Optimasi Kinerja Arsitektur CNN Ringan Menggunakan Pendekatan Bayesian untuk Identifikasi Skrip Bima
Dayang Aisyah(1); Muhammad Faisal(2*); Lukman Anas(3); Abd Rakhim Nanda(4); Syadiah Nor Wan Shamsuddin(5); Muhammad Syafaat S. Kuba(6);
(1) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(2) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(3) Informatika, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(4) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(5) Faculty of Informatics and Computing, Universiti Sultan Zainal Abidin, Terengganu, Malaysia
(6) Teknik Pengairan, Universitas Muhammadiyah Makassar, Makassar, Indonesia
(*) Corresponding Author
AbstractIdentifikasi aksara daerah penting untuk mendukung pelestarian budaya digital, namun masih terkendala keterbatasan dataset, kemiripan karakter, dan kebutuhan model yang efisien. Penelitian ini mengoptimasi arsitektur Lightweight CNN menggunakan Bayesian Optimization untuk identifikasi aksara Bima. Dataset terdiri atas 6.190 citra aksara Bima dalam 44 kelas, mencakup aksara Bima baru dan lama. Model menggunakan MobileNetV3-Large sebagai backbone