-service laundry kiosk connected with a mobile application that aims to improve the laundry experience by improving user convenience and operational efficiency. This study aims to streamline the washing process using autonomous payment systems, real-time monitoring, and AI-based queue management, resulting in better resource utilization and higher user satisfaction. The development technique comprises identification and requirement gathering, development of both software and hardware prototypes, and evaluation of the prototype. In the requirement-gathering phase, the design of a kiosk machine that consists of hardware and software is defined by combining regular washing machines with IoT technologies for remote control and monitoring. We also developed a mobile application to engage with the kiosk machine. The kiosk simplifies the choice of laundry bundles and accepts various payment options, including cash, cashless transactions, and card-based purchases. The evaluation procedure of the prototype was conducted by using expert evaluations. They are from academics and industry professionals who verified the system’s effectiveness and market potential. The results have shown several unique selling features for KILAO. Extensive payment options and self-service operations were highlighted from the customer’s perspective as key benefits. From the seller’s perspective, its interoperability with traditional washing machines enables a low-cost shift to intelligent, self-service operations, eliminating the need for pricey coin-operated machines. Also, the automatic monitoring system that detects cycle completion can reduce waiting times and improve energy efficiency. In summary, KILAO presents a significant advancement in laundry automation by integrating IoT and AI. Moreover, the Gradient boosting algorithm forecasts waiting times and gives real-time information on machine availability, removing the need for physical queueing. The research demonstrates that KILAO’s capability to provide self-service laundry by providing a user-friendly mobile application can enhance user experience, operational efficiency, and energy utilization. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Kementerian Pendidikan, Kebudayaan, Riset, dan Teknologi (Kemdikbudristek) 2024-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2050 10.33096/ilkom.v16i3.2050.382-393 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 382-393 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 382-393 2548-7779 2087-1716 10.33096/ilkom.v16i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2050/pdf Copyright (c) 2024 Kusrini Kusrini, Alva Hendi Muhammad, Moch Farid Fauzi, Jeki Kuswanto, Bernadhed Bernadhed, Wiwi Widayani, Eko Pramono, Elik Hari Muktafin, Yossy Ariyanto https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/811 2026-04-20T06:04:57Z ILKOM:ART driver

Forensic storage framework development using composite logic method Rachman, Helmi Sugiantoro, Bambang Prayudi, Yudi Storage Forensics; Composite Logic; Framework Increasing number of information technology users allows possibility for crimes to take advantage of information technology to continue increasing either directly and indirectly. Criminals often use computer devices to commit crimes. This is a major concern so that the need for handling digital evidences becomes significantly urgent. Therefore, a forensic storage framework is required for managing digital evidences. This framework is designed by applying the composite logic method to determine role model of each variable or the initial pattern of the stages to be collaborated. Composite logic produces a role model that is to generate patterns in order to achieve the same goal. This method collaborates framework for handling the pre-existing hdd, ssd, and vmware to be in turn combined into a forensic storage framework. Based on the results of the test, this study proposes a new framework called forensic storage framework which comprises of four main stages, namely preparation, collection, analysis and report. The advantage of this framework is that it can be used to handle digital evidences in four storages which are SSD, HDD, VmWare, and cloud. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/811 10.33096/ilkom.v13i1.811.58-66 ILKOM Jurnal Ilmiah; Vol 13, No 1 (2021); 58-66 ILKOM Jurnal Ilmiah; Vol 13, No 1 (2021); 58-66 2548-7779 2087-1716 10.33096/ilkom.v13i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/811/pdf Copyright (c) 2021 Helmi Rachman, Bambang Sugiantoro, Yudi Prayudi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1138 2026-04-20T06:03:31Z ILKOM:ART driver

Analysis of recommendations for recipients of COVID-19 cash social assistance financing the ministry of social affairs Susanto, Erliyan Redy Rusliyawati, Rusliyawati Wantoro, Agus Purnama, Citra Andini Diasari, Itce Decision Support System; Social Grants; Covid-19 Pandemic Effect; Profile Matching In order to solve the problems that exist in the economic aspect due to the COVID-19 pandemic in Indonesia, the government has implemented various programs related to economic recovery. One of these programs is cash social assistance (BST). During the implementation of the social assistance program in various regions, it was reported that the recipients of the program were not properly targeted. Based on the results of a survey from one of the leading universities in Indonesia, it is known that many social assistance programs related to the impact of the COVID-19 pandemic are suspected to have not been in accordance with their designation. Based on this, the research was conducted in Bandar Lampung City. The purpose of this study is to conduct an analysis for recommendations for prospective BST recipients, namely people affected by Covid-19. The method used is profile matching by taking samples in the Jagabaya village, Bandar Lampung City. The criteria used include the work of the head of the family, wife's work, home status, number of dependents and ID cards. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City. Based on the results of an interview with one of the BST officials in Bandar Lampung City, in this study the criteria were grouped into core factors and secondary factors. The results of the research can be used by stakeholders as recommendations for prospective BST recipients in Bandar Lampung City. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1138 10.33096/ilkom.v14i2.1138.126-133 ILKOM Jurnal Ilmiah; Vol 14, No 2 (2022); 126-133 ILKOM Jurnal Ilmiah; Vol 14, No 2 (2022); 126-133 2548-7779 2087-1716 10.33096/ilkom.v14i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1138/pdf Copyright (c) 2022 Erliyan Redy Susanto, Rusliyawati, Agus Wantoro, Citra Andini Purnama, Itce Diasari https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/241 2026-04-20T06:17:18Z ILKOM:ART driver

APLIKASI SISTEM PENDUKUNG KEPUTUSAN PENEMPATAN BIDAN DI DESA MENGGUNAKAN METODE ANALITYCAL HIERARCHY PROCESS (AHP) Annur, Haditsah Bidan Desa; Sistem Pendukung Keputusan; Analitycal Hierarchy Process (AHP) Penempatan bidan desa merupakan peningkatan mutu dan pemerataan pelayanan dalam menurunkan angka kematian ibu, anak balita dan menurunkan angka kelahiran serta meningkatkan kesadaran masyarakat untuk berperilaku hidup sehat. Bidan desa mempunyai tugas dan wewenang seperti mempercepat penurunan angka kematian ibu dan anak, meningkatkan cakupan dan pemerataan jangkauan pelayanan kesehatan ibu hamil, pertolongan persalinan dan konseling. Pada penelitian ini akan dibangun media dengan pendekatan sistem pendukung keputusan, dengan menggunakan metode Analytical Hierarchy Process (AHP) dengan bantuan Tools seperti PHP sebagai bahasa pemrogramannya dan MySQL sebagai database. Alasan menggunakan metode ini dibandingkan dengan metode lain karena proses penentuan penempatan bidan desa merupakan permasalahan yang melibatkan  banyak komponen atau kriteria yang dinilai (multikriteria). AHP digunakan untuk dapat meningkatkan proses serta kualitas hasil pengambilan keputusan dengan memadukan data dan pengetahuan  dalam meningkatkan efektivitas dalam proses pengambilan keputusan. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/241 10.33096/ilkom.v10i1.241.44-51 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 44-51 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 44-51 2548-7779 2087-1716 10.33096/ilkom.v10i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/241/126 Copyright (c) 2018 Haditsah Annur https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2523 2026-04-20T05:52:18Z ILKOM:ART driver

Performance Comparison of Ensemble Learning Models for Brain Tumor Detection on Augmented MRI Datasets Titaley, Gilberth Valentino Rismayanti, Nurul Handayani, Anik Nur Ardiansah, Jevri Tri Brain Tumor; Classification Model; Ensemble Algorithms; Machine Learning; Magnetic Resonance Imaging (MRI). Brain tumors are highly fatal diseases, making early detection a critical factor in improving patient survival rates. Magnetic Resonance Imaging (MRI) has become a primary tool in brain tumor diagnosis; however, manual analysis processes are often time-consuming and prone to subjective errors. This study employs a machine learning-based classification model to detect four categories of brain tumors—glioma, meningioma, pituitary, and healthy—with high accuracy. The methods include image segmentation using the U-Net model, which excels in medical image analysis due to its encoder-decoder architecture with skip connections, allowing efficient integration of spatial and contextual information. Features are extracted using HuMoments, known for their invariance to rotation, translation, and scale, ensuring robust spatial pattern representation. Data normalization is conducted using Robust Scaling and L2 Normalization to address outliers and harmonize feature scales, enhancing model performance. The MRI dataset, originally comprising 7,023 images, was augmented to 8,000 images using techniques such as rotation, flipping, and contrast adjustments to improve class balance and minimize overfitting. Three ensemble algorithms—Random Forest, XGBoost, and Stacking—were employed to train the models, with performance evaluation based on accuracy, ROC-AUC, F1-score, and confusion matrix. The results demonstrate that Random Forest achieved the best performance with an accuracy of 72% and an ROC-AUC of 0.91. This study illustrates the potential of machine learning approaches for automated brain tumor diagnosis, with further improvement possible through model optimization and the use of more diverse datasets. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2025-08-19 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2523 10.33096/ilkom.v17i2.2523.86-97 ILKOM Jurnal Ilmiah; Vol 17, No 2 (2025); 86-97 ILKOM Jurnal Ilmiah; Vol 17, No 2 (2025); 86-97 2548-7779 2087-1716 10.33096/ilkom.v17i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2523/pdf Copyright (c) 2025 Nurul Rismayanti, Gilberth Valentino Titaley, Anik Nur Handayani, Jevri Tri Ardiansah https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1224 2026-04-20T06:03:10Z ILKOM:ART driver

Generating game immersion features for immersive game selection Umar, Najirah Yuyun, Yuyun Gani, Hamdan Game Immersion Features; The Digital Game; Game Immersion Selection The immersion is an essential component of the modern digital game. Currently, immersion is the required component which should be included in the digital game. The modern game which success within game industry surely has included immersion as a component. Although digital games have been introduced for many years, yet what is immersion game been known very little. Regarding the intensive study about user immersion, there is still a lack of knowledge about game immersion. First, the game designers, game developers, and gamers are facing problems how to understand whether their game is immersive or not. There is no knowledge regarding how to evaluate their game, whether immersive or not, and this process requires expert knowledge. Second, currently, the game designers are relied on speculative interpretation to evaluate their game because there is no method to examine whether the game is immersive or not. Therefore, this study aims to propose a method  that enable to evaluate if the game is immersive or not. This method is emerged as knowledge and recommendation that quickly be able to assist the game designers, game developers, and gamers evaluating whether a game is immersive or not. First, this research conducts a literature review to categorize the game immersion features. Second, this study proposes an effective method that can analyse and recommends whether a game is immersive or not. Finally, this study reveals that the finding could be used as a recommendation for the other immersive technology platforms. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-12-19 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1224 10.33096/ilkom.v14i3.1224.264-274 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 264-274 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 264-274 2548-7779 2087-1716 10.33096/ilkom.v14i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1224/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1224/326 Copyright (c) 2022 Najirah Umar, Yuyun Yuyun, Hamdan Gani https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/303 2026-04-20T06:16:56Z ILKOM:ART driver

Klasifikasi Masyarakat Miskin Menggunakan Metode Naive Bayes Annur, Haditsah Poverty Level; Data Mining; Classification; Naïve Bayes The main problem in the current poverty reduction effort is related to the fact that economic growth is not evenly distributed. The research will classify based on the data of poor people obtained from Tibawa District by using data mining technique. Attributes to be used in classifying the population are Age, Education, Work, Income, Dependent, Status (Married / Unmarried). The method to be used is the Naïve Bayes Classifier method, which is one of the classification techniques in data mining. Based on the research, it is concluded that, the classification system of the poor in the administrative area of Tibawa sub-district, Gorontalo regency can be engineered and Based on the result of confusion matrix testing with split validation technique, the use of naïve Bayes classification method to the dataset which has been taken on the research object obtained the level of accuracy 73% or included in the Good category. While the Precision value of 92% and Recall of 86%. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/303 10.33096/ilkom.v10i2.303.160-165 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 160-165 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 160-165 2548-7779 2087-1716 10.33096/ilkom.v10i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/303/142 Copyright (c) 2018 Haditsah Annur https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2906 2026-04-20T05:50:20Z ILKOM:ART driver

Comparative Study of Random Forest and Ordinal Regression in Concept Map Quality Assessment: The Role of TF-IDF, BERT, and SMOTE-based Balancing Rismayanti, Nurul Prasetya, Didik Dwi Widiyaningtyas, Triyanna Hirashima, Tsukasa Concept Map Classification; Random Forest; Ordinal Regression; SMOTE; TF-IDF Automatic assessment of concept map quality is an important challenge in the field of education, particularly in evaluating students' conceptual understanding objectively and efficiently. This study aims to compare the performance of two machine learning algorithms, namely Random Forest and Ordinal Regression, in classifying the quality of concept maps. The evaluation was conducted on three approaches to text feature representation: Term Frequency-Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT), and a combination of both (TF-IDF + BERT). Additionally, this study compares the performance of the models under two dataset conditions: original data and data balanced using the Synthetic Minority Over-sampling Technique (SMOTE), to address the class imbalance that often occurs in educational data. The data used consists of a collection of propositions from students' concept maps that have been labeled with ordinal scores based on quality. Text representation is extracted using the TF-IDF and BERT approaches, and then used as input to build the classification model. Performance evaluation was conducted using the metrics of Accuracy, Precision, Recall, F1-score, Cohen’s Kappa, and MAE. The results show that the Ordinal Regression model with TF-IDF representation combined with SMOTE achieved the best performance, with an accuracy of 0.8777, an F1-score of 0.8773, and a Cohen’s Kappa of 0.7701. These results indicate that classical feature representations like TF-IDF remain effective in limited data scenarios, and that the SMOTE technique successfully improved the model's performance by reducing bias towards the majority class. This research contributes to the development of an automatic concept map assessment system and suggests optimal classification strategies for educational datasets with ordinal and imbalanced characteristics Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2025-12-21 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2906 10.33096/ilkom.v17i3.2906.336-345 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 336-345 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 336-345 2548-7779 2087-1716 10.33096/ilkom.v17i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2906/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/2906/799 Copyright (c) 2025 Nurul Rismayanti, Didik Dwi Prasetya, Triyanna Widiyaningtyas, Tsukasa Hirashima https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1504 2026-04-20T06:02:05Z ILKOM:ART driver

The Implementation of GLCM and ANN Methods to Identify Dragon Fruit Maturity Level Faisal, Muhammad Hasan, Maryam Pelangi, Kartika Candra Prediction, Dragon Fruit; GLCM; ANN The identification of the maturity level of dragon fruit in this study was divided into two groups of ripeness: the unripe and the ripe. This study aims to classify the maturity level based on dragon fruit images using the feature extraction method, the gray level co-occurrence matrix (GLCM). This research method consists of converting RGB data to grayscale, image normalization, detection of dragon fruit maturity, feature extraction, and identification. Data collection from real data totaled 60 images used in this study consisting of 40 training data and 20 testing data which are RGB image data in JPG format. Each data consists of 2 maturity categories. Training data consists of 20 images of 99% ripe dragon fruit and 20 images of 85%. Meanwhile, the testing data consisted of 10 of 99% ripe dragon fruit images and 10 of 85% ripe dragon fruit images. The image data is processed into a grayscale image which then detects the ripeness of the dragon fruit. After the maturity of the dragon fruit is obtained, segmentation is carried out on the location of the dragon fruit found. Then the feature calculation is performed using the Gray Level Co-Occurrence Matrix (GLCM). The Artificial Neural Network (ANN) algorithm is used for the identification process. The final test results show that the proposed method has been able to detect dragon fruit maturity level with an accuracy of = 9/10* 100% = 90%, calculated using the confusion matrix. Thus, implementing the Gray Level Co-Occurrence Matrix and Artificial Neural Network methods to the maturity level problem dragon fruit needs to be developed. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-04-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1504 10.33096/ilkom.v15i1.1504.64-71 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 64-71 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 64-71 2548-7779 2087-1716 10.33096/ilkom.v15i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1504/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1504/428 Copyright (c) 2023 Muhammad faisal, Maryam Hasan https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/365 2026-04-20T06:16:36Z ILKOM:ART driver

ROBOT OPERATING SYSTEM (ROS) DAN GAZEBO SEBAGAI MEDIA PEMBELAJARAN ROBOT INTERAKTIF Jalil, Abdul Robot Operating System (ROS); Gazebo; Robot A robot is a prototype that is able to control by automatically to help the human work. Some of the parts to build a robot system are making the mechanical system, hardware, and software. The limitation of cost to make the robot hardware and programming skills are an obstacle to learn and develop the robot system. The development of the robot community nowadays makes the Robot Operating System (ROS) and Gazebo as an interactive media to learn and make the robot simulation. ROS is a middleware that equipped with tools and libraries to create a robot software, while Gazebo is a 3D simulation application to build a robot hardware design. On this paper, the researcher makes a robot simulation to avoid the object using Lidar sensor and camera, the simulation has developed using ROS and Gazebo that be able to use as a media for robot learning interactive. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-12-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/365 10.33096/ilkom.v10i3.365.284-289 ILKOM Jurnal Ilmiah; Vol 10, No 3 (2018); 284-289 ILKOM Jurnal Ilmiah; Vol 10, No 3 (2018); 284-289 2548-7779 2087-1716 10.33096/ilkom.v10i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/365/160 Copyright (c) 2018 Abdul Jalil https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/48 2026-04-20T06:19:05Z ILKOM:ART driver

