https://jurnal.fikom.umi.ac.id/index.php/ILKOM/issue/feedILKOM Jurnal Ilmiah2024-01-22T23:06:25+09:00ILKOM Jurnal Ilmiahjurnal.ilkom@umi.ac.idOpen Journal Systems<table class="data" width="100%" bgcolor="#f0f0f0"><tbody><tr valign="top"><td width="20%">Journal title</td><td width="80%"><strong>ILKOM Jurnal Ilmiah</strong></td></tr><tr valign="top"><td width="20%">Initials</td><td width="80%"><strong>ILKOM</strong></td></tr><tr valign="top"><td width="20%">Abbreviation</td><td width="80%"><strong>ilk. J. Ilm</strong></td></tr><tr valign="top"><td width="20%">Frequency</td><td width="80%"><strong>3 issues per year</strong></td></tr><tr valign="top"><td width="20%">DOI</td><td width="80%"><strong>prefix 10.33096</strong><strong><br /></strong></td></tr><tr valign="top"><td width="20%">Online ISSN</td><td width="80%"><strong>2548-7779</strong></td></tr><tr valign="top"><td width="20%">Editor-in-chief</td><td width="80%"><a href="https://www.scopus.com/authid/detail.uri?authorId=57202237115" target="_blank"><strong>Yulita Salim</strong></a></td></tr><tr valign="top"><td width="20%">Managing Editor</td><td width="80%"><a href="https://www.scopus.com/authid/detail.uri?authorId=57211712874" target="_blank"><strong>Ramdan Satra</strong></a></td></tr><tr valign="top"><td width="20%">Publisher</td><td width="80%"><a href="https://fikom.umi.ac.id/" target="_blank"><strong>Teknik Informatika Fakultas Ilmu Komputer Universitas Muslim Indonesia</strong></a></td></tr><tr valign="top"><td width="20%">Citation Analysis</td><td width="80%"><a href="https://scholar.google.co.id/citations?user=nWedlZoAAAAJ&hl=en" target="_blank"><strong>Google Scholar</strong></a> / <strong><a href="https://app.dimensions.ai/discover/publication?search_mode=content&or_facet_source_title=jour.1364591" target="_blank">Dimenssion</a></strong></td></tr><tr valign="top"><td width="20%">Frequency published</td><td valign="top" width="80%"><div style="text-align: justify;"><p>ILKOM Jurnal Ilmiah is issued three times a year in <strong>April, August, and December.</strong></p></div></td></tr></tbody></table><hr /><p><strong>Focus and Scope, </strong>ILKOM Jurnal Ilmiah encompasses all aspects of the latest outstanding research and developments in the field of Computer science including:</p><ul><li><strong>Artificial intelligence</strong></li><li><strong>Data science</strong></li><li><strong>Computer security and cryptography</strong></li><li><strong>Computer networks</strong></li><li><strong>Parallel and distributed systems</strong></li><li><strong>Internet of Things</strong></li><li><strong>Software engineering</strong></li></ul>https://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1770N-gram and Kernel Performance Using Support Vector Machine Algorithm for Fake News Detection System2024-01-17T19:20:41+09:00Deny Jollytadeny.jollyta@lecturer.pelitaindonesia.ac.idGusrianty Gusriantygusrianty@lecturer.pelitaindonesia.ac.idPrihandoko Prihandokoprihandoko@gmail.comDarmanta Sukriantodarman1407@gmail.comThe modern technological advancements have made it simpler for fake news to circulate online. The researchers have developed several strategies to overcome this obstacle, including text classification, distribution network analysis, and human-machine hybrid methods. The most common method is text categorization, and many researchers offer deep learning and machine learning models as remedies. An Indonesian language fake news detection system based on news headlines was developed in this work using the Support Vector Machine (SVM) kernel and n-gram. The objective of this research is to identify the model that produces the best performance outcomes. The system deployment on the web will employ the model that produces the greatest outcomes. According to the research findings, the linear kernel SVM algorithm produces the best results, with an accuracy value of 0.974. Furthermore, the bigram feature used in the development of a classification model does not increase the precision of fake