Pendeteksian Tepi Objek Menggunakan Metode Gradien Indra, Dolly Gradien, Prewitt, Sobel Pada tahap melakukan ekstraksi ciri (feature extraction) faktor yang sangat penting adalah kemampuan untuk mendeteksi keberadaan tepi di dalam citra. Tujuan penelitian ini adalah menggunakan konsep matematis untuk melakukan fungsi pendeteksian tepi. Uji coba yang dilakukan menggunakan matlab versi R2009a dengan menggunakan citra masukan berupa citra abu-abu (grayscale). Setiap citra diuji dengan menggunakan 3 cara yaitu menggunakan metode gradien citra, gradien Prewitt dan gradien Sobel. Cara kerja dari metode gradien terdiri dari gradien horizontal arah x menghasilkan tepi objek berupa garis vertikal dan diagonal dari citra input, gradien arah vertikal y menghasilkan tepi objek berupa garis horizontal dan diagonal dari citra input sedangkan total gradien merupakan gabungan dari gradien arah x dan gradien arah y sedangkan cara kerja dari untuk metode gradien Prewitt dan Sobel, pemilteran dilakukan secara parsial dengan arah yang berlawanan dengan arah fungsi turunan pertama, bila pemilteran dilakukan dalam arah y maka turunan pertama dari hasil pemilteran dilakukan dalam arah x. Pendeteksian tepi menggunakan gradien Prewitt dan Sobel merupakan hasil gabungan dari konvolusi gradien Prewitt/Sobel arah x dengan gradien Prewitt/Sobel arah y. Hasil uji coba dari penelitian ini memperlihatkan bahwa pendeteksian  tepi menggunakan gradien Sobel lebih tajam dibandingkan dengan gradien Prewitt dan gradien citra. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2016-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/48 10.33096/ilkom.v8i2.48.69-75 ILKOM Jurnal Ilmiah; Vol 8, No 2 (2016); 69-75 ILKOM Jurnal Ilmiah; Vol 8, No 2 (2016); 69-75 2548-7779 2087-1716 10.33096/ilkom.v8i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/48/27 Copyright (c) 2016 Dolly Indra https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1510 2026-04-20T05:59:42Z ILKOM:ART driver

Diabetes Mellitus Early Detection Simulation using The K-Nearest Neighbors Algorithm with Cloud-Based Runtime (COLAB) Jamil, Mohamad Warsito, Budi Wibowo, Adi Kiswanto, Kiswanto Classification; COLAB; Diabetes; K-Nearest Neighbors Diabetes Mellitus is a genetically and clinically heterogeneous metabolic disorder with manifestations of loss of carbohydrate tolerance characterized by high blood glucose levels as a result of insulin insufficiency. Public knowledge of diabetes mellitus 39.30% is influenced by public health education and information about diabetes mellitus that the public has ever received. Early detection of diabetes mellitus can prevent the development of chronic complications and allow timely and rapid treatment. The aim of this study is to simulate the early detection of diabetes mellitus with the K-Nearest Neighbors (K-NN) algorithm using Cloud-Base Runtime (COLAB). The highest accuracy is 76% in K=3, the highest precision is 68% in K=3 and the highest recall is 60% in K=3.  The researchers used K-NN as a method to classify data from the Pima Indians Diabetes Database and obtained a fairly good accuracy value of 76% with a value of k = 3. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-08-16 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1510 10.33096/ilkom.v15i2.1510.215-221 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 215-221 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 215-221 2548-7779 2087-1716 10.33096/ilkom.v15i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1510/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1510/399 Copyright (c) 2023 Mohamad Jamil, Budi Warsito, Adi Wibowo, Kiswanto Kiswanto https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/413 2026-04-20T06:13:33Z ILKOM:ART driver

PENGEMBANGAN MODEL SIMULASI SISTEM DINAMIK UNTUK MENINGKATKAN EFISIENSI SISTEM OPERASIONAL TRANSPORTASI Faradibah, Amaliah Suryani, Erma Transportation System; Efficiency; Traffic congestion; System Dynamics If transport continues to increase, plus manufacturers competing to produce interesting transportation on the market, thus allowing the improvement of the transport users. If the increase occurs, it will cause congestion. Congestion was a factor that greatly affect the efficiency of the transport system, where the transportation system is a form of attachment and the interconnected between the passenger, shuttles and infrastructure that interact in order to transfer people or goods, which is covered in an order, either by natural or artificial or engineered. It takes the right planning strategies in addressing conditions congestion such as implementation of reconfiguration of the route network, a program that using dynamical systems in proper design and planning, and the determination of the most appropriate scenario can improve the efficiency of the transportation system. This research uses scenario through reconfiguration of network routes to improve the efficiency of the transportation system. in this study, this scenario is considered to be the most appropriate to increase the efficiency of vehicle travel time by way of the transfer of light vehicle routes that will go towards the Urip Sumoharjo street because it results in a reduction in travel time by 1.2% of travel time before the scenario. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2019-05-01 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/413 10.33096/ilkom.v11i1.413.67-76 ILKOM Jurnal Ilmiah; Vol 11, No 1 (2019); 67-76 ILKOM Jurnal Ilmiah; Vol 11, No 1 (2019); 67-76 2548-7779 2087-1716 10.33096/ilkom.v11i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/413/177 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/413/104 Copyright (c) 2019 Amaliah Faradibah, Erma Suryani https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/68 2026-04-20T06:18:43Z ILKOM:ART driver

DETEKSI PINEAP PADA FIRMWARE WIFI PINEAPPLE MENGGUNAKAN SMARTPHONE BERBASIS ANDROID Romisa, Fahmi Sugiantoro, Bambang Deteksi, Jaringan nirkabel, Wifi Pineapple, Pineap Kebutuhan akan akses jaringan nirkabel atau wireless saat ini sangat dibutuhkan oleh hampir semua orang, hampir di semua tempat terdapat akses jaringan wifi. Sebuah ilmu penetrasi jaringan semakin lama selama meningkat, tidak hanya menggunakan suatu penetrasi yang menggunakan perangkat lunak, tetapi sudah merambah ke perangkat keras yang sudah berubah fungsi, tidak lagi berfungsi sebagai menyebar sebuah koneksi data, tetapi sudah merambah sebagai alat penetrasi jaringan, sistem ini berguna untuk mendeteksi adanya sebuah router yang dapat menduplikasi semua router sekitar dengan permintaan probe request, maka dari itu diperlukan suatu alat pendeteksian yang dapat mendeteksi secara real time terhadap router tersebut . penelitian ini menghasilkan suatu alat pendeteksian yang user friendly menggunakan smartphone berbasis android, beserta analisis dan melakukan suatu uji beda pada router yang memiliki firmware wifi pineapple yang memiliki core pineap.  Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2016-12-11 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/68 10.33096/ilkom.v8i3.68.204-211 ILKOM Jurnal Ilmiah; Vol 8, No 3 (2016); 204-211 ILKOM Jurnal Ilmiah; Vol 8, No 3 (2016); 204-211 2548-7779 2087-1716 10.33096/ilkom.v8i3 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/68/48 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/68/12 Copyright (c) 2016 Fahmi Romisa https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1692 2026-04-20T05:59:42Z ILKOM:ART driver

Classifying BISINDO Alphabet using TensorFlow Object Detection API Classifying BISINDO Alphabet using TensorFlow Object Detection API Hayati, Lilis Nur Handayani, Anik Nur Irianto, Wahyu Sakti Gunawan Asmara, Rosa Andrie Indra, Dolly Fahmi, Muhammad Artificial Intelligence; BISINDO; Computer Vision; Real-time; TensorFlow Object Detection API Artificial Intelligence; BISINDO; Computer Vision; Real-time; TensorFlow Object Detection API Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite  SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of  consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well. Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite  SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of  consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-08-16 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1692 10.33096/ilkom.v15i2.1692.358-364 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 358-364 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 358-364 2548-7779 2087-1716 10.33096/ilkom.v15i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1692/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1692/454 Copyright (c) 2023 Lilis Nur Hayati, Anik Nur Handayani, Wahyu Sakti Gunawan Irianto, Rosa Andrie Asmara, Dolly Indra, Muhammad Fahmi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/108 2026-04-20T06:18:23Z ILKOM:ART driver

PENERAPAN SISTEM REPLIKASI DAN INTEGRASI BASIS DATA TERDISTRIBUSI PADA PANGKALAN DATA PENDIDIKAN TINGGI (PDPT) Belluano, Poetri Lestari Lokapitasari PDPT; Replikasi; Basis data; PostgreSQL Besarnya data pelaporan EPSBED dari Prodi ke PDPT-Universitas hingga ke PDPT-DIKTI membutuhkan sarana integrasi dan komunikasi data yang konsisten, belum mengikuti standarisasi pengelolaan database terpusat pada siklus manajemen yang terkait dengan sistem Pangkalan Data Pendidikan Tinggi (PDPT). Penelitian ini bertujuan membangun sistem informasi yang memiliki  integritas, konsistensi dan validitas data antar Program Studi dan PDPT Universitas. Metode yang digunakan meliputi studi lapangan dan kepustakaan untuk mengetahui data pelaporan EPSBED dari Prodi ke PDPT-Universitas hingga ke PDPT-DIKTI, perancangan sistem informasi dan basis data menggunakan Convention Over Configuration, pemodelan sistem Unified Modeling Language, pengelolaan Data Base Management System menggunakan PostgreSQL, dan port TCP-IP sebagai sarana komunikasi data. Hasil penelitian ini menunjukkan penerapan sistem replikasi yang bersifat real time sebagai  bentuk alternatif pengiriman data berjumlah besar, menjamin sinkronisasi integrasi basis data dari server asal ke server tujuan, dan sistem replikasi DBMS menggunakan PostgreSQL membantu DBMS Program Studi terintegrasi dan terkorelasi langsung dengan PDPT-Universitas Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/108 10.33096/ilkom.v9i1.108.42-48 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 42-48 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 42-48 2548-7779 2087-1716 10.33096/ilkom.v9i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/108/65 Copyright (c) 2017 Poetri Lestari Lokapitasari Belluano https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1780 2026-04-20T05:58:32Z ILKOM:ART driver

MobileNet Classifier for Detecting Chest X-Ray Images of COVID-19 based on Convolutional Neural Network Ghani, ST. Aminah Dinayati Intan, Indo Rizal, Muhammad Chest X-Ray; CNN; COVID-19; Image Analysis; MobileNet Since the COVID-19 pandemic occurred all over the world, numerous studies were carried out to overcome this problem, including COVID-19 image analysis. An expert analysis based on the Chest X-ray images of COVID-19 determines the progression of the lung condition. Eye visualization and expertise of a radiologist have limitations in handling big cases. This study aims to implement the Convolutional Neural Network (CNN) and MobileNet models as deep learning models to classify chest X-ray images into multiclassification, three categories: COVID-19, normal, and virus. The processes were pre-processing and processing. The pre-processing stage was preparing data, and the processing stage was the implementation model and investigating the best model performance in both convolution and classification in depth-wise convolution and batch normalization. The metrics were accuracy, precision, f1-score, and recall. The CNN results of accuracy, precision, recall, and f1-score respectively were 0.94; 0.99; 0.95; and 0.96. The MobileNet results of the metrics were 0.97; 0.98; 0.99, and 0.99. The MobileNet outperforms the CNN results due to depth-wise convolution and batch normalization. Both models contribute to the faster epoch of the best hyperparameter to achieve loss and accuracy convergence. The models are worth recommending to deployment front-end. Prodi Teknik Informatika FIK Universitas Muslim Indonesia DRPM Ditjen Diktiristek 2023-12-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1780 10.33096/ilkom.v15i3.1780.488-497 ILKOM Jurnal Ilmiah; Vol 15, No 3 (2023); 488-497 ILKOM Jurnal Ilmiah; Vol 15, No 3 (2023); 488-497 2548-7779 2087-1716 10.33096/ilkom.v15i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1780/pdf Copyright (c) 2023 ST. Aminah Dinayati Ghani, Indo Intan, Muhammad Rizal https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/494 2026-04-20T06:12:26Z ILKOM:ART driver

Pengelompokan Buah Jeruk menggunakan Naïve Bayes dan Gray Level Co-occurrence Matrix Haba, Rahmat Karim Pelangi, Kartika Chandra Classification; GlCM; Naïve Bayes Tangerines are fruits that are rich in high vitamin C content. Every orchard owner always tries to improve the quality of their plantation. In the selection of tangerines to be classified as ripe or immature at harvest time, the garden planters are already accustomed, but sometimes the farmer grouping the ripe oranges has problems such as physical limitations of the farmer, which is caused by fatigue factor. because it is still grouping with conventional systems so it is not effective and efficient in classifying ripe oranges. So from that we need a computerized system that can help gardeners in classifying ripe oranges. One of the technologies currently developing in agriculture and plantations is digital image processing using a classification system based on the texture and naïve bayes method. Based on the results that have been made, that the classification system using the Naïve Bayes method on tangerine images can be classified and obtain effective and efficient performance based on testing of 82% so that it can be implemented. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/494 10.33096/ilkom.v12i1.494.17-24 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 17-24 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 17-24 2548-7779 2087-1716 10.33096/ilkom.v12i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/494/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/494/150 Copyright (c) 2020 Rahmat Karim Haba https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/847 2026-04-20T06:04:29Z ILKOM:ART driver

Enterprise architecture design using TOGAF at foundation of triputra persada horizon education Purba, Arif Budimansyah Mubarok, Ahmad Mulyana, Jajang Information Technology; Enterprise Architecture; TOGAF ADM The use of information technology in the field of education is currently a top priority for managing academic and supporting activities. Tri Putra Persada Horizon Education Foundation which manages two high schools, namely the College of Health Sciences and the College of Information and Computer Management should face a challenge to align business strategy with information technology, and how to integrate all the parts involved in the business and represent it in an information system. To find out the business strategy and governance of information technology used at the Tri Putra Persada Horizon Education Foundation, an Enterprises Architecture Framework is needed, one of which is TOGAF ADM. The Enterprises Architecture design contained in TOGAF ADM includes a vision architecture that defines the vision of the company or agency, a mapped business architecture in the form of value chain analysis, an information system architecture in which there is a data architecture and application architecture and the last is technology architecture. This research produced an enterprise architecture design blueprint consisting of artifacts, in the form of catalogues, matrices, and diagrams based on the phases of TOGAF ADM. The result of the Enterprise Architecture design was an integrated information system recommendation and the technology architecture. The design is expected to be a reference in improving the quality of business and is expected to make it easier to achieve the business goals of the Tri Putra Persada Horizon Education Foundation. Prodi Teknik Informatika FIK Universitas Muslim Indonesia STMIK Horizon Karawang 2021-08-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/847 10.33096/ilkom.v13i2.847.155-162 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 155-162 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 155-162 2548-7779 2087-1716 10.33096/ilkom.v13i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/847/pdf Copyright (c) 2021 jajang mulyana https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/133 2026-04-20T06:18:00Z ILKOM:ART driver

ANALISIS DEKOMPOSISI WAVELET PADA PENGENALAN POLA LURIK DENGAN METODE LEARNING VECTOR QUANTIZATION Robi'in, Bambang Citra; Lurik; Jaringan syaraf tiruan; Learning Vector Quantization; Wavelet Indonesia merupakan negara yang terdiri dari banyak suku dan adat istiadat. Keragaman budaya di Indonesia juga dapat dilihat dari kerajinan tenun seperti songket dari daerah sumatra, ulos dari daerah batak, dan kain lurik dari daerah jawa tengah. Kain lurik dibuat dengan motif bergaris-garis atau kotak-kotak tetapi memiliki pola yang bermacam-macam dan sulit dibedakan antara satu pola dengan yang lainnya. Dalam penelitian ini, pengenalan pola dilakukan dengan membangun jaringan syaraf tiruan dengan metode Learning Vector Quantization (LVQ). Proses dekomposisi yang digunakan untuk ekstraksi ciri suatu citra ini digunakan metode Discrete Wavelet Transform (DWT). Hasil penelitian menunjukan bahwa Jaringan syaraf tiruan untuk Pengenalan pola menggunakan metode LVQ dan wavelet haar, wavelet daubechies, wavelet symlet, dan wavelet coiflet menghasilkan sebuah jaringan syaraf tiruan yang memiliki kinerja berbeda-beda. Hasil terbaik dari kinerja jaringan ini diperoleh kinerja terbaik dengan akurasi sebesar 80% pada JST yang menggunakan metode dekomposisi wavelet haar. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-08-24 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/133 10.33096/ilkom.v9i2.133.153-160 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 153-160 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 153-160 2548-7779 2087-1716 10.33096/ilkom.v9i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/133/87 Copyright (c) 2017 Bambang Robi'in https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1908 2026-04-20T05:56:05Z ILKOM:ART driver

Improving Source Code Quality by Minimizing Refactoring Effort Oumarou, Hayatou Tizi, Kabirrou Hamadou Evaluation Model; Maintainability; Metric; Refactoring; Software Quality Software maintenance is a time-consuming and costly endeavor. As a part of maintenance, refactoring is aimed at enhancing quality. Due to project deadlines and limited resources, developers need to prioritize refactoring activities. In this paper, we present a livestock management-inspired approach for identifying and prioritizing classes to refactor within an object-oriented program. This approach empowers developers to enhance the time/quality ratio. The novelty of our approach lies in utilizing established metrics for detecting code defects to prioritize each class. To validate its effectiveness, the approach was tested on four distinct Pharo-based open source programs. The results demonstrate the approach's efficacy in improving software quality, reducing development time, and enhancing team productivity Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-08-27 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1908 10.33096/ilkom.v16i2.1908.145-150 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 145-150 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 145-150 2548-7779 2087-1716 10.33096/ilkom.v16i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1908/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1908/503 Copyright (c) 2024 Hayatou Oumarou, Kabirrou Hamadou Tizi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/596 2026-04-20T06:09:30Z ILKOM:ART driver

Anti-WebShell PHP Backdoor Scanner pada Linux Server Sopaheluwakan, Christian Ronaldo Chandra, Dian Widiyanto Anti Web Shell; Backdoor Scanner; Backdoor Shell; Network Security; Linux Server Backdoor or commonly also known as web shell is one of the malicious software that hackers use to maintain access systems that they have entered. Relatively few programs like Anti Web-Shell, PHP Backdoor Scanner circulating on the Internet, and can be obtained free of charge to deal with the issues above. But most of these programs have no actual database of signature behavior to deal with PHP backdoor / Shell nowadays. Then comes the contemporary Anti Web-Shell program that can deal with today's backdoor shell. This study uses an experimental method concerning previous similar studies and is implemented directly into the world of cyber security professional industries. By enriching the Regex dictionary signature and String Array Matching the actualized Anti Web-Shell program can detect more backdoor than similar programs that have existed in the past. The results of this study are in the form of a web application software in PHP extension. The application can minimize 100% of false positives and is twice as fast in scanning files because it is more specific in heuristic analysis scan. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Dian W. Chandra, Dosen Senior Teknik Informatika, Fakultas Teknologi Informasi, Universitas Kristen Satya Wacana. 2020-08-27 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/596 10.33096/ilkom.v12i2.596.143-153 ILKOM Jurnal Ilmiah; Vol 12, No 2 (2020); 143-153 ILKOM Jurnal Ilmiah; Vol 12, No 2 (2020); 143-153 2548-7779 2087-1716 10.33096/ilkom.v12i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/596/pdf Copyright (c) 2020 Christian Ronaldo Sopaheluwakan, Dian Widiyanto Chandra https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/937 2026-04-20T06:04:10Z ILKOM:ART driver

Identification of chicken egg fertility using SVM classifier based on first-order statistical feature extraction Saifullah, Shoffan Suryotomo, Andiko Putro Egg Fertility; Feature Extraction; Identification; Image Processing; Machine Learning This study aims to identify chicken eggs fertility using the support vector machine (SVM) classifier method. The classification basis used the first-order statistical (FOS) parameters as feature extraction in the identification process. This research was developed based on the processs identification process, which is still manual (conventional). Although currently there are many technologies in the identification process, they still need development. Thus, this research is one of the developments in the field of image processing technology. The sample data uses datasets from previous studies with a total of 100 egg images. The egg object in the image is a single object. From these data, the classification of each fertile and infertile egg is 50 image data. Chicken egg image data became input in image processing, with the initial process is segmentation. This initial segmentation aims to get the cropped image according to the object. The cropped image is repaired using image preprocessing with grayscaling and image enhancement methods. This method (image enhancement) used two combination methods: contrast limited adaptive histogram equalization (CLAHE) and histogram equalization (HE). The improved image becomes the input for feature extraction using the FOS method. The FOS uses five parameters, namely mean, entropy, variance, skewness, and kurtosis. The five parameters entered into the SVM classifier method to identify the fertility of chicken eggs. The results of these experiments, the method proposed in the identification process has a success percentage of 84.57%. Thus, the implementation of this method can be used as a reference for future research improvements. In addition, it may be possible to use a second-order feature extraction method to improve its accuracy and improve supervised learning for classification. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-12-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/937 10.33096/ilkom.v13i3.937.285-293 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 285-293 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 285-293 2548-7779 2087-1716 10.33096/ilkom.v13i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/937/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/937/262 Copyright (c) 2021 Shoffan Saifullah, Andiko P Suryotomo https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/155 2026-04-20T06:17:39Z ILKOM:ART driver

DESAIN MOBILE SISTEM INFORMASI GEOGRAFIS SEKOLAH GARIS DEPAN (SGD) BERBASIS ANDROID DI PROVINSI GORONTALO. Ibuna, Abdul Malik Sistem Informasi Geografis; Sekolah Garis Depan; Android. Sekolah Garis Depan (SGD) merupakan sekolah yang terletak di daerah terluar, terpencil, dan tertinggal (3T), propinsi Gorontalo yang merupakan propinsi baru pemekaran dari Sulawesi Utara masih memiliki ±25 sekolah yang termasuk sekolah 3T. Tujuan penelitian ini adalah merancang suatu Sistem Informasi Geografis agar dapat mengetahui lokasi akurat sekolah yang termasuk 3T serta memberikan informasi tentang kondisi sekolah 3T dari segi fasilitas sekolah, guru-guru pengajar dan jumlah siswa. Penelitian ini dilaksanakan di propinsi Gorontalo. Metode analisis sistem yang digunakan adalah metode SDLC (system Development Life Cycle) dengan tahapan yaitu perencanaan sistem (system planning), analisis sistem (system analysis), desain sistem (system design), seleksi sistem (system selection), implementasi sistem (system implementation). Pengujian sistem menggunakan metode test case dengan pendekatan white box testing. Sistem informasi geografis sekolahgaris depan dipropinsi Gorontalo, di desain dan di bangun menggunakan bahasa pemrograman PHP, Google Maps, Android studio dan dreamweaver serta GPS sebagai pendukung penentuan titik koordinat lokasi sekolah. Hasil yang diperoleh yaitu sebuah map/peta digital yang dapat di terapkan di mobile HP/tablet menggunakan sistem operasi android, dilengkapi dengan rute atau jarak yang dapat memudahkan user mengetahui informasi bila mau mencari dan berkunjung ke lokasi. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/155 10.33096/ilkom.v9i3.155.268-273 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 268-273 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 268-273 2548-7779 2087-1716 10.33096/ilkom.v9i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/155/105 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/155/28 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/155/29 Copyright (c) 2017 Abdul Malik Ibuna https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2378 2026-04-20T05:54:17Z ILKOM:ART driver

Techniques for Video Authenticity Analysis Using the Localization Tampering Method to Support Forensic CCTV Investigations Anggraini, Ririn Prayudi, Yudi CCTV; Digital Forensics; Evidence; Histogram; Localization Tampering. Closed Circuit Television (CCTV) is frequently utilized as legal evidence in judical proceedings. However, the authenticity of CCTV footage is often contested, requiring forensic analysis to verify its reliability as digital evidence. This study aimed to assess the authenticity of video footage using the Localization Tampering method. To simulate manipulation, various manipulation techniques, such as zooming, cropping, converting to grayscale, deleting frames, and rotating video sections, were applied. The Localization Tampering method was then used to detect manipulated areas by analyzing individual frames, calculating their histograms, and interpreting the histogram graph result. The findings demonstrated the method's ability to accurately identify the location and duration of manipulated frames. This offered a valuable tool to support forensic investigations of CCTV footage. Furthermore, this study highlights the challenges in detecting manipulation in low-quality videos, which required more sophisticated remediation techniques. Despite these challenges, the Localization Tampering method demonstrated consistent reliability in preserving the integrity of video footage, making it a practical solution for verifying digital evidence in a legal context. Overall, this study provides an effective approach to ensure that manipulated videos can be identified and corrected, contributing to a more robust CCTV forensics process and maintaining the credibility as evidence in a crime case. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-12-29 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2378 10.33096/ilkom.v16i3.2378.318-329 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 318-329 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 318-329 2548-7779 2087-1716 10.33096/ilkom.v16i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2378/pdf Copyright (c) 2024 ririn anggraini, Yudi Prayudi, Yudi Prayudi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/750 2026-04-20T06:04:57Z ILKOM:ART driver

Fuzzy logic algorithm and analytic network process (ANP) for boarding houses searching recommendations Gunawan, Wawan Analytic Network Process ; Fuzzy Logic; DSS; boarding house; recommendation Finding a boarding house is usually done manually or by visiting the boarding house in person. Several choices of boarding houses make boarding house seekers have to make choices according to the desired criteria, so it takes quite a long time. A decision support system is a system that can be used to help make decisions based on existing criteria for determining several alternatives to be selected. The methods used in this research are the Analytic Network Process (ANP) and the Fuzzy Logic method. This study employed several criteria in providing recommendations, including distance, price, facilities, security, number of spaces, parking space and convenience. The weighting of these criteria used the fuzzy logic method based on the priority scale determined by the boarding house seekers. This system has provided a recommendation for boarding houses based on the results of the calculation process using the ANP method and weighting using fuzzy logic. The result of calculations shows that the highest value was obtained by Munawar kos (boarding house) with a value of 6.55% and followed by Diding kos with a value of 6.52%. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/750 10.33096/ilkom.v13i1.750.18-30 ILKOM Jurnal Ilmiah; Vol 13, No 1 (2021); 18-30 ILKOM Jurnal Ilmiah; Vol 13, No 1 (2021); 18-30 2548-7779 2087-1716 10.33096/ilkom.v13i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/750/pdf Copyright (c) 2021 Wawan Gunawan https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1106 2026-04-20T06:03:47Z ILKOM:ART driver

LSTM-based Multivariate Time-Series Analysis: A Case of Journal Visitors Forecasting Saputra, Anggie Wahyu Wibawa, Aji Prasetya Pujianto, Utomo Putra Utama, Agung Bella Nafalski, Andrew Forecasting; Multivariate; Long Short-term Memory; Sessions. Forecasting is the process of predicting something in the future based on previous patterns. Forecasting will never be 100% accurate because the future has a problem of uncertainty. However, using the right method can make forecasting have a low error rate value to provide a good forecast for the future. This study aims to determine the effect of increasing the number of hidden layers and neurons on the performance of the long short-term memory (LSTM) forecasting method. LSTM performance measurement is done by root mean square error (RMSE) in various architectural scenarios. The LSTM algorithm is considered capable of handling long-term dependencies on its input and can predict data for a relatively long time. Based on research conducted from all models, the best results were obtained with an RMSE value of 0.699 obtained in model 1 with the number of hidden layers 2 and 64 neurons. Adding the number of hidden layers can significantly affect the RMSE results using neurons 16 and 32 in Model 1. Prodi Teknik Informatika FIK Universitas Muslim Indonesia We would like to say our gratitude to the KEDS journal for sharing the visitor dataset 2022-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1106 10.33096/ilkom.v14i1.1106.57-62 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 57-62 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 57-62 2548-7779 2087-1716 10.33096/ilkom.v14i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1106/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1106/306 Copyright (c) 2022 anggie wahyu saputra, Aji Prasetya Wibawa, Utomo Pujianto, Agung Bella Putra Utama, Andrew Nafalski https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/203 2026-04-20T06:17:18Z ILKOM:ART driver

APLIKASI VIRTUAL IKLAN PERUMAHAN DENGAN SISTEMAUGMENTED REALITY Wirawan, Raden Augmented Reality; Iklan Perumahan; Virtual 3D Rumah merupakan kebutuhan manusia dan dapat dijadikan aset bisnis sehingga bisnis perumahan berkembang dengan pesat. Saat ini iklan perumahan biasanya melalui media cetak maupun promosi secara langsung yang kebanyakan dalam bentuk dua Dimensi (2D). Augmented Reality (AR) adalah suatu lingkungan yang memasukkan objek virtual 3D ke dalam lingkungan nyata. Dengan adanya program Augmented Reality sistem marketing perumahan dapat mempromosikan rumah dalam bentuk tiga dimensi (3D) dan membawa maket perumahan dalam bentuk 3D dimana objek rumah dapat di zoom in , zoom out, rotasi secara vertical, rotasi secara horizontal dan terdapat denah untuk tiap rumah serta informasi mengenai rumah tersebut. Melalui aplikasi Augmented Reality ini penulis berharap dapat memberi pengetahuan lebih kepada pembaca dan bisa membantu para pelaku bisnis properti pada umumnya, khususnya para sales dalam mempromosikan rumah dalam bentuk virtual 3D. Hasil penelitian ini menunjukkan bahwa penerapan teknologi Augmented Reality dapat diaplikasikan pada brosur perumahan dan dapat menarik perhatian pelanggan karena lebih mudah dalam memberikan informasi mengenai model rumah yang ditawarkan pada brosur perumahan. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-04-29 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/203 10.33096/ilkom.v10i1.203.11-16 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 11-16 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 11-16 2548-7779 2087-1716 10.33096/ilkom.v10i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/203/121 Copyright (c) 2018 Raden Wirawan https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2562 2026-04-20T05:52:18Z ILKOM:ART driver

Enhancing Kubernetes-Based Microservices Deployment Efficiency Through DevOps and GitOps Maulana, Irvan Umar, Rusydi Yudhana, Anton Kubernetes, DevOps, Microservices, GitOps, CI/CD An effective and resilient means to deploy microservices to Kubernetes is an ongoing challenge. This challenge becomes more difficult with ever increasingly complex application architectures. This research explored a DevOps model based on GitOps that integrates ArgoCD and GitLab CI/CD, as a means to create a more effective, resilient, and scalable deployment. Twelve microservices that were deployed in a controlled experimentation format were used in a comparative approach to previous deployment practices that only considered manual deployments. The results show an overall deployment time improvement of 40%. For the deployments that were executed incorrectly, ArgoCD ensures service availability leveraging its self-healing capabilities. During the computation of each run we also experienced system performance in a sustained high-load environment. Upon high demand, we experienced the desired autoscaling behavior requested, which resulted in higher service responsiveness. In comparison to previous studies, this research considered statistical analysis, while also looking at an aspect of real-world orchestration and networking efficiency while adopting Kubernetes. Altogether, this research gives organizations practical advice on how they may optimize their deployment pipelines for efficient, scalable and resilient microservices. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Universitas Ahmad Dahlan 2025-08-14 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2562 10.33096/ilkom.v17i2.2562.107-119 ILKOM Jurnal Ilmiah; Vol 17, No 2 (2025); 107-119 ILKOM Jurnal Ilmiah; Vol 17, No 2 (2025); 107-119 2548-7779 2087-1716 10.33096/ilkom.v17i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2562/pdf Copyright (c) 2025 Irvan Maulana, Rusydi Umar, Anton Yudhana https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1328 2026-04-20T06:03:10Z ILKOM:ART driver

Classification of stroke patients using data mining with adaboost, decision tree and random forest models Imran, Bahtiar Wahyudi, Erfan Subki, Ahmad Salman, Salman Yani, Ahmad Data Mining; AdaBoost; Decision Tree; Random Forest; Stroke. A stroke is a fatal disease that usually occurs to the people over the age of 65. The treatment progress of the medical field is growing rapidly, especially with the technological advance, with the emergence of various medical record data sets that can be used in medical records to identify trends in these data sets using data mining. The purpose of this study was to propose a model to classify stroke survivors using data mining, by utilizing data from the kaggle sharing dataset. The models proposed in this study were AdaBoost, Decision Tree and Random Forest, evaluation results using Confusion Matrix and ROC Analysis. The results obtained were that the decision tree model was able to provide the best accuracy results compared to  the other models, which was 0.953 for Number of Folds 5 and 10. From the results of this study, the decision tree model was able to provide good classification results for stroke sufferers. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-12-19 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1328 10.33096/ilkom.v14i3.1328.218-228 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 218-228 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 218-228 2548-7779 2087-1716 10.33096/ilkom.v14i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1328/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1328/337 Copyright (c) 2022 Bahtiar Imran, Erfan Wahyudi, Ahmad Subki, Salman Salman, Ahmad Yani https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/271 2026-04-20T06:16:56Z ILKOM:ART driver

SISTEM KONTROL INFORMASI AKTIVITAS LANSIA BERBASIS INTERNET OF THINGS (IoT) Wahyuningsih, Pujianti Elderly; Control Systems; Internet of Things (IoT) Elderly is a human phase are notabel to much do an activity because of physical factors and age. On doing daily activity the elderly should be kept by the family or nurse so in this research will be built a control system thatabel to detection of elderly activity and control an electronic device remotely using the Internet of Things (IoT). All of the elderly activity has detected based on sensor data input from the carpet, PIR sensor, DHT22 temperature sensor then processed in the Arduino Mega and Raspberry Pi. The function of Raspberry Pi is to connect all elderly information to the internet using node.js. Based on the information the family or nurse able to see the elderly activity remotely using website and able to control electronic device like a fan and heater by manually and automatically using the Internet of Things technology. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/271 10.33096/ilkom.v10i2.271.120-127 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 120-127 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 120-127 2548-7779 2087-1716 10.33096/ilkom.v10i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/271/137 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/271/60 Copyright (c) 2018 Pujianti Wahyuningsih https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2857 2026-04-20T05:50:20Z ILKOM:ART driver