news identification in Indonesian. Utilizing the unigram function yields the most accurate results.2023-12-20T22:03:30+09:00Copyright (c) 2023 Deny Jollyta, Gusrianty Gusrianty, Prihandoko Prihandoko, Darmanta Sukriantohttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1687The Determination of Dawn Time through Image Processing Camera2024-01-17T19:27:47+09:00Harry Ramzahramza@uhamka.ac.idTossa Hario Yudhantotossah56@gmail.comDedy Sugihartodedysugiharto12@gmail.comAs’ad Syaifudin Ulumulummrs09@gmail.comMohammad Mujirudinmujirudin@uhamka.ac.idEmilia Rozaemilia_roza@uhamka.ac.idMohammad Syuhaimi Ab-Rahmansyuhaimi@ukm.edu.myTono Saksonotonosaksono@uhamka.ac.idMohd Haris Md Khirharisk@utp.edu.my<p>Determining the early time prayer is very fundamental for Muslims as it directly relates to the legal requirements of prayer. Prayers are not performed whenever we want, but rather there is a determination of the beginning and end of the prayer time as a guideline for Muslims to carry it out. The Indonesia government sets standards for Muslims to perform the dawn prayer service, by precisely determining the degree of the emergence of the dawn of <em>Sadiq</em> by -20<sup>0</sup>. This study aims to compare the determination of the government's dawn time using different sensors, specifically drone cameras as image sensors. Drones were chosen due to their several advantages. The data generated by the drone is in the form of photos, which are subsequently processed using digital image processing software, called image-J. The data obtained are in the form of mean and standard deviation. All data collected in 1 day is recorded using Excel to form a graph of data which is then carried out by a polynomial approach to find out the cutoff point as the beginning of the dawn of <em>Sadiq</em> which indicates the start of dawn. The method used in this research is using the 4<sup>th</sup> order polynomial approach and the <em>Sarrus</em> method and the data obtained is the mean value and standard deviation. The conclusions obtained in the image analysis research are that the government's dawn time is 15 minutes too fast, the standard obtained in this study is -14.98° and unlike 2D SQM data, 3D drone data results in more accurate data analysis.</p>2023-12-20T22:03:30+09:00Copyright (c) 2023 Harry Ramza, Tossa Hario Yudhanto, Tossa Hario Yudhanto, Dedy Sugiharto, Dedy Sugiharto, As’ad Syaifudin Ulum, As’ad Syaifudin Ulum, Mohammad Mujirudin, Mohammad Mujirudin, Emilia Roza, Emilia Roza, Mohammad Syuhaimi Ab-Rahman, Mohammad Syuhaimi Ab-Rahman, Tono Saksono, Tono Saksono, Mohd Haris Md Khir, Mohd Haris Md Khirhttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1945Cloud-Based Realtime Decision System for Severity Classification of COVID-19 Self-Isolation Patients using Machine Learning Algorithm2024-01-22T23:06:25+09:00Bhima Satria Rizki Sugionobhimasatria.1905366@students.um.ac.idMokh. Sholihul Hadimokh.sholihul.ft@um.ac.idIlham Ari Elbaith Zaeniilham.ari.ft@um.ac.idSujito Sujitosujito.ft@um.ac.idMhd Irvanirvan@yamagula.ic.i.u-tokyo.ac.jp<p><span>The global impact of the COVID-19 pandemic has been profound, affecting economies and societal structures worldwide. Indonesia, with a high caseload, has encountered significant challenges across various sectors. Virus transmission primarily occurs through physical contact, and the surge in active cases has strained hospital capacities, leading to the hospitalization of only severe cases. The remaining patients receive home telecare, but some experience sudden health deterioration with fatal consequences. To address this issue, this study proposes a remote outpatient care system utilizing Internet of Things (IoT) technology and medical electronics. This integrated system aims to provide an effective response to the COVID-19 pandemic. The research includes a comparative analysis of three machine-learning algorithms: decision tree, gradient tree boosting, and random forest for the classification of COVID-19 