Detection of Curcuma and Turmeric Differences Utilizing Fuzzy Tsukamoto Android-Based CCN Model Putra, Fajar Rahardika Bahari Setyawan, Muhammad Rizki Ilham, Ahmad Suseno, Dimas Adi Curcuma, Turmeric, CNN, Fuzzy Tsukamoto, Android Classification. Turmeric and curcuma are herbs that are often used in medicine and cooking. However, their similar shapes and colours make it difficult for people, especially in Southwest Papua, to distinguish between them directly. According to the Central Statistics Agency (BPS) in 2023, turmeric production reached 18,302 units, far higher than turmeric, which only reached 2,950 units. Based on field interviews in Southwest Papua, more than 60% of respondents had difficulty distinguishing turmeric from turmeric. To address this issue, this research develops an Android-based classification system by integrating the Fuzzy Tsukamoto algorithm with Convolutional Neural Network (CNN) models. Five CNN models VGG16, MobileNetV2, NASNetMobile, EfficientNetB2, and EfficientNetB3 were selected based on their balance between computational efficiency (MobileNetV2, NASNetMobile), depth and proven stability (VGG16), and modern scalable architectures (EfficientNetB2 and B3). Each model was combined with fuzzy logic to enhance classification accuracy. he dataset consisted of 800 images of curcuma and turmeric obtained from Kaggle and field collections. The data were divided into training, validation, and testing sets, and augmented through a series of transformations including rescaling to a range of 0 to 1, rotation up to 40 degrees, horizontal shift of 20%, angular distortion (shear) of 20%, zoom up to 30%, horizontal flipping, and brightness adjustment. Empty areas generated during augmentation were filled using the nearest pixel value with the ‘nearest’ mode to preserve image integrity. Training was performed using the AdamW optimizer and fine-tuning. Model evaluation employed accuracy, precision, recall, F1-score, and confusion matrix metrics. The results showed that the VGG16 model performed best, achieving 97% accuracy, 98% precision, 97% recall, and 98% F1-score, as confirmed by the classification report and confusion matrix. This model was also the most stable when tested on the Android system, while EfficientNetB2 and B3 produced less satisfactory outcomes. These findings demonstrate that combining CNN and Fuzzy Tsukamoto improves the classification accuracy of images with high visual similarity. The proposed system has the potential to be applied as a direct plant identification tool in the field and can be further extended to classify other visually similar plants Prodi Teknik Informatika FIK Universitas Muslim Indonesia Majelis Diktilitbang PP Muhammadiyah (Majelis Diktilitbang PP Muhammadiyah) 2025-12-09 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2857 10.33096/ilkom.v17i3.2857.276-291 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 276-291 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 276-291 2548-7779 2087-1716 10.33096/ilkom.v17i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2857/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/2857/790 Copyright (c) 2025 Fajar Rahardika Bahari Putra, Muhammad Rizki Setyawan, Ahmad Ilham, Dimas Adi Suseno https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1455 2026-04-20T06:02:05Z ILKOM:ART driver

User Interface and User Experience Analysis of Kejar Mimpi Mobile Application using the User-Centered Design Method User Interface and User Experience Analysis of Kejar Mimpi Mobile Application Using The User-Centered Design Method Angela, Brigitha Valensia Wulansari, Tina Tri Riyayatsyah, Riyayatsyah Fitrianto, Yuli Rahim, Abdul User Interface; User Experience; User Centered Design; Kejar Mimpi Application User Interface; User Experience; User Centered Design; Kejar Mimpi Application User criticism on the Play Store revealed some flaws in the Kejar Mimpi App review. Observations were made on research that discussed the Kejar Mimpi Application, and it discovered that no prior research on User Experience and User Interface had been conducted. Interviews will be conducted to collect additional data, and the initial questionnaire will be distributed on May 6, 2022. Developers and designers use User-Centered Design (UCD) design methodologies to ensure that the product or system meets the users' needs. This study used the System Usability Scale (SUS) and User Experience Questionnaire (UEQ) methods or techniques to assess user interface and user experience. This research has produced as many as 24 design recommendations and a style guide. The final evaluation results measured using the SUS questionnaire increased the average value by 14,9% from a value of 67 (adjective rating Ok category, grade scale D, High Marginal category) to 77 (adjective rating Good, grade scale C, Acceptable category). The results of the UEQ also have gained an average increase in the ratio, where previously most were in below-average positions, now in good positions. Research on the user interfaces analysis and user experience of the Kejar Mimpi Application has the potential to be developed further. Therefore, the author has several suggestions that can be used for further research so that prototype part can be developed again to be more responsive and use different methods for evaluation of design results, such as Eye Tracking, Cognitive Walkthrough, and Heuristic Evaluation. User criticism on the Play Store revealed some flaws in the Kejar Mimpi App review. Observations were made on research that discussed the Kejar Mimpi Application and discovered that no prior research on User Experience and User Interface had been conducted. Interviews will be conducted to collect additional data, and the initial questionnaire will be distributed on May 6, 2022. User-Centered Design (UCD) design methodologies are used by developers and designers to ensure that the product or system meets the needs of the users. This study used the System Usability Scale (SUS) and User Experience Questionnaire (UEQ) methods or techniques to assess user interface and user experience. This research has produced as many as 24 design recommendations accompanied by a style guide. The final evaluation results measured using the SUS questionnaire increased the average value by 14,9% from a value of 67 (adjective rating Ok category, grade scale D, High Marginal category) to 77 (adjective rating Good, grade scale C, Acceptable category). The results of the UEQ also gained an average increase in the ratio, where previously most were in below-average positions, now in good positions. Research on the user interface analysis and user experience of the Kejar Mimpi Application has the potential to be developed further, therefore the author has several suggestions that can be used for further research so that part prototype can be developed again to be more responsive and use different methods for evaluation of design results, such as Eye Tracking, Cognitive Walkthrough, and Heuristic Evaluation. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Mulia University Universitas Mulia 2023-04-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1455 10.33096/ilkom.v15i1.1455.1-10 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 1-10 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 1-10 2548-7779 2087-1716 10.33096/ilkom.v15i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1455/pdf Copyright (c) 2023 Brigitha Valensia Angela, Tina Tri Wulansari, Riyayatsyah Riyayatsyah, Yuli Fitrianto, Abdul Rahim. https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/300 2026-04-20T06:16:56Z ILKOM:ART driver

Penerapan Metode C4.5 untuk Klasifikasi Mahasiswa Berpotensi Drop Out Nasrullah, Asmaul Husnah Drop Out; Classification; C4.5 Method The quality of education in universities can be seen from the high level of student success and the low failure of students. One indicator of student failure is the case of Drop Out (stop study). The problem of Drop Out becomes something interesting to study, because this can affect the quality of education. Faculty of Economics UNISAN Gorontalo is a favorite Faculty in UNISAN Gorontalo so it has a number of students of approximately 1000 students until 2017. But the ratio of the number of graduate students and not pass unbalanced. So as to produce the number of students Drop Out approximately 200 students per year. To solve the problem, we proposed a new model by utilizing a C4.5 computation method, in order to produce a pattern based on the results of the correct classification in determining the potential Drop Out students. The results obtained from the application of method C4.5 in this research is the discovery of 17 rules that can be used as a pattern to determine the potential students Drop Out. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-09-02 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/300 10.33096/ilkom.v10i2.300.244-250 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 244-250 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 244-250 2548-7779 2087-1716 10.33096/ilkom.v10i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/300/154 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/300/71 Copyright (c) 2018 Asmaul Husnah Nasrullah https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/23 2026-04-20T06:19:26Z ILKOM:ART driver

Interoperabilitas Sistem Terdistribusi Berbasis Protokol Soap Wardana, Mohamad Ali Rahman, Rahman SOAP , e - KTP Sistem e-KTP yang yang diadopsi pemerintah menerapkan sistem database nasional kependudukan terpusat. Database ini menjadi referensi resmi dan yang dipercaya untuk mengidentifikasi status dan informasi kewarganegaraan seseorang. Siapapun baik perseorangan maupun lembaga dapat menjadikan referensi database nasional untuk memproses data kependudukan seseorang melalui sistem perangkat lunak kantor, lembaga atau struktur pemerintahan lokal di Indonesia. Kehadiran teknologi sistem terdistribusi dengan jenis arsitektur berbasis protokol SOAP, memungkinkan komunikasi perangkat lunak lintas platform sistem operasi dan bahasa pemrograman, berkomunikasi dengan model database apapun yang menyediakan antarmuka aplikasi layanan web. Penelitian ini telah menguji arsitektur SOAP untuk mengakses struktur data kependudukan dengan menggunakan perangkat lunak lintas bahasa pemrograman (Java dan Visual Basic .Net 2008). Pengujian menunjukan kinerja yang dapat diandalkan dengan tingkat akurasi data perolehan dan validasi record penduduk 100%. Hasil lainnya yang berjalan baik adalah pada pengujian Cross Tringgering-Event dan Penanganan struktur data server pada sisi oleh client. Meskipun demikian fleksibelitas penggunaan tipe data kompleks dan kecepatan respon server kurang begitu baik. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2016-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/23 10.33096/ilkom.v8i1.23.57-62 ILKOM Jurnal Ilmiah; Vol 8, No 1 (2016); 57-62 ILKOM Jurnal Ilmiah; Vol 8, No 1 (2016); 57-62 2548-7779 2087-1716 10.33096/ilkom.v8i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/23/18 Copyright (c) 2016 Mohamad Ali Wardana, Rahman Rahman https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2894 2026-04-27T07:10:10Z ILKOM:ART driver

Automated Hyperparameter Optimization of Lightweight YOLO11s for Efficient Road Crack Detection Angreni, Ida Ayu Ari Diyanti, Diyanti Valentine, Vega Detection; Hyperparameter Tuning; Model; Road Crack; YOLO11s; Automatic road crack detection plays an essential role in infrastructure maintenance, where rapid and accurate visual inspection is required under real-world conditions. Although deep learning–based detection models have demonstrated promising performance, many existing approaches rely on computationally intensive architectures or require manual hyperparameter tuning, which limits their efficiency and real-time applicability. Moreover, the integration of lightweight detection models with automated hyperparameter optimization remains relatively underexplored.This study proposes an efficient road crack detection framework based on a lightweight YOLO11s architecture enhanced through automated hyperparameter optimization using Optuna on the DeepCrack dataset. The proposed methodology includes image preprocessing through data augmentation, normalization, and resizing to improve model robustness. Subsequently, key hyperparameters including learning rate, weight decay, dropout rate, and optimizer selection are automatically optimized to obtain the best model configuration. Experimental results indicate that the optimized YOLO11s model achieves a precision of 90.4%, recall of 86.8%, mAP@0.5 of 89.8%, and mAP@0.5:0.95 of 63.6% after 25 optimization trials. These results demonstrate that automated hyperparameter optimization can significantly improve detection performance while maintaining computational efficiency. The main contribution of this study lies in the systematic integration of automated hyperparameter tuning within a lightweight YOLO-based framework, providing a resource efficient and accurate solution suitable for real-time and large-scale road damage monitoring Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2026-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2894 10.33096/ilkom.v18i1.2894.138-150 ILKOM Jurnal Ilmiah; Vol 18, No 1 (2026); 138-150 ILKOM Jurnal Ilmiah; Vol 18, No 1 (2026); 138-150 2548-7779 2087-1716 10.33096/ilkom.v18i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2894/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/2894/796 Copyright (c) 2026 Ida Ayu Ari Angreni, Diyanti Diyanti, Vega Valentine https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1357 2026-04-20T06:02:05Z ILKOM:ART driver

Analysis of the Ensemble Method Classifier's Performance on Handwritten Arabic Characters Dataset Manga', Abdul Rachman Handayani, Anik Nur Herwanto, Heru Wahyu Asmara, Rosa Andrie Sulistya, Yudha Islami Kasmira, Kasmira Ensemble Method; Voting Classifiers; Arabic Character Handwriting; Evaluation Model. Arabic character handwriting is one of the patterns and characteristics of each person's writing. This characteristic makes Arabic writing more challenging if the letter recognition process is based on a dataset of Arabic scripts. This Arabic script has been presented in a dataset totaling 16800, each representing a class of hijaiyah letters starting from alif to yes, consisting of 600 data for each class. The accuracy of the data used can be increased using the ensemble method. By using multiple algorithms at simultaneously, the ensemble technique can raise the level or result of a score in machine learning. This study's primary goal is to evaluate the ensemble method classifier's performance on datasets of handwritten Arabic characters. The classifier uses the ensemble method by applying the proposed soft voting to provide a multiclass classification of three machine learning algorithms, namely, SVM, Random Forest, and Decision Tree for classification. This research process produces an accuracy value for the voting classifier of 0.988 and several other SVM algorithms with an accuracy of 0.103, a random forest with an accuracy of 1.0, and a decision tree with an accuracy of 0.134. The test results used the confusion matrix evaluation model, including accuracy, precision, recall, and f1-score of 0.99. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-04-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1357 10.33096/ilkom.v15i1.1357.186-192 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 186-192 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 186-192 2548-7779 2087-1716 10.33096/ilkom.v15i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1357/pdf Copyright (c) 2023 Yudha Islami Sulistya https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/388 2026-04-20T06:13:33Z ILKOM:ART driver

IMPLEMENTASI METODE WEIGHTED PRODUCT DALAM SISTEM PENUNJANG KEPUTUSAN PEMBUANGAN MATERIAL NOT GOOD (NG) PRODUKSI Mujahidin, Mujahidin Purba, Arif Budimansyah Agustian, Tresa Weighted Product; Material Not Good (NG); Weighted product; Decision Support System; SDLC Waterfall Bad Material is a product whose condition is Damaged or Not In accordance with a predetermined size, in the matter of this NG material can be determined what materials must be disposed of and what materials must be repaired. In the material there are several criteria that can be used as a yardstick to determine whether the NG material is directly discharged into production waste or not. To determine the NG material production can be done by using a weighted product support system. Ranking determination can be done by looking at the number of criteria in the alternative NG production by calculating weighted products can help in making decisions in the disposal of NG material and only choose one material to be disposed of into production waste whose status cannot be repaired again and the final result of the Weighted Product method has a final value that changes according to the number of alternatives. Prodi Teknik Informatika FIK Universitas Muslim Indonesia STMIK Kharisma Karawang 2019-05-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/388 10.33096/ilkom.v11i1.388.25-33 ILKOM Jurnal Ilmiah; Vol 11, No 1 (2019); 25-33 ILKOM Jurnal Ilmiah; Vol 11, No 1 (2019); 25-33 2548-7779 2087-1716 10.33096/ilkom.v11i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/388/172 Copyright (c) 2019 Mujahidin Mujahidin, Arif Budimansyah Purba, Tresa Agustian https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/67 2026-04-20T06:18:43Z ILKOM:ART driver

SISTEM MANAJEMEN DATA MONOGRAFI DI KELURAHAN SIDODADI Yudhana, Anton Umar, Rusydi Alameka, Faza Kelurahan, Monografi, Database, Website Kelurahan merupakan salah satu lembaga yang mempunyai peranan penting dalam pemerintahan. Salah satu instansi pemerintahan yang dituntut dalam memperbaharui data monografi wilayahnya yaitu kelurahan Sidodadi yang berada pada kecamatan Samarinda ULU. Manfaat data monografi adalah mempermudah pihak yang ingin memerlukan informasi dan data dari suatu wilayah khususnya data monografi kelurahan Sidodadi.Dalam penelitian ini dijelaskan tentang perancangan dan pengembangan data monografi. Dalam pengembangan sistem ini penulis menggunakan pendekatan Model Incremental yang setiap tahapan-tahapan tersebut dilakukan secara berurutan. Setiap bagian yang sudah selesai dilakukan testing kemudian dikirim kepada pemakai untuk langsung dapat digunakan. Pembuatan sistem ini menggunakan Sistem Informasi terintegrasi server-side berbasis website yang memungkinkan pengembangan sistem yang dinamis dengan reusability. Data disimpan dalam bentuk database, sehingga mempunyai efisiensi dan integritas yang tinggi. Pengembangan dan perubahan sistem dapat dilakukan dengan mudah dan terpusat pada sisi server. Sedangkan program aplikasi tidak perlu diinstall dan didistribusikan kepada setiap client atau web browser. Prodi Teknik Informatika FIK Universitas Muslim Indonesia universitas ahmad dahlan 2016-12-11 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/67 10.33096/ilkom.v8i3.67.167-173 ILKOM Jurnal Ilmiah; Vol 8, No 3 (2016); 167-173 ILKOM Jurnal Ilmiah; Vol 8, No 3 (2016); 167-173 2548-7779 2087-1716 10.33096/ilkom.v8i3 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/67/43 Copyright (c) 2016 Faza Alameka https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1590 2026-04-20T05:59:42Z ILKOM:ART driver

Sentiment Analysis for Online Learning using the Lexicon-Based Method and the Support Vector Machine Algorithm Sentiment Analysis for Online Learning using The Lexicon-Based Method and The Support Vector Machine Algorithm Anam, M. Khairul Fitri, Triyani Arita Agustin, Agustin Lusiana, Lusiana Firdaus, Muhammad Bambang Nurhuda, Agus Tri Lexicon Based; Online Learning; Sentiment Analysis; Support Vector Machine Lexicon Based; Online Learning; Sentiment Analysis; Support Vector Machine The pros and cons regarding online learning has been a hot topic in society, both on social media and in the real world. Indonesian netizens still post opinions about online learning on social media such as Twitter. This study aims to analyze public comments to determine whether the trend of the comments is positive, negative, or neutral. The classification of netizen opinions is called sentiment analysis. This study applies 2 ways of carrying out sentiment analysis. The first stage employs the SVM algorithm with data labeling automatically obtained from the Emprit Academy drone portal while the second stage is still using the SVM algorithm but the data labeling with lexicon-based method. The results of this study are comparisons of labels obtained automatically from the Emprit Academy drone portal and labeling using lexicon based. The SVM algorithm obtains an accuracy of 90%, while the use of lexicon-based increases the accuracy value by 5% to 95%. It can be concluded that labeling data using a lexicon-based method can improve the accuracy of the SVM algorithm. The pros and cons regarding online learning has been a hot topic in society, both on social media and in the real world. Indonesian netizens still post opinions about online learning on social media such as Twitter. This study aims to analyze public comments to determine whether the trend of the comments is positive, negative, or neutral. The classification of netizen opinions is called sentiment analysis. This study applies 2 ways of carrying out sentiment analysis. The first stage employs the SVM algorithm with data labeling automatically obtained from the Emprit Academy drone portal while the second stage is still using the SVM algorithm but the data labeling with lexicon-based method. The results of this study are comparisons of labels obtained automatically from the Emprit Academy drone portal and labeling using lexicon based. The SVM algorithm obtains an accuracy of 90%, while the use of lexicon-based increases the accuracy value by 5% to 95%. It can be concluded that labeling data using a lexicon-based method can improve the accuracy of the SVM algorithm. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-08-16 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1590 10.33096/ilkom.v15i2.1590.290-302 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 290-302 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 290-302 2548-7779 2087-1716 10.33096/ilkom.v15i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1590/pdf Copyright (c) 2023 M. Khairul anam, Triyani Arita Fitri, Triyani Arita Fitri, Agustin Agustin, Agustin Agustin, Lusiana Lusiana, Lusiana Lusiana, Muhammad Bambang Firdaus, Muhammad Bambang Firdaus, Agus Tri Nurhuda, Agus Tri Nurhuda https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/441 2026-04-20T06:13:16Z ILKOM:ART driver

PENGAPLIKASIAN CERTAINTY FACTOR PADA SISTEM PAKAR UNTUK MENDIAGNOSA PENYAKIT CAMPAK RUBELLA PENGAPLIKASIAN CERTAINTY FACTOR PADA SISTEM PAKAR UNTUK MENDIAGNOSA PENYAKIT CAMPAK RUBELLA Zuhriyah, Sitti Wahyuningsih, Pujianti Certainty factor, Campak rubella, Sistem pakar. Certainty factor; Rubella measles; Expert system Campak rubella merupakan penyakit yang dapat menyerang ibu hamil, balita, anak-anak, dan orang dewasa. Tujuan penelitian ini adalah penggunaan metode certainty factor pada aplikasi sistem pakar berbasis website untuk mendiagnosa penyakit campak rubella. Pemanfatan teknologi informasi pada aplikasi sistem pakar dapat membantu masyarakat dalam mendeteksi penyakit campak rubella sejak dini. Certainty factor merupakan salah satu metode yang dapat digunakan untuk menghadapi suatu permasalahan yang belum pasti jawabannya. Pada penelitian ini, metode certainty factor telah diaplikasikan pada aplikasi sistem pakar untuk mendiagnosa penyakit campak rubella berdasarkan gejala penyakit yang dirasakan oleh pasien. Hasil dari penelitian ini adalah sistem pakar berbasis website dapat memberikan informasi dan mendiagnosa gejala penyakit campak rubella sesuai dengan pertanyaan yang diajukan oleh sistem pakar dan gejala penyakit yang dirasakan oleh pasien.  Rubella measles is a disease that can infect to the pregnant mothers, toddlers, children, and adults. The purpose of this study is applicate the certainty factor method to the expert system application based on website to diagnose the rubella measles disease. The utilization of information technology into the expert system application can help society to detect the rubella measles disease early. Certainty factor is one method that can be used to handle a problem that is uncertain the answer. In this study, the certainty factor method has been applied on expert system application to diagnose rubella measles based on symptoms of the disease felt by patients. The result of this study is an expert system based on the website can provide information and diagnose symptoms of rubella measles following the questions proposed by the system and symptoms of the disease felt by the patient. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2019-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/441 10.33096/ilkom.v11i2.441.159-166 ILKOM Jurnal Ilmiah; Vol 11, No 2 (2019); 159-166 ILKOM Jurnal Ilmiah; Vol 11, No 2 (2019); 159-166 2548-7779 2087-1716 10.33096/ilkom.v11i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/441/188 Copyright (c) 2019 Sitti Zuhriyah, Pujianti Wahyuningsih https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1608 2026-04-20T05:58:32Z ILKOM:ART driver

Z-Score and Floyd Warshall Algorithms for Determining Alternative Routes of Mugging-Prone Areas in Medan City, Indonesia Dinata, Rozzi Kesuma Bustami, Bustami Fiasari, Fiasari Retno, Sujacka Z-Score; Floyd Warshall; Mugging; Medan; System This study analyzes and implements the Floyd Warshall algorithm using Z-Score to track alternative routes to areas in Medan City, Indonesia that are prone to mugging. The data was obtained from Porlestabes (Police station) Medan-Indonesia. This study employed the Z-Score rank method to rank specific values and determine the levels of crime-prone areas. The highest and lowest levels of crime-proneness were identified using the Z-Score method, and the Floyd Warshall Algorithm is used to identify alternative routes to avoid such areas. The language used in this study adheres to objective and formal writing principles, with value-neutral and clear terminology employed throughout.  The results of this analysis showed that out of 99 roads across 18 districts, 4.04% of them were classified as very high prone, 9.09% as high prone, 11.11% as prone, and 75.76% as low prone. The search results from conducting alternative route analysis with the Floyd Warshall algorithm on Perintis Kemerdekaan street indicate the identification of the safest routes. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-12-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1608 10.33096/ilkom.v15i3.1608.436-444 ILKOM Jurnal Ilmiah; Vol 15, No 3 (2023); 436-444 ILKOM Jurnal Ilmiah; Vol 15, No 3 (2023); 436-444 2548-7779 2087-1716 10.33096/ilkom.v15i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1608/pdf Copyright (c) 2023 Rozzi Kesuma Dinata, Bustami Bustami, Fiasari Fiasari, Sujacka Retno https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/489 2026-04-20T06:12:56Z ILKOM:ART driver

ANALISIS PERFORMA METODE K-NEAREST NEIGHBOR UNTUK IDENTIFIKASI JENIS KACA Baharuddin, Mus Mulyadi Azis, Huzain Hasanuddin, Tasrif K-Nearest Neighbor; classification; supervised learning; data mining; machine learning Nowadays, the industry makes various types of goods that have glass-based materials, float car window panes, non-float building windows, lamps, jars, and tableware. These glasses have the same production material, the difference between one and the other is the composition of the production material. K-Nearest Neighbor (KNN) algorithm which is one of the classification methods in data mining and also a supervised learning algorithm in machine learning is a method for classifying objects based on learning data that is the closest distance to the object.. This study discusses the performance measurement (accuracy, precision, recall and f-measure) of the KNN method with a variety of values on 1000 glass type production data objects obtained from the central UCI Machine Learning Repository dataset. The conclusion of this research is the results of the value of K = 3 to K = 9, the best performance values obtained at K = 3, where the level of accuracy reaches 64%, 63% precision, 71% recall, and F-Measure of 67%. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2019-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/489 10.33096/ilkom.v11i3.489.269-274 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 269-274 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 269-274 2548-7779 2087-1716 10.33096/ilkom.v11i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/489/201 Copyright (c) 2019 Mus Mulyadi Baharuddin, Huzain Azis, Tasrif Hasanuddin https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/121 2026-04-20T06:18:00Z ILKOM:ART driver

PENERAPAN PERBANDINGAN METODE AHP-TOPSIS DAN ANP-TOPSIS MENGUKUR KINERJA SUMBER DAYA MANUSIA DI GORONTALO Kaluku, Moh Ramdhan Arif Pakaya, Nikmasari AHP, ANP, TOPSIS, KINERJA, SDM Kinerja merupakan faktor kunci sebuah instansi pemerintahan untuk mengelola SDM. Kinerja SDM pada instansi menunjukkan ukuran kualitas pekerjaan dan digunakan sebagai ukuran untuk mengamati tingkat kinerja. Kinerja yang kurang akan berdampak pada kualitas perkerjaan yang akan dilakukan, terutama pada pelayanan kepada masyarakat. Penelitian ini bertujuan untuk membandingkan hasil yang diperoleh menggunakan metode Analytical Hierarchy Process (AHP)- Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) dengan Analytic Network Process (ANP) TOPSIS dalam pengambilan keputusan untuk mencari nilai yang tertinggi. Pada penelitian ini, metode AHP dan ANP digunakan untuk mencari bobot dari masing-masing kriteria menggunakan parameter dari nilai yang dimasukan untuk memperoleh bobot prioritas, yang nantinya akan digunakan dalam perhitungan TOPSIS. Hasil penelitian menunjukkan bahwa perbandingan kedua metode memiliki perbedaan dalam menghitung kinerja dari SDM di Gorontalo. Dari penelitian diperoleh nilai kinerja tertinggi dengan menggunakan metode AHP-TOPSIS adalah 0,6549 sedangkan nilai tertinggi dengan menggunakan metode ANP-TOPSIS adalah 0,5906.  Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-08-23 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/121 10.33096/ilkom.v9i2.121.124-131 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 124-131 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 124-131 2548-7779 2087-1716 10.33096/ilkom.v9i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/121/77 Copyright (c) 2017 Moh Ramdhan Arif Kaluku, Nikmasari Pakaya https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1927 2026-04-20T05:57:29Z ILKOM:ART driver

Classification of Correlation Patterns Based on electrocardiogram Data of Heart Defects Using the Pearson Correlation Coefficient Method Sumiati, Sumiati Fernando, Donny Hasoloan, Hamonangan Iman Purnamasari, Marlia Keyword: electrocardiogram, pearson correlation coefficient, symptoms, diagnosis, heart disease This study was conducted to map the relationship between a symptom and the type of heart disease, based on the results of the electrocardiogram medical record data. The purpose of this study was to apply a symptom correlation pattern based on electrocardiogram data of heart abnormalities. Where the results of this study produce values that determine symptoms that have a very close relationship with the type of heart disorder, and make an analysis to diagnose normal and abnormal heart disorders using the Pearson Correlation Coefficient (PCC) approach. The results show that the relationship between symptoms has a very strong relationship. dominant with normal heart defects is the relationship between AV conduction duration and other symptoms because the relationship between AV conduction duration and other symptoms has a very strong average level of association. symptoms also have a strong average level of association, while the relationship between other symptoms appears to have a moderate relationship and does not even have any relationship with someone who is identified as having a heart abnormality diagnosis (abnormal) and normal heart Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1927 10.33096/ilkom.v16i1.1927.100-107 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 100-107 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 100-107 2548-7779 2087-1716 10.33096/ilkom.v16i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1927/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1927/610 Copyright (c) 2024 Sumiati, Donny Fernando, Viktor Vekky Ronald Repi, Hamonangan Iman Hasoloan, Marlia Purnamasari https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/539 2026-04-20T06:09:30Z ILKOM:ART driver

Algoritma K-Nearest Neighbor dengan Euclidean Distance dan Manhattan Distance untuk Klasifikasi Transportasi Bus Dinata, Rozzi Kesuma Akbar, Hafizal Hasdyna, Novia Komparasi; Klasifikasi; K-Nearest Neighbor; Euclidean Distance; Manhattan Distance K-Nearest Neighbor is a data mining algorithm that can be used to classify data. K-Nearest Neighbor works based on the closest distance. This research using the Euclidean and Manhattan distances to calculate the distance of Lhokseumawe-Medan bus transportation. Data that used in this research was obtained from the Organisasi Angkutan Darat Kota Lhokseumawe. The results of the test with k = 3 has obtained the percentage of 44.94% for Precision, 37.06% Recall, and 81.96% Accuracy for the performance of K-NN with Euclidean Distance. Whereas by using Manhattan Distance the result obtained was 45.49% for Precision, 36.39% Recall, and 84.00% Accuracy. The result shown that Manhattan Distance obtained the highest accuracy, with the difference of 2.04% higher than Euclidean Distance. It indicates that Manhattan Distance is more accurate than Euclidean Distance to classify the bus transportation. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-08-27 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/539 10.33096/ilkom.v12i2.539.104-111 ILKOM Jurnal Ilmiah; Vol 12, No 2 (2020); 104-111 ILKOM Jurnal Ilmiah; Vol 12, No 2 (2020); 104-111 2548-7779 2087-1716 10.33096/ilkom.v12i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/539/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/539/192 Copyright (c) 2020 Rozzi Kesuma Dinata https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/816 2026-04-20T06:04:29Z ILKOM:ART driver

'Pakarena' dance image classification using convolutional neural network algorithm Ibrahim, Abdul Rachmat, Rachmat Makassar Community Dance; Convolutional Neural Networks; Image One of the riches of the Indonesian nation comes from the diversity of ethnicities and cultures, especially dance, which is the culture of the Indonesian people, starting from their ancestors until now, their authenticity is still maintained. The wrong cultural dance that develops, especially in South Sulawesi, which consists of four (4) ethnic groups, namely: Bugis, Makassar, Toraja and Mandar, which have their own dance dances from each tribe in South Sulawesi to maintain this dance. There is a need for collaboration between local community leaders, government and researchers, especially researchers to raise dance dances from the Makassar Tribe called Pakkarena dance using the Convolutional Neural Network (CNN) method to the Pakarena dance image in distinguishing or classifying an object on digital images with an accuracy level of 95 75%. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-08-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/816 10.33096/ilkom.v13i2.816.134-139 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 134-139 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 134-139 2548-7779 2087-1716 10.33096/ilkom.v13i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/816/pdf Copyright (c) 2021 Rachmat memet https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/148 2026-04-20T06:17:39Z ILKOM:ART driver

PREDIKSI HARGA KOMODITI JAGUNG MENGGUNAKAN K-NN DAN PARTICLE SWARM OPTIMAZATION SEBAGAI FITUR SELEKSI Lasulika, Mohamad Efendi Time Series; K-Nearest Neighbor; Particle Swarm Optimazation Jagung merupakan komponen terpenting pakan pabrikan di dunia, terutama di daerah tropis. Fluktuasi harga produk pertanian akan mengakibatkan ikut berfluktuasinya pendapatan yang diterima oleh petani dari hasil produksi pertanian mereka. Salah satu upaya untuk mengantisipasi terjadinya fluktuasi harga adalah dengan melakukan peramalan harga. Peramalan harga dimaksudkan untuk melakukan prakiraan/prediksi harga masa depan dalam kurun waktu tertentu, dengan hasil keluaran berupa harga masa depan. metode KNN dapat digunakan untuk memprediksi harga komoditi. Hasil eksperiment yang telah dilakukan peneliti menunjukkan bahwa algoritma K-NN berbasis Particle Swarm Optimazation lebih baik dibandingkan dengan algoritma K-NN tanpa fitur seleksi. Berdasarkan hasil penelitian nilai RMSE terendah terdapat pada K-Nearest Neighbor berbasis Particle Swarm Optimazation untuk data jagung dengan variabel periode 4 parameter k 7 nilai population 5 Max Of Generation 40 dengan nilai RMSE 0,06 Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/148 10.33096/ilkom.v9i3.148.233-238 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 233-238 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 233-238 2548-7779 2087-1716 10.33096/ilkom.v9i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/148/99 Copyright (c) 2017 Mohamad Efendi Lasulika https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2326 2026-04-20T05:54:17Z ILKOM:ART driver

Performance Analysis of LoRaWAN Communication Utilizing the RFM96 Module Yassir, Muhammad Soepandi, Harry Hanani, Ajib Prakasa, Johan Ericka Wahyu Puspitadewi, Ganis Chandra Wibowo, Sastya Hendri Adi, Puput Dani Prasetyo Kitagawa, Akio Indonesia Provider; LoRaWAN; LoRa Communication; Low Power Consumption; LPWA; LPWAN This research discusses the utilization of LoRa and LoRaWAN or Low Power Wide Area (LPWA) and Low Power Wide Area Network (LPWAN). In this study, the application server is utilized using Telkom IoT. In its utilization, Telkom IoT can provide comprehensive results regarding LoRa quality of service capabilities such as bit rate, latency, and longitude and latitude data. Terrestrial measurements conduct tests in different areas with different conditions that cause different data obstruction, with several LoRa end-node points transmitting data with low bit-rate. For example, heart rate data. Some other parameters are the spreading factor (SF) and power consumption. Some parameters that determine the quality of transmitting data include the Spreading Factor and the Bandwidth used. From the analysis dan Experiment results, the Delay (ms) generated from measurements using RFM96 LoRa for IoT is around 0.02 seconds or 20 ms to around 0.05 seconds or 50 ms, and sometimes it can reach 0.07 ms to 0.09 ms. RSSI and SNR show the quality of the signal obtained which will provide a Quality of Service (QoS) value. From the measurement results using Telkom IoT in several times of data collection and testing, the average RSSI (-dBm) is at -110 dBm to -115 dBm. While SNR is at -10 dB to -16 dB. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-12-12 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2326 10.33096/ilkom.v16i3.2326.255-270 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 255-270 ILKOM Jurnal Ilmiah; Vol 16, No 3 (2024); 255-270 2548-7779 2087-1716 10.33096/ilkom.v16i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2326/pdf Copyright (c) 2024 Muhammad Yassir, Harry Soepandi, Ajib Hanani, Johan Ericka Wahyu Prakasa, Ganis Chandra Puspitasdewi, Sastya Hendri Wibowo, Puput Dani Prasetyo Adi, Akio Kitagawa https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/619 2026-04-20T06:05:19Z ILKOM:ART driver