patients. The results reveal that the random forest algorithm outperforms the others with an accuracy rate of 70%, as compared to 67% for the decision tree and 62% for the gradient tree boosting algorithm. This integrated system not only addresses immediate healthcare delivery challenges but also offers data-driven insights for patient classification, thereby enhancing the effectiveness and reach of medical interventions</span></p>2023-12-20T22:03:30+09:00Copyright (c) 2023 Bhima Satria Rizki Sugiono, Mokh. Sholihul Hadi, Ilham Ari Elbaith Zaeni, Sujito Sujito, Mhd Irvanhttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1610Sentiment Analysis of Shopee App Reviews Using Random Forest and Support Vector Machine2024-01-17T19:38:03+09:00Suswadi Suswadisuswadi@lecture.utp.ac.idMoh. Erkamimerkamim@lecture.utp.ac.idDuring the COVID-19 outbreak, Indonesian marketplaces were significantly impacted including Shopee app. It is necessary to evaluate the features and services of the Shopee application by looking at the feedback given by the public in Google Play Store reviews. This is what prompted research to be conducted from Kaggle data in the form of Shopee reviews. From this data, sentiment analysis is carried out utilizing the Support Vector Machine (SVM) and Random Forest methods. This method are used to classify reviews based on positive and negative sentiments. The results showed that the level of classification accuracy in the Random Forest model is 82.21%. While the SVM model provides a higher level of accuracy of 84.71%. Data exploration on positive and negative sentiment classes is used to find insight into this problem. In positive sentiment, words that often appear such as “<em>belanja</em>”, “<em>aplikasi</em>”, and “<em>barang</em>” are found. As for the negative sentiments, namely “<em>ongkir</em>”, “<em>kirim</em>”, “<em>aplikasi</em>”. These words can be used to be a quality improvement or evaluation for the Shopee company.2023-12-20T22:03:30+09:00Copyright (c) 2023 Suswandi, Moh Erkamimhttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1608Z-Score and Floyd Warshall Algorithms for Determining Alternative Routes of Mugging-Prone Areas in Medan City, Indonesia2024-01-17T19:41:24+09:00Rozzi Kesuma Dinatarozzikesumadinata@gmail.comBustami Bustamibustami@unimal.ac.idFiasari Fiasarifiasari@mhs.unimal.ac.idSujacka Retnosujacka@unimal.ac.idThis 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 <em>Porlestabes</em> (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.2023-12-20T22:03:30+09:00Copyright (c) 2023 Rozzi Kesuma Dinata, Bustami Bustami, Fiasari Fiasari, Sujacka Retnohttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1636Realtime Monitoring and Analysis Based on Cloud Computing Internet of Things (CC-IoT) Technology in Detecting Forest and Land Fires in Riau Province2024-01-17T19:45:17+09:00Yuda Irawanyudairawan89@gmail.comRometdo Muzawirometdomuzawi@gmail.comAgus Alamsyahagus41@gmail.comReno Renaldirenorenaldi03@gmail.comElisawati Elisawatielisawati112@gmail.comNurhadi Nurhadiflinkdumai@gmail.comMohd Rinaldi Amarthaamartharc@gmail.comAbdullah Mitrinabdullahmitrin@htp.ac.idHadi Asnalhadiasnal@stmik-amik-riau.ac.idZupri Henra Hartomizupri.henra@gmail.com<p>Forest and land fires in Riau are natural disasters that always repeat every time they enter the dry season. The solution of this research is to apply the leading technology of cloud computing internet of things (CC-IoT) to find out more quickly the existence of forest or land fires. This study uses Particle Argon (Photon) to connect to the internet and several IR Fire Detector sensors, DHT22 MQ2 and GPS Neo 6m. Particle Argon can receive input and perform processing so that it is connected using the CC-IoT concept to a web server so the users can monitor land conditions in real time. Based on the test results, it can be concluded that a fire detector using fire parameters (2000 = Normal and > 2000 = Danger) , temperature (≤37 = Normal, 38 – 45 = Alert, and 46 = Danger), humidity (≤50 = Dry, 51 = Humid) , smoke (≤ 1700 = Normal, > 1700 = Danger), and soil moisture can work well (> 3500 = Dry Moisture Content, 1500 to 3500 = Medium Moisture Content, and < 1500 = High Moisture Content). The fire detection tool developed can detect fires in real time and also has a fire early detection function that is useful for anticipating land conditions to prevent fires. The results obtained from the test are that the sensor can read indications of fire, smoke, soil moisture with a success rate of 93% and send location data and sensor values to the website. The use of sensors has their respective roles so that if there is a problem with one of the sensors, the tool has an alternative sensor and can continue to function.</p>2023-12-20T22:03:30+09:00Copyright (c) 2023 Yuda Irawan, Rometdo Muzawi, Agus Alamsyah, Reno Renaldi, Elisawati, Nurhadi, Mohd Rinaldi Amartha, Abdullah Mitrin, Hadi Asnal, Zupri Henra Hartomihttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1906Comparative Analysis of Long Short-Term Memory Architecture for Text Classification2024-01-17T19:48:38+09:00Moh Fajar Abdillahmoh.abdillah@students.amikom.ac.idKusnawi Kusnawikhusnawi@amikom.ac.id<p>Text classification which is a part of NLP is a grouping of objects in the form of text based on certain characteristics that show similarities between one document and another. One of methods used in text classification is LSTM. The performance of the LSTM method itself is influenced by several things such as datasets, architecture, and tools used to classify text. On this occasion, researchers analyse the effect of the number of layers in the LSTM architecture on the performance generated by the LSTM method. This research uses IMDB movie reviews data with a total of 50,000 data. The data consists of positive, negative data and there is data that does not yet have a label. IMDB Movie Reviews data go through several stages as follows: Data collection, data pre-processing, conversion to numerical format, text embedding using the pre-trained word embedding model: Fastext, train and test classification model using LSTM, finally validate and test the model so that the results are obtained from the stages of this research. The results of this study show that the one-layer LSTM architecture has the best accuracy compared to two-layer and three-layer LSTM with training accuracy and testing accuracy of one-layer LSTM which are 0.856 and 0.867. While the training accuracy and testing accuracy on two-layer LSTM are 0.846 and 0.854, the training accuracy and testing accuracy on three layers are 0.848 and 864.</p>2023-12-20T22:03:30+09:00Copyright (c) 2023 Moh Fajar Abdillah, Kusnawi Kusnawihttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1614The Application of Weighted Ranking Method Using Combination of ROC and CPI to Select Eligible Family for Keluarga Harapan Program Aids2024-01-17T19:53:39+09:00Aishiyah Saputri Laswiaishiyah.rustam@gmail.comUlvah Ulvahulvahinformatik@gmail.comDasril Dasrildasrilbachmid@gmail.comThe <em>Keluarga Harapan Program</em> (KHP), a financial assistance, is a program launched by the government to deal with poverty in various regions of Indonesia by conducting direct surveys and collecting data on disadvantaged families in each region. However, the issue is that many recipients do not meet the appropriate criteria or are not categorized as recipients. The Composite Performance Index and Rank Centeroid algorithms are a solution in the selection process for the recipients for the KHP by carrying out the analysis and comparison stages of whether they are categorized as KM (Disadvantage Families) through several stages. The results obtained based on analysis for recipient selection with a minimum performance index coverage value of 70% can be categorized as eligible to receiv assistance. In this study, 50 KM data samples were taken with the highest assessment value 128.41. In the top tenth ranking of the highest score from the 