Penentuan Harga Tandan Buah Segar (TBS) Kelapa Sawit Menggunakan Metode Fuzzy Logic Amriana, Amriana Kasim, Anita Ahmad Maghfirat, Maghfirat Determination; Price; Fresh Fruit Bunches; Palm Oil; Fuzzy Logic Tujuan penelitian ini adalah membuat sistem penentuan harga Tandan Buah Segar kelapa sawit menggunakan metode Fuzzy Logic. Perkebunan kelapa sawit adalah perkebunan yang memiliki sumber daya alam yang dapat menghasilkan keuntungan besar, karena digunakan sebagai minyak goreng dan masih banyak lagi. TBS kelapa sawit terdiri dari Crude Palm Oil (CPO) yaitu minyak daging buah dan Palm Kernel (PK) yaitu inti biji sawit. Penelitian ini membuat sistem menggunakan 5 variabel input yaitu harga CPO, harga IKS, Indeks K, Rendemen CPO dan Rendemen IKS, serta satu variabel output yaitu harga TBS kelapa sawit. Sistem ini menggunakan metode Fuzzy Logic karena dalam penelitian ini terdapat suatu fuzzy yang dapat ditentukan, yaitu harga TBS kelapas sawit. Sistem ini menggunakan 100 data untuk diuji menggunakan MAPE sehingga didapatkan  nilai persentase sebesar 85.75%. Sedangkan nilai rata-rata dari selisih antara data aktual dengan data hasil fuzzy mamdani adalah sebesar 17852 dengan rata-rata persentase kesalahan dari fuzzy mamdani adalah sebesar 14.25%. Hasil dari sistem ini adalah variabel output harga TBS kelapa sawit berdasarkan 5 variabel input. Metode Fuzzy Logic Mamdani menentukan hasil dari nilai yang tidak pasti. Proses fuzzy logic dimulai dari pembentukan himpunan fuzzy, kemudian aplikasi fungsi implikasi, lalu tahap komposisi aturan, setelah itu tahap deffuzifikasi. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/619 10.33096/ilkom.v12i3.619.236-244 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 236-244 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 236-244 2548-7779 2087-1716 10.33096/ilkom.v12i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/619/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/619/184 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/619/185 Copyright (c) 2020 Maghfirat Maghfirat, Amriana Amriana, Anita Ahmad Kasim https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1092 2026-04-20T06:03:47Z ILKOM:ART driver

Implementation of Fuzzy Logic in Fish Dryer Design Yanti, Nur Nur, Taufik Randis, Randis fuzzy logic; microcontroller; fish dryer The fish drying process aims to preserve fish, so as to reduce losses due to the spoilage process. There is sunlight, the drying process does not experience obstacles, however if it is raining, it will take a longer time, and give a smell effect that disturbs the surrounding environment for a relatively long time. Fish dryer designed to work automatically, aims to speed up drying time using fuzzy logic, thus minimizing rot and air pollution due to the smell of the fish drying process. The design of the tool used experimental methods through literature study as a source of study, planning and manufacturing of fish drying equipment consists of hardware using the Arduino Mega 2560 microcontroller, temperature sensor of DHT 22, load cell sensor, humidity sensor, fan, heating element and LCD and software using the Fuzzy Mamdani method. The results obtained are the weight of the fish that has undergone a drying process using an automatic drying device, namely 500 grams, indicating that the drying process is 50% of the initial weight of 1000 grams, with a drying time of 4.48 hours, while drying time by drying or manually takes 45 hours. Shows the control system using fuzzy logic on fish drying equipment, speed up the drying time about 10 hours faster than the drying time by drying in the sun. So that it can increase the amount of dry fish production, reduce the smell in the environment around the drying, because the fish are in the dryer closed. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1092 10.33096/ilkom.v14i1.1092.39-51 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 39-51 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 39-51 2548-7779 2087-1716 10.33096/ilkom.v14i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1092/pdf Copyright (c) 2022 Nur Yanti, Taufik Nur, Randis Randis https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/178 2026-04-20T06:17:39Z ILKOM:ART driver

ANALISA ALGORITMA HAVERSINE FORMULA UNTUK PENCARIAN LOKASI TERDEKAT RUMAH SAKIT DAN PUSKESMAS PROVINSI GORONTALO Farid, Farid Yunus, Yulanda Analisa Algoritma Haversine; Lokasi Rumah Sakit; Puskesmas Pemerintah Provinsi Gorontalo saat ini dihadapkan pada suatu masalah yang berhubungan dengan layanan informasi data. Data layanan informasi yang berkaitan dengan data sarana puskesmas dan rumah sakit belum terinci, sehingga pemerintah kesulitan dalam pengambilan keputusan dalam bentuk peta digital sehingga kebanyakan masyarakat Gorontalo apabila mengalami masalah kesehatan seperti sakit, kecelakaan, meninggal dan lain-lain, akan sering mengalami kesulitan dalam mencari lokasi terdekat layanan kesehatan. Kegunaaan dari Algoritma Haversine Formula adalah digunakan untuk menghitung jarak antara dua titik di bumi berdasarkan panjang garis lurus antar dua titik tanpa mengabaikan kelengkungan yang dimiliki bumi. Berdasarkan hasil analisa Algoritma Haversine Formula dapat menghitung jarak antara lokasi setiap rumah sakit dan puskesmas yang ada di Provinsi Gorontalo dan berdasarkan jarak tersebut maka masyarakat dapat mengetahui jarak  lokasi terdekat antara rumah sakit ke rumah sakit lainnya, begitu juga dengan puskesmas ke puskesmas lainnya.  Prodi Teknik Informatika FIK Universitas Muslim Indonesia LEMLIT STMIK ICHSAN GORONTALO 2017-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/178 10.33096/ilkom.v9i3.178.353-355 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 353-355 ILKOM Jurnal Ilmiah; Vol 9, No 3 (2017); 353-355 2548-7779 2087-1716 10.33096/ilkom.v9i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/178/116 https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/178/33 Copyright (c) 2017 Farid Farid, Yulanda Yunus https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2363 2026-04-20T05:53:11Z ILKOM:ART driver

Quantum Computing Approach in K-Medoids Method for AIDS Disease Prediction Using Manhattan Distance Wahyudi, Mochamad Sintagel br Sianipar, Imeldi Pujiastuti, Lise Solikhun, Solikhun Kurniawan, Deny Clustering; Data Mining; K-Medoids; Manhattan Distance; Quantum Computing. Acquired Immunodeficiency Syndrome (AIDS) caused by the Human Immunodeficiency Virus (HIV) is one of the deadliest infectious diseases in the world. Understanding its spread and epidemiological characteristics is crucial for developing and preventing more effective treatments. This study uses the K-Medoids method with a quantum computing approach to predict AIDS based on clinical and demographic data. K-Medoids is chosen to group large amounts of data using a clustering technique that determines the center point (medoid) of each cluster, minimizing the overall distance between data in a cluster. The Manhattan distance is used because it is easier to process data. The quantum computing approach is used to overcome the limitations of classical computing when processing large-scale medical data. This study shows that the application of quantum algorithms to the K-Medoids method allows for faster and more accurate predictions in the diagnosis of AIDS. The tests carried out showed that the prediction accuracy of classical and quantum methods was comparable, namely 85%. The results support the great potential of quantum computing to improve the efficiency of medical predictions. The research involves converting data into quantum format, processing it with the K-Medoids algorithm, and evaluating its performance based on metrics such as intercluster distance and computation time. The research will also identify patterns and risk factor for the spread of AIDS that can be used to develop more effective health interventions. The conclusion of the research is that integrating the K-Medoids techniques can only increase the speed of data processing but also provide competitive accuracy compared to traditional techniques. This research opens up new possibilities in medical data analysis, especially when managing large and complex data sets. The bottom line is that these findings can help make better medical decisions and strategically support AIDS prevention and treatment efforts. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2025-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2363 10.33096/ilkom.v17i1.2363.44-53 ILKOM Jurnal Ilmiah; Vol 17, No 1 (2025); 44-53 ILKOM Jurnal Ilmiah; Vol 17, No 1 (2025); 44-53 2548-7779 2087-1716 10.33096/ilkom.v17i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2363/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/2363/629 Copyright (c) 2025 Mochamad Wahyudi, Imeldi Sintagel br Sianipar, Lise Pujiastuti, Solikhun, Deny Kurniawan https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/733 2026-04-20T06:04:29Z ILKOM:ART driver

Glucose level detection system in glucose solution using TCS3200 sensor with If-Else method Thoriq Al-Azis, Kemal Ma'arif, Alfian Sunardi, Sunardi Nuraisyah, Fatma Rusdiarna Indrapraja, Apik Non-Invasive; Glucose Solution; TCS3200 Sensor; If-Else; Arduino Early and routine examination of glucose levels plays an important role in preventing and controlling diabetes mellitus and maintaining the quality of life. Checking blood sugar levels by hurting the body (invasive) can lead to infections caused by needles. As an alternative, the examination is carried out in a non-invasive way using excretory fluid in the form of urine, which is reacted with Benedict's solution that create a color change. Experts in the laboratory only carry out an examination using non-invasive methods because in determining glucose levels, it requires accuracy and eye health factors. Therefore, a glucose level detection system was created using a sample of glucose solution to determine the system's parameters using the if-else method. The glucose level detection system is conducted by mixing the glucose solution with Benedict's solution to produce a color change. Then the reaction results are read by the TCS3200 sensor and processed by Arduino to be classified, according to predetermined parameters. The decision results based on the classification of the glucose level parameters that have been determined are displayed on a 16x2 LCD. The results achieved in this study on 10 samples of glucose solution that were tested and processed by the if-else method were successfully read and classified based on predetermined parameters. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-08-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/733 10.33096/ilkom.v13i2.733.110-116 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 110-116 ILKOM Jurnal Ilmiah; Vol 13, No 2 (2021); 110-116 2548-7779 2087-1716 10.33096/ilkom.v13i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/733/pdf Copyright (c) 2021 Kemal Thoriq Al-Azis, Alfian Maarif, Sunardi Sunardi, Fatma Nuraisyah, Apik Rusdiarna Indrapraja https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1254 2026-04-20T06:03:10Z ILKOM:ART driver

Deepfake Detection in Videos Using Long Short-Term Memory and CNN ResNext Abidin, Muhammad Indra Nurtanio, Ingrid Achmad, Andani Deepfake; ResNext CNN; LSTM Deep-fake in videos is a video synthesis technique by changing the people’s face in the video with others’ face. Deep-fake technology in videos has been used to manipulate information, therefore it is necessary to detect deep-fakes in videos. This paper aimed to detect deep-fakes in videos using the ResNext Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) algorithms. The video data was divided into 4 types, namely video with 10 frames, 20 frames, 40 frames and 60 frames. Furthermore, face detection was used to crop the image to 100 x 100 pixels and then the pictures were processed using ResNext CNN and LSTM. The confusion matrix was employed to measure the performance of the ResNext CNN-LSTM algorithm. The indicators used were accuracy, precision, and recall. The results of data classification showed that the highest accuracy value was 90% for data with 40 and 60 frames. While data with 10 frames had the lowest accuracy with 52% only. ResNext CNN-LSTM was able to detect deep-fakes in videos well even though the size of the image was small. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-12-19 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1254 10.33096/ilkom.v14i3.1254.178-185 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 178-185 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 178-185 2548-7779 2087-1716 10.33096/ilkom.v14i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1254/pdf Copyright (c) 2022 Muhammad Indra Abidin, Ingrid Nurtanio, Andani Achmad https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/232 2026-04-20T06:17:18Z ILKOM:ART driver

SISTEM PENDUKUNG KEPUTUSAN PENENTUAN PRIORITAS PEMBANGUNAN MENGGUNAKAN METODE PROMETHEE PADA DESA AYULA KECAMATAN RANDANGAN KABUPATEN POHUWATO PROVINSI GORONTALO Karim, Jorry Priorias; Pembangunan; Desa; PROMETHEE Permasalahan yang sering terjadi di desa yaitu tahap pembangunan didesa harus mempertimbangkan skala prioritas dan unsur keadilan, serta belum adanya Sistem Pendukung Keputusan untuk Penentuan Prioritas Pembangunan pada Desa Ayula Kecamatan Randangan dan juga sistem yang digunakan saat ini belum terkomputerisasi secara maksimal. Oleh karena itu, pada penelitian ini akan dirancang sebuah sistem pendukung keputusan untuk menentukan prioritas pembangunan.Metode yang digunakan adalah Metode MCDM digunakan untuk melakukan penilaian atau seleksi terhadap beberapa alternatif dalam jumlah terbatas. Salah satu metode penyelesaian masalah MCDM yaitu PROMETHEE yang merupakan salah satu metode penentuan urutan atau prioritas.Sistem inidirancang menggunakan bahasa Pemrograman PHP dengan Database MySQL, untuk membuatkan sebuah sistem pendukung keputusan baru yang berbasis komputerisasi yang merupakan salah satu alternatif yang baik dengan mengedepankan efektifitas dan efisien dalam Penentuan Prioritas Pembangunan.  Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2018-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/232 10.33096/ilkom.v10i1.232.86-91 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 86-91 ILKOM Jurnal Ilmiah; Vol 10, No 1 (2018); 86-91 2548-7779 2087-1716 10.33096/ilkom.v10i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/232/132 Copyright (c) 2018 Jorry Karim https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/3001 2026-04-20T05:50:20Z ILKOM:ART driver

Urban Traffic Volume Prediction using LSTM and Bi-LSTM: Performance Evaluation on the Metro Interstate Dataset Pranolo, Andri Saifullah, Shoffan Putra, Agung Bella Utama Dreżewski, Rafał Wibawa, Aji Prasetya LSTM; Bi-LSTM; Deep Learning; Time Series Forecasting; Urban Traffic Urban traffic forecasting underpins the mitigation of congestion, enhancement of road safety, and reduction of emissions in intelligent transportation systems. We benchmark Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM) models on the Metro Interstate Traffic Volume dataset under an identical preprocessing and training pipeline for a fair comparison. Using a 24-hour multivariate input window (temperature, rainfall, snowfall, cloud cover), LSTM delivers the best overall balance of accuracy and efficiency on the full test sequence (RMSE = 0.196, MAPE = 2.36%, R² = 0.480; 7,344 s training). Bi-LSTM achieves competitive short-window accuracy but underperforms on the full sequence (RMSE = 0.231, MAPE = 2.92%, R² = 0.280; 12,672 s training). We attribute the Bi-LSTM gap to prediction "flattening" over long horizons, i.e., over-smoothed peaks from bidirectional averaging, despite its slightly stronger short-segment fit. Compared with prior RNN/GRU/CNN baselines on the same data, LSTM improves variance explanation while remaining deployable for near-real-time use. We also examine seasonality (daily/weekly cycles), weather effects, and data imbalance (peak versus off-peak) as factors that shape model error. These results support LSTM as a practical default for city-scale forecasting and motivate future work with attention/Transformer encoders and richer exogenous signals (incidents, events). The findings inform policy by enabling proactive traffic management that can reduce delays, emissions, and crash risk through earlier, data-driven interventions. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2025-10-29 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/3001 10.33096/ilkom.v17i3.3001.227-240 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 227-240 ILKOM Jurnal Ilmiah; Vol 17, No 3 (2025); 227-240 2548-7779 2087-1716 10.33096/ilkom.v17i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/3001/pdf Copyright (c) 2025 Andri Pranolo, Shoffan Saifullah, Agung Bella Utama Putra, Rafał Dreżewski, Aji Prasetya Wibawa https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1149 2026-04-20T06:03:10Z ILKOM:ART driver

Predicting the success of the government’s program of lomaya (Regional PKH) in reducing poverty Sulaehani, Ruhmi Botutihe, Marniyati Husain Poverty reduction is one indicator of the success of development. The form of support from the Pohuwato Regency Government through the Social Service is to organize PKH-D, which is known as LOMAYA. It is one of the implementations of the Community Movement Towards Independent Prosperity (Gerakan Masyarakat Menuju Sejahtera Mandiri). This research was conducted to assist the government in predicting the level of development success indicated by the satisfaction of beneficiaries of lomaya. The method employed was the Naïve Bayes method and forward feature selection. The research data was obtained from a survey of lomaya beneficiaries in the last two years. The accuracy result obtained using the Naïve Bayes algorithm was 94.19%, while Naïve Bayes with the Forward Selection feature was only 94.03%. Therefore, the Naïve Bayes algorithm method is better than the Forward Selection based Naïve Bayes algorithm. Forward selection does not improve accuracy because the selection process causes many attributes to be discarded because they are considered irrelevant. This happened because of the inaccuracy of the data after being selected for its attributes using the Forward Selection feature resulting 1 attribute  only as a determinant. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-12-19 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1149 10.33096/ilkom.v14i3.1149.323-328 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 323-328 ILKOM Jurnal Ilmiah; Vol 14, No 3 (2022); 323-328 2548-7779 2087-1716 10.33096/ilkom.v14i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1149/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1149/317 Copyright (c) 2022 Ruhmi Sulaehani, Marniyati Husain Botutihe https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/318 2026-04-20T06:16:56Z ILKOM:ART driver

KOLABORASI FISH-NET DAN TECHNOLOGY UNTUK OPTIMALISASI ALAT TANGKAP IKAN Irwan, Irwan Fikar, Sul Surachmad, Winarto Hayati, Lilis Nur Gill Net Surface; FiNe-Tech; Fishing Equipment; Catching Process; Catch AbstractKelurahan Untia is one of the areas occupied by the fishermen and also the majority of the population work as fishermen catch fishermen. The dominant fishing gear used by fishermen in the village of Untia is surface gill net. But the use of surface gill net capture device is considered not effective and efficient because it has constraints on the process of checking the net, the old fishing process, the net tends to disappear, and the catch is considered less. So from that problem, we encourage us to create a technological innovation called FiNe-Tech (Fish Net Technology). FiNe-Tech is designed to be able to monitor fish trapped in surface gill net captures, simplify the process of catching fish in the sea, tracking the position of the jarring, speeding up the fishing process, and increasing the net catch through a smartphone application at close range and distance from the position nets even though we are at home though. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Kementerian Riset, Teknologi, dan Perguruan Tinggi 2018-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/318 10.33096/ilkom.v10i2.318.207-214 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 207-214 ILKOM Jurnal Ilmiah; Vol 10, No 2 (2018); 207-214 2548-7779 2087-1716 10.33096/ilkom.v10i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/318/149 Copyright (c) 2018 Irwan Irwan, Sul Fikar, Winarto Surachmad, Lilis Nur Hayati https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/11 2026-04-20T06:19:26Z ILKOM:ART driver

Sistem Interaktif Membaca Permulaan bagi Anak Usia Dini Herman, Suherman Muhdiah, Mumuy membaca permulaan, anak usia dini, metode abjad, bunyi dan gambar Penelitian ini dengan menggunakan metode abjad, bunyi dan gambar. Penelitian ini bertujuan untuk mengetahui pengaruh pembelajaran media interaktif terhadap semangat, dan minat anak dalam membaca permulaan. Penelitian membaca permulaan ini digunakan untuk anak usia 4-5 tahun. Untuk pengujian hasil penelitian berjumlah 20 siswa, dan diambil sampel sebanyak 10 siswa untuk tahun pelajaran 2015/2016. Sebagai pengamat dilakukan oleh 3 guru dan 1 kepala sekolah. Pengumpulan data dalam penelitian ini dilakukan dengan cara observasi, kuesioner, wawancara dan dokumentasi. Penelitian dilakukan di PAUD Pelita Hati Pandeglang. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Universitas Serang Raya 2016-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/11 10.33096/ilkom.v8i1.11.23-28 ILKOM Jurnal Ilmiah; Vol 8, No 1 (2016); 23-28 ILKOM Jurnal Ilmiah; Vol 8, No 1 (2016); 23-28 2548-7779 2087-1716 10.33096/ilkom.v8i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/11/13 Copyright (c) 2016 Suherman Herman, Mumuy Muhdiah https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/3224 2026-04-27T07:10:10Z ILKOM:ART driver

Blockchain-Based Diploma Authentication System: A Design Science Approach Using Smart Contracts and Ganache Haryati, Haryati Vernanda, Dwi Blockchain; Smart Contract; Diploma Authentication; Ganache; DSRM Academic credential fraud poses a critical challenge to Indonesian higher education, with approximately 30% of job applicants providing false academic qualifications while conventional verification processes require 2–4 weeks with significant administrative costs. This research addresses the gap where 77% of blockchain education research remains conceptual by proposing and evaluating a four-layer blockchain system architecture for academic diploma authentication. Using Design Science Research Methodology (DSRM), the study designs and implements a layered architecture comprising a Presentation Layer (React 18.2.0 with client-side SHA-256 hashing), Application Layer (Node.js 18.20.8 with Web3.js), Data Layer (PostgreSQL 14.5 for off-chain metadata), and Blockchain Layer (DiplomaValidator smart contract in Solidity 0.8.19 on Ganache 2.7.1). The architectural design enforces separation of concerns, enabling tamper-evident credential storage through immutable on-chain hash registration and trustless public verification through zero-gas view functions. Comprehensive evaluation through 38 functional tests, performance benchmarking, security auditing, and integration testing demonstrates 100% pass rate across all categories. Performance metrics show registration in 15.23 ms (240,082 gas units) and verification in 9.47 ms at zero gas cost, achieving 51.81 TPS throughput. Security audit yields 95/100 with zero high or medium vulnerabilities. The primary contribution of this research is a formally documented four-layer blockchain architecture for academic credential authentication validated through DSRM providing a replicable architectural model and quantified performance baselines for the Computer Science community and Indonesian higher education institutions considering blockchain adoption Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2026-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/3224 10.33096/ilkom.v18i1.3224.69-84 ILKOM Jurnal Ilmiah; Vol 18, No 1 (2026); 69-84 ILKOM Jurnal Ilmiah; Vol 18, No 1 (2026); 69-84 2548-7779 2087-1716 10.33096/ilkom.v18i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/3224/pdf Copyright (c) 2026 Haryati, Dwi Vernanda https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1531 2026-04-20T06:02:05Z ILKOM:ART driver

User’s Satisfaction Analysis of the Academic Information Systems Quality using the Modified Webqual 4.0 Method and Importance-Performance Analysis Anwarudin, Aang Fadlil, Abdul Yudhana, Anton Academic Information System; AIS; User Satisfaction; Importance-Performance Analysis; Web Quality. Currently, the academic information system (AIS) at universities processes academic data to facilitate student’s activities. AIS was developed to provide maximum service to students. To optimize the use of information technology and to ensure the appropriateness of the provided AIS services, it is necessary to examine the level of service provided to improve quality. This study aimed to analyze the level of AIS service quality based on user perceptions and expectations. Dissemination of online questionnaires using Google Forms with a total of 100 students as respondents. This study used the modified Webqual 4.0 method as an indicator in the preparation of the questionnaire and the importance-performance analysis (IPA) method as an analysis method. The results of data were classified based on the percentage of user’s satisfaction with AIS services with three classifications, namely good, moderate, and poor. The results of the IPA analysis showed that the AIS had good quality. The results obtained from the analysis of the quality of the AIS system had a conformity level of 90.90%, where respondents perceived close to satisfaction with AIS services. The gap level was -0.3281 which was the result of the perception/performance of the AIS that was not in line with the expectations of the user. The results of this study contribute to Universitas Muhammadiyah Gombong as reference material and evaluation of AIS system services in the future. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-04-07 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1531 10.33096/ilkom.v15i1.1531.132-143 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 132-143 ILKOM Jurnal Ilmiah; Vol 15, No 1 (2023); 132-143 2548-7779 2087-1716 10.33096/ilkom.v15i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1531/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/1531/405 Copyright (c) 2023 Aang Anwarudin, Abdul Fadlil, Anton Yudhana https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/363 2026-04-20T06:16:36Z ILKOM:ART driver

KENDALI ROBOT BLUETOOTH DENGAN SMARTPHONE ANDROID BERBASIS ARDUINO UNO Handayani, Yanolanda Suzantry Mardiana, Yessi Mobile Robot; Android; Bluetooth Hc-05; Arduino Uno The Mobile Robot is a robot construction whose characteristic is to have an actuator in the form of a wheel to move the entire body of the robot, so that the robot can shift positions from one point to another. This Mobile Robot is designed to move using an Android Smartphone controller that has an application that is suitable for robot movements. This robot uses Arduino Uno as a Bluetooth robot control system, the Bluetooth module functions as receiving commands sent via an Android Smartphone, a DC Motor is functioned as a controlled Robot drive using an Android Smartphone and Boarduino application installed via Playstore. The method used is the experimental method, the research will focus on communication between smartphone devices and Arduino Uno microcontrollers via Bluetooth to control robotic devices. Based on testing Bluetooth connections on robots, it can be concluded that the Bluetooth connection between the Smartphone and the Bluetooth robot can be fully controlled by a range of 25 meters, for a distance of 25-32 meters has a signal drop and is broken, and more than a range of 32 meters will experience a broken connection so that the robot cannot be controlled anymore. Prodi Teknik Informatika FIK Universitas Muslim Indonesia Direktorat Jenderal Penguatan Riset dan Pengembangan, Kementerian Riset, Teknologi dan Pendidikan Tinggi melalui Penelitian Dosen Pemula (PDP) Tahun Anggaran 2018 2018-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/363 10.33096/ilkom.v10i3.363.331-337 ILKOM Jurnal Ilmiah; Vol 10, No 3 (2018); 331-337 ILKOM Jurnal Ilmiah; Vol 10, No 3 (2018); 331-337 2548-7779 2087-1716 10.33096/ilkom.v10i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/363/166 Copyright (c) 2018 Yanolanda Suzantry Handayani, Yessi Mardiana https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/57 2026-04-20T06:19:05Z ILKOM:ART driver

Aplikasi Penentuan Jenis Part Of Speech Menggunakan Metode N-Gram dan String Matching Nurzaenab, Nurzaenab Purnawansyah, Purnawansyah Grammar, N-Gram, Part Of Speech, String Matching Bahasa Inggris merupakan bahasa ibu dalam skala internasional sebagai alat komunikasi antar negara. Bahasa Inggris memiliki aturan baik dalam hal pengucapan dan penulisan disebut Grammar yang membentuk pola-pola. Pola-pola tersebut tersusun oleh setiap kata yang memiliki bentuk-bentuk tersendiri yang disebut Parts Of Speech. Bentuk dalam Parts Of Speech terbagi dalam delapan bentuk yaitu Noun (kata benda), Pronoun (kata ganti), Verb (kata kerja), Adjective (kata sifat), Adverb (kata keterangan), Preposition (kata depan), Conjuction (kata penghubung), Interjection (kata seru). Tingkat ingatan manusia tentu berbeda-beda. Ingatan untuk membedakan kata-kata dan pembentukan pola kalimat dalam part of speech. Setiap kata akan ditentukan jenis part of speech-nya, tergantung dari inputan user. Sedangkan pola kalimat akan di tentukan sesuai inputan user berdasarkan part of speech-nya. Perancangan dilakukan menggunakan metode uni-gram dan String Matching (Knuth Morris Pratt). Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2016-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/57 10.33096/ilkom.v8i2.57.132-136 ILKOM Jurnal Ilmiah; Vol 8, No 2 (2016); 132-136 ILKOM Jurnal Ilmiah; Vol 8, No 2 (2016); 132-136 2548-7779 2087-1716 10.33096/ilkom.v8i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/57/37 Copyright (c) 2016 Nurzaenab Nurzaenab, Purnawansyah Purnawansyah https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1686 2026-04-20T05:59:42Z ILKOM:ART driver

The Support Vector Regression Method Performance Analysis in Predicting National Staple Commodity Prices Analisis Performa Metode Support Vector Regression (SVR) dalam Memprediksi Harga Bahan Sembako Nasional Azis, Huzain Purnawansyah, Purnawansyah Nirwana, Nirwana Dwiyanto, Felix Andika Food Prices; Machine Learning; Predictions; Support Vector Regression. Harga Sembako; Prediksi; Support Vector Regression; Machine Learning Support Vector Regression (SVR) is a supervised learning algorithm to predict continuous variable values. The basic goal of the SVR algorithm is to find the most suitable decision line. SVR has been successfully applied to several issues in time series prediction. In this research, SVR is used to predict the price of staple commodity, which are constantly changing in price at any time due to several factors making it difficult for the public to get groceries that are easy to reach. National staple commodity data consisting of 17 commodities, including shallots, honan garlic, kating garlic, medium rice, premium rice, red cayenne peppers, curly red chilies, red chili peppers, meat of broiler chicken, beef hamstrings, granulated sugar, imported soybeans, bulk cooking oil, premium packaged cooking oil, simple packaged cooking oil, broiler chicken eggs, and wheat flour. With a data set for the last 3 years, including from January 1, 2020, to December 31, 2022. There are 3 variables in the data set, namely commodity, date, and price. This research divides the entire dataset into 80% training and 20% testing data. The results of this research show that SVR using the RBF kernel produces good forecasting accuracy for all datasets with an average Mean Square Error (MSE) training data of 6,005 while data testing is 6,062, Mean Absolute Deviation (MAD) of training data is 6,730 while data testing is 6.6831, Mean Absolute Percentage Error (MAPE) training data is 0.0148 while data testing is 0.0147, and Root Mean Squared Error (RMSE) training data is 7.772 while data testing is 7.746. Support Vector Regression (SVR) adalah algoritma supervised learning yang digunakan untuk memprediksi nilai variabel kontinu. Tujuan dasar dari algoritma SVR adalah menemukan garis keputusan yang paling sesuai. SVR sukses diterapkan di beberapa permasalahan dalam prediksi time series sehingga pada penilitian ini SVR diterapkan untuk memprediksi harga bahan sembako nasional yang terdiri 17 Komoditas yaitu bawang merah, bawang putih honan, bawang putih kating, beras medium, beras premium, cabe merah besar, cabe merah keriting, cabe rawit merah, daging ayam ras, daging sapi paha belakang, gula pasir, kedelai impor, minyak goreng curah, minyak goreng kemasan premium, minyak goreng kemasan sederhana, telur ayam ras, dan tepung terigu. Dengan himpunan data selama 3 tahun terakhir, yaitu dari tanggal 1 Januari 2020 sampai dengan tanggal 31 Desember 2022. Terdapat 3 variabel di dalam himpunan data tersebut yaitu variabel komoditas, tanggal, dan harga. Penilitian ini membagi dataset keseluruhan menjadi data training 80% dan data testing 20%. Hasil dari penilitian ini  menunjukkan bahwa SVR dengan menggunakan kernel RBF menghasilkan akurasi peramalan yang sangat baik untuk semua dataset dengan nilai rata-rata Mean Square Error (MSE) data training sebesar 6.005 sedangkan data testing sebesar 6.062 , Mean Absolute Deviation (MAD) data training sebesar  6.730 sedangkan data testing sebesar 6.6831, Mean Absolute Percentage Error (MAPE) data training sebesar 0.0148 sedangkan data testing sebesar 0.0147 , dan  Mean Root Squared Error (MRSE) data training sebesar 7.772 sedangkan data testing sebesar 7.746 Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2023-08-16 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1686 10.33096/ilkom.v15i2.1686.390-397 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 390-397 ILKOM Jurnal Ilmiah; Vol 15, No 2 (2023); 390-397 2548-7779 2087-1716 10.33096/ilkom.v15i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1686/pdf Copyright (c) 2023 Huzain Azis, Purnawansyah, Nirwana, Felix Andika Dwiyanto https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/398 2026-04-20T06:13:16Z ILKOM:ART driver

Analysis of User Satisfaction Level of Information System Library Using PIECES Framework ANALISIS TINGKAT KEPUASAN PENGGUNA SISTEM INFORMASI PERPUSTAKAAN MENGGUNAKAN PIECES FRAMEWORK Indrawati, Indrawati Lokapitasari Belluano, Poetri Lestari Harlinda, Harlinda Tuasamu, Fatima A.R Lantara, Dirgahayu Analysis; Satisfaction;librarian; Library Information Systems; PIECES Framework; Analysis; Satisfaction; Users; Library Information Systems; PIECES Framework The use of information systems requires special management and management, so this system is commonly referred to as a management information system. In it there are various activities ranging from system planning, maintenance, to measuring performance. In running a library information system, software and hardware are needed as well as humans as operators. The above components must be activities that are interconnected so that the library can run smoothly. To determine whether the components of the information system are running well, it requires an evaluation process.The purpose of this study is to measure the level of satisfaction of system users and to determine the strengths and weaknesses of the system in the use of library information systems. The method used is the analytical method PIECES Framework, which consists of several points of analysis, namely: Performance, Information and Data, Economics, Control and Security, Efficiency, and Service. Where each analysis point is a reference for evaluation and analysis of information systems.The results of this study are web applications that are able to analyze the level of user satisfaction with the library information system using the PIECES Framework analysis method and equipped with a satisfaction level reporting chart of the system measured in the 2018 period The use of information systems requires special management and management, so this system is commonly referred to as a management information system. In it there are various activities ranging from system planning, maintenance, to measuring performance. In running a library information system, software and hardware are needed as well as humans as operators. The above components must be activities that are interconnected so that the library can run smoothly. To determine whether the components of the information system are running well, it requires an evaluation process. The purpose of this study is to measure the level of satisfaction of system users and to determine the strengths and weaknesses of the system in the use of library information systems. The method used is the analytical method PIECES Framework, which consists of several points of analysis, namely: Performance, Information and Data, Economics, Control and Security, Efficiency, and Service. Where each analysis point is a reference for evaluation and analysis of information systems. The results of this study are web applications that are able to analyze the level of user satisfaction with the library information system using the PIECES Framework analysis method and equipped with a satisfaction level reporting chart of the system measured in the 2018 period. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2019-09-03 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/398 10.33096/ilkom.v11i2.398.118-128 ILKOM Jurnal Ilmiah; Vol 11, No 2 (2019); 118-128 ILKOM Jurnal Ilmiah; Vol 11, No 2 (2019); 118-128 2548-7779 2087-1716 10.33096/ilkom.v11i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/398/183 Copyright (c) 2019 Poetri Lestari Lokapitasari Belluano, Indrawati Indrawati, Harlinda Harlinda, Fatima A.R Tuasamu, Dirgahayu Lantara https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/103 2026-04-20T06:18:23Z ILKOM:ART driver

INVESTIGASI LIVE FORENSIK DARI SISI PENGGUNA UNTUK MENGANALISA SERANGAN MAN IN THE MIDDLE ATTACK BERBASIS EVIL TWIN Ahmad, Muhammad Sabri Riadi, Imam Prayudi, Yudi Wifi ;Evil Twin Attack; Live forensik; MITM; User side MITM based Evil twin menjadi suatu ancaman yang berbahaya bagi para pengguna jaringan Wifi. Pelaku penyerangan ini memanfaatkan AP (Access Point) palsu dengan konfigurasi gateway yang berbeda dengan legitimate AP, sehingga jenis serangan ini menjadi cukup sulit untuk dideteksi, disisi lain proses pengungkapan kasus serangan MITM based Evil Twin hanya sebatas mendeteksi aktivitas serangan dan belum ada pembahasan lebih lanjut terkait digital forensik. Penelitian ini dilakukan dengan menerapkan pendekatan metode Live forensik dan pendekatan dari sisi user, untuk mendeteksi aktivitas ilegal yang terjadi di dalam jaringan Wifi, Proses investigasi MITM Based Evil dibagi menjadi empat tahapan, dimulai dari proses collection, examination, analysis dan reporting dan analisa Forensik, selain itu penelitian ini difokuskan pada dua proses penelitian yaitu proses analisa Wifi scanning dan analisa network trafik untuk proses penemuan barang bukti digital berupa informasi traffik data dari serangan mitm based evil twin. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/103 10.33096/ilkom.v9i1.103.1-8 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 1-8 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 1-8 2548-7779 2087-1716 10.33096/ilkom.v9i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/103/60 Copyright (c) 2017 Muhammad Sabri Ahmad, Imam Riadi, Yudi Prayudi https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/477 2026-04-20T06:12:56Z ILKOM:ART driver