50 data held indicated that they were truly entitled to receive PKH KM financial assistance. Before using this method, only around 40% was eligible recipients.2023-12-20T22:03:30+09:00Copyright (c) 2023 Aishiyah Saputri Laswi, Ulvah Ulvah, Ulvah Ulvahhttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1775Analysis of Twitter User Sentiment on Presidential Candidate Anies Baswedan Using Naïve Bayes Algorithm2024-01-17T19:59:22+09:00Rudi Setiawanrudi@trilogi.ac.idFitria Dewifitria.dewi@trilogi.ac.id<p><span>Indonesian hold presidential election in 2024. One of the most discussed topics by public is the presidential candidates. The discussion about the presidential candidate certainly reaped various kinds of responses from public, ranging from support to statements of disapproval. </span><span>This research was limited to the candidacy of <em>Anies Baswedan</em> as a presidential candidate before a vice president candidate as his pair was selected. </span><span>The purpose of this study is to conduct a sentiment analysis of public responses regarding Indonesia 2024 presidential candidate <em>Anies Baswedan</em> using <em>tweets</em> data from October 2022 to January 2023 using the <em>naïve bayes classifier algorithm</em>. This is expected to provide<em> </em>an overview of the public opinions on Twitter. Three test models were carried out with differences in the division of the amount of training data and test data, respectively 60%:40%, 70%:30% and 80%:20%. The test results showed the highest accuracy level was obtained by the 3<sup>rd</sup> model using training and testing data of 80%:20% with an accuracy value of 76.21%. </span><span>Further research is recommended to conduct sentiment analysis on the pairs of Presidential and Vice-Presidential candidates who have been officially registered with the General Election Commission using various other classification algorithms.</span></p>2023-12-20T22:03:30+09:00Copyright (c) 2023 Rudi Setiawan, Fitria Dewihttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1780MobileNet Classifier for Detecting Chest X-Ray Images of COVID-19 based on Convolutional Neural Network2024-01-17T20:03:52+09:00ST. Aminah Dinayati Ghaniindo.intan@undipa.ac.idIndo Intanindo.intan@undipa.ac.idMuhammad Rizalmuhammad.rizal@undipa.ac.id<p><span>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.</span></p>2023-12-20T22:03:31+09:00Copyright (c) 2023 ST. Aminah Dinayati Ghani, Indo Intan, Muhammad Rizalhttps://jurnal.fikom.umi.ac.id/index.php/ILKOM/article/view/1702MobileNet V2 Implementation in Skin Cancer Detection2024-01-17T20:07:24+09:00Windha Mega Pradnya Dhuhitawindha@amikom.ac.idMuhammad Yahya Ubaidmuhammad.ubaid@students.amikom.ac.idAnna Baitaanna@amikom.ac.id<p>Skin cancer is one of the most worrying diseases for humans. In Indonesia alone, skin cancer occupies the third position after cervical cancer and breast cancer. Currently, doctors still use the biopsy method to diagnose skin cancer. It is less effective because this method requires the performance of an experienced doctor, takes a long time, and is a painful process. Because of that, we need a way in which skin cancer can be classified using dermoscopic images to help doctors diagnose skin cancer earlier. Researchers proposed to classify skin cancer into seven classes, namely actinic keratoses, basal cell carcinoma, benign keratosis-like lesions, dermatofibroma, melanoma, melanocytic nevus, and vascular lesions. The method used in this study is a convolutional neural network (CNN) with the MobileNet V2 architecture. The dataset used is the HAM10000 dataset, with a total of 10015 images. In this study, a comparison was made between data augmentation, learning rate, epochs, and different amounts of data. Based on the test results, the highest accuracy results were obtained, namely 79%. The best model is implemented into a mobile application.</p>2023-12-20T22:03:31+09:00Copyright (c) 2023 Windha Mega Pradnya Dhuhita, Muhammad Yahya Ubaid, Anna Baita