PENGAMANAN FILE DOKUMEN MENGGUNAKAN KOMBINASI METODE SUBTITUSI DAN VIGENERE CIPHER Budi, Sarwo Purba, Arif Budimansyah Mulyana, Jajang Cryptography; Subtitution; Vigenere cipher; SDLC Waterfall Cryptography is a method of securing data using algorithms that have been developed continuously until now. Cryptography offers security in the form of data confidentiality, for example the confidentiality of data generated through encryption algorithms that scrambles personal information so that it cannot be read or solved by unauthorized parties. One of them is the substitution algorithm and the vigenere cipher is a classic method used for data security. The combination of these algorithm methods becomes a solution for double security as file protection. By using a cryptographic application for data security, the combination of the two method algorithms produces a data file that provides more security to the text file so that it is not easy and difficult to solve. Prodi Teknik Informatika FIK Universitas Muslim Indonesia STMIK KHARISMA KARAWANG 2019-12-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/477 10.33096/ilkom.v11i3.477.222-230 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 222-230 ILKOM Jurnal Ilmiah; Vol 11, No 3 (2019); 222-230 2548-7779 2087-1716 10.33096/ilkom.v11i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/477/196 Copyright (c) 2019 Sarwo Budi, Arif Budimansyah Purba, Jajang Mulyana https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/114 2026-04-20T06:18:23Z ILKOM:ART driver

SISTEM TRACER STUDY ALUMNI FAKULTAS ILMU KOMPUTER UNIVERSITAS MUSLIM INDONESIA MENGGUNAKAN METODE ON-LINE ANALITYCAL PROCESSING (OLAP) Syam, Aminurlah Manga, Abdul Rachman data alumni; data warehouse; olap Penyimpanan data secara rutin dan terus menerus data alumni Fakultas Ilmu Komputer dapat menimbulkan penumpukan data. Seperti data quesioner alumni yang menjadi salah satu masalah dalam melakukan inputan dikarenakan terkendala jarak. Selama ini pihak fakultas harus mecari data alumni yang telah bekerja atau berada diluar daerah. Sistem yang berbasis website tersebut akan menggunakan data warehouse dan penerapan metode Online Analitycal Processing (OLAP) yang nantinya akan berfungsi sebagai laporan dari data alumni dalam bentuk grafik. Dalam penelitiannya ini data warehouse dirender kedalam metode OLAP yang menghasilkan laporan dalam bentuk grafik. Sistem berbasis website juga memudahkan staff kemahasiswaan dan alumni dalam melakukan inputan karena bisa dilakukan dimanapun dengan adanya koneksi internet Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-04-20 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/114 10.33096/ilkom.v9i1.114.86-90 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 86-90 ILKOM Jurnal Ilmiah; Vol 9, No 1 (2017); 86-90 2548-7779 2087-1716 10.33096/ilkom.v9i1 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/114/71 Copyright (c) 2017 Aminurlah Syam, Abdul Rachman Manga https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/1831 2026-04-20T05:57:29Z ILKOM:ART driver

Optimizing Bitcoin Price Predictions Using Long Short-Term Memory Algorithm: A Deep Learning Approach Khumaidi, Ali Kusmanto, Panji Hikmah, Nur Bitcoin, Hyperparameter Tuning, LSTM, Prediction, Real Time Data. Currently bitcoin is considered an investment tools, the value of bitcoin itself is unstable so it is difficult to predict which can cause losses for bitcoin traders. Some previous research shows that Long Short-Term Memory (LSTM) which is a deep learning approach as an improvement of RNN has the best performance in predicting stocks and cryptocurrencies compared to Support Vector Machine (SVM), Exponential Moving Average (EMA), and Moving Average (MA), and Seasonal Autoregressive Integrated Moving Average (SARIMA). LSTM has the disadvantage that it is difficult to understand in determining the best parameters and to obtain good results it needs strict hyperparameter adjustment. This study aims to find the best parameters in LSTM by selecting the amount of data, training data composition, batch size, epoch and the amount of prediction time and analyzing prediction performance. In this study, data collection was carried out in real time and was able to provide predictions for the next few days. The test results of the LSTM algorithm have a performance with an average accuracy of 93.69% with the parameters of the amount of bitcoin price data used is 3 years, with a percentage of train data of 85%, using 10 batch sizes, with a number of epochs 125, and the highest average accuracy rate for 7 days of prediction. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1831 10.33096/ilkom.v16i1.1831.38-45 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 38-45 ILKOM Jurnal Ilmiah; Vol 16, No 1 (2024); 38-45 2548-7779 2087-1716 10.33096/ilkom.v16i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1831/pdf Copyright (c) 2024 Ali Khumaidi, Panji Kusmanto, Nur Hikmah. https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/527 2026-04-20T06:12:26Z ILKOM:ART driver

Analisis Implementasi Server Chatting pada Wireless LAN Satra, Ramdan server chatting; local network; kamailio There are currently many types of social media, but all of them are based on external servers. This causes communication data between users on social media to be stored on an external server. Retrieval of data without the permission of the owner is very possible. Therefore, we need a local server to store these data in certain companies or organizations. This research consists of several stages, namely designing a chat server topology, then configuring a chat server using Kamailio and finally testing the performance of the local network with parameters delay, packet loss and wireless signal strength (decibels). The results of this study indicate that the chat server implementation can be applied to the Faculty of Computer Science UMI based on observations of delay, packet losss and signal strength on the 1st and 2nd floors. On the 1st floor, the network access is quite good. WiFi is in the position of -50 dBm to -76 dBm and 0% packet loss and delays from 8 ms - 60 ms. On the 2nd floor, the WiFi network access is good enough, but at the 2nd location point, the second floor has a long delay of 563 ms, this shows bad access to the chat server, but the whole point shows that the second server's chat access is good. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-04-26 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/527 10.33096/ilkom.v12i1.527.64-70 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 64-70 ILKOM Jurnal Ilmiah; Vol 12, No 1 (2020); 64-70 2548-7779 2087-1716 10.33096/ilkom.v12i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/527/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/527/156 https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/856 2026-04-20T06:04:10Z ILKOM:ART driver

Effects of spectral transformations in support vector machine on predicting 'Arumanis' mango ripeness using near-infrared spectroscopy Khumaidi, Ali Purwanto, Y. Aris Sukoco, Heru Wijaya, Sony Hartono Maturity Prediction; Arumanis Mango; Near Infrared; Support Vector Machines; Spectral Transformation One of the challenges of exporting Arumanis mangoes is their accurate grading ability because the mangoes do not change color during ripening. Near-Infrared (NIR) spectroscopy is a non-destructive method for detecting the internal ripeness of fruit which is quite reliable. However, NIR absorbance bands are often nonspecific, extensive, and overlapping. Although SVM modeling is quite good in performance, it can still be improved by spectral transformation. In this study, 11 spectral transformation operations were compared with their combinations to find the best input model. Spectral transformation operations include SAVGOL, RNV, BASELINE, MSC, EMSC, NORML, CLIP, RESAMPLE, DETREND, SNV, and LSNV. In the 2 class classification model, the highest accuracy is obtained using RNV and SAVGOL. The prediction model for SSC content with the best MSE value uses 3 combinations of spectral transformation operations, namely DETREND, LSNV, and SAVGOL with parameter values: 'deriv_order': 0, 'filter_win': 31, 'poly_order': 6. As for the prediction model of mango hardness with The best MSE value uses 2 combinations of spectral transformation operations, namely LSNV and SAVGOL with parameter values: deriv_order ': 0,' filter_win ': 15,' poly_order ': 6. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2021-08-08 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/856 10.33096/ilkom.v13i3.856.206-215 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 206-215 ILKOM Jurnal Ilmiah; Vol 13, No 3 (2021); 206-215 2548-7779 2087-1716 10.33096/ilkom.v13i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/856/pdf Copyright (c) 2021 Ali Khumaidi, Y. Aris Purwanto, Heru Sukoco, Sony Hartono Wijaya https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/140 2026-04-20T06:18:00Z ILKOM:ART driver

PERANCANGAN APLIKASI MONITORING PC BERBASIS DESKTOP PADA PROGRAM STUDI TEKNIK INFORMATIKA FAKULTAS ILMU KOMPUTER UMI Mansyur, Hajrah Duwila, Ichroman Raditya Aplikasi Monitoring; Platform Desktop; UML; Client; Aplikasi Server Proses praktikum di Laboratorium Terpadu Fakultas Ilmu Komputer UMI adalah salah satu komponen vital dalam kegiatan belajar mengajar di Fakultas Ilmu Komputer UMI. Dalam melakukan praktikum di laboratorium, asisten laboratorium melakukan monitoring terhadap praktikan dengan cara standar, yaitu mengontrol dan memperhatikan aktivitas praktikan dengan langsung mendatangi PC atau komputer tempat praktikan melakukan aktivitasnya. Adanya sistem yang tanpa bantuan sebuah aplikasi monitoring sedikit menyulitkan kinerja asisten dimana harus dilakukan monitoring secara simultan. Tujuan dari penelitian ini adalah menghasilkan sebuah aplikasi yang kiranya dapat membantu asisten laboratorium untuk melakukan pengontrolan dan pengawasan terhadap praktikan. Aplikasi monitoring PC ini dibangun menggunakan bahasa pemrograman Java, editor Netbeans serta menggunakan UML dalam perancangan sistem. Hasil dari penelitian ini yaitu sebuah aplikasi monitoring yang berjalan di platform desktop dan dapat diakses oleh asisten laboratorium dimana aplikasi ini berjalan di sisi praktikan sebagai aplikasi client (berjalan di background) dan di sisi server sebagai aplikasi server. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2017-08-31 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/140 10.33096/ilkom.v9i2.140.196-202 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 196-202 ILKOM Jurnal Ilmiah; Vol 9, No 2 (2017); 196-202 2548-7779 2087-1716 10.33096/ilkom.v9i2 ind https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/140/94 Copyright (c) 2017 Hajrah Mansyur, Ichroman Raditya Duwila https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/2092 2026-04-20T05:56:05Z ILKOM:ART driver

Optimizing THD in Modified Multilevel Inverters with IoT-Integrated MPPT Systems for Enhanced Efficiency Optimizing THD in Modified Multilevel Inverters with IoT-Integrated MPPT Systems for Enhanced Efficiency Syarifuddin, Andi Pakka, Hariani Ma'tang Eren, Halit AlGhamdi, Ahmed Saeed Baso, Nur Fadliah Boost converters; IOT; Multilevel Inverter; Simulink; Solar Photovoltaic; Total Harmonic Distortion Boost converters; IOT; Multilevel Inverter; Simulink; Solar Photovoltaic; Total Harmonic Distortion This work proposes a new Modified Multilevel Inverter (MMLI) and provides a comprehensive comparison with Conventional Cascaded H-bridge Inverters. The MMLI features fewer switching devices compared to the conventional H-Bridge Inverter for 9-level voltages and higher. Maximum Power Point Tracking (MPPT) incorporated with a Boost converter ensures a constant output from photovoltaic (PV) arrays, which is then fed to the inverter to achieve the desired number of voltage levels. To enhance the performance and efficiency of the system, IoT technologies were integrated for real-time monitoring and control. Smart sensors and cloud-based platforms were utilized for data collection and analysis, enabling precise control of the MPPT and inverter systems. The integration of IoT resulted in significant improvements in the system's dynamic response, energy conversion efficiency, and overall reliability. The results were validated through simulations in Simulink, with outcomes presented and compared for voltage waveform and harmonic spectrum. The integration of IoT technologies provided substantial benefits, showcasing the interdisciplinary approach of this research in reducing Total Harmonic Distortion (THD) while optimizing inverter operations This work proposes a new Modified Multilevel Inverter (MMLI) and provides a comprehensive comparison with Conventional Cascaded H-bridge Inverters. The MMLI features fewer switching devices compared to the conventional H-Bridge Inverter for 9-level voltages and higher. Maximum Power Point Tracking (MPPT) incorporated with a Boost converter ensures a constant output from Photovoltaic (PV) arrays, which is then fed to the inverter to achieve the desired number of voltage levels. To enhance the performance and efficiency of the system, IoT technologies were integrated for real-time monitoring and control. Smart sensors and cloud-based platforms were utilized for data collection and analysis, enabling precise control of the MPPT and inverter systems. The integration of IoT resulted in significant improvements in the system's dynamic response, energy conversion efficiency, and overall reliability. The results were validated through simulations in Simulink, with outcomes presented and compared for voltage waveform and harmonic spectrum. The integration of IoT technologies provided substantial benefits, showcasing the interdisciplinary approach of this research in reducing Total Harmonic Distortion (THD) while optimizing inverter operations. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2024-08-24 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2092 10.33096/ilkom.v16i2.2092.198-209 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 198-209 ILKOM Jurnal Ilmiah; Vol 16, No 2 (2024); 198-209 2548-7779 2087-1716 10.33096/ilkom.v16i2 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/2092/pdf Copyright (c) 2024 Andi Syarifuddin, Hariani Ma’tang Pakka, Halit Eren, Ahmed Saeed AlGhamdi, Nur Fadliah Baso https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/652 2026-04-20T06:05:19Z ILKOM:ART driver

Penerapan Metode AHP-Topsis untuk Mengukur Tingkat Kesejahteraan Masyarakat Pesisir Kaluku, Moh Ramdhan Arif Pakaya, Nikmasari Wellfare; Coast; AHP; TOPSIS Tujuan dari penelitian ini yaitu memperoleh terobosan terbaru dalam ilmu pengetahuann terutama pada masalah indikator pengembangan kawasan pesisir dan kesejahteraan masyarakat nelayan yang kemudian dapat diimplementasikan dalam aplikasi sistem informasi dengan menggunakan metode AHP-TOPSIS. Dengan menerapkan metode AHP untuk menentukan bobot global dari setiap kriteria, kemudian metode TOPSIS untuk melakukan penilaian pada kondisi kesejahteraan Masyarakat pesisir, penelitian ini bertujuan untuk meninjau faktor-faktor yang dapat mempengaruhi kesejahteraan masyarakat pesisir dengan mengukur tingkat kesejahteraan masyarakat pesisir, dan menerapkan rancangan model ke dalam aplikasi sistem informasi pengukuran kesejahteraan masyarakat pesisir. Prediksi dari tingkat kesejahteraan dapat dilihat dari hasil penelitian yang diperoleh dari perhitungan yang dilakukan. Penilaian pada tingkat kesejahteraan masyarakat menunjukan nilai akhir terbesar dengan 0,8095, sedangkan nilai terendah dengan nilai 0,1113. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2020-12-28 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/652 10.33096/ilkom.v12i3.652.191-199 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 191-199 ILKOM Jurnal Ilmiah; Vol 12, No 3 (2020); 191-199 2548-7779 2087-1716 10.33096/ilkom.v12i3 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/652/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/downloadSuppFile/652/204 Copyright (c) 2020 Moh Ramdhan Arif Kaluku, Nikmasari Pakaya https://creativecommons.org/licenses/by-sa/4.0

oai:ojs.103.2:article/910 2026-04-20T06:03:47Z ILKOM:ART driver

Classification of Coffee Bean Defects Using Gray-Level Co-Occurrence Matrix and K-Nearest Neighbor Jumarlis, Mila Mirfan, Mirfan Manga, Abdul Rachman Coffee beans; Digital Image; GLCM; Classification; K-NN Defects in coffee beans can significantly affect the quality of coffee production so that defects in coffee beans can cause a decreasing the level of coffee production. The purpose of this study is to implement the GLCM (gray-level co-occurrence matrix) and the K-NN (k-nearest neighbor) method on a web-based program and provided a website to detect coffee bean defects. This study uses the GLCM algorithm to extract the features of the coffee images and uses the K-NN algorithm to classify the defect level of coffee beans. The system development was built using Unified Modeling Language. The development of this website was utilized the programming structure of PHP, HTML, CSS, Javascript, Mozilla Firefox as a browser for the website and MySql for the database management systems. The results show that the system can provide the output in the form of a classification level of the defect level of the coffee bean images. Then, the accuracy of the coffee bean defect assessment was achieved by 90%. Finally, this study concluded that the proposed system could help the coffee farmers determine the defect level of the coffee beans using images input. Prodi Teknik Informatika FIK Universitas Muslim Indonesia 2022-04-30 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion application/pdf https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/910 10.33096/ilkom.v14i1.910.1-9 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 1-9 ILKOM Jurnal Ilmiah; Vol 14, No 1 (2022); 1-9 2548-7779 2087-1716 10.33096/ilkom.v14i1 eng https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/910/pdf Copyright (c) 2022 Mila Jumarlis, Mirfan, Abdul Rachman Manga https://creativecommons.org/licenses/by-sa/4.0 09f2496a7790bb82567f195b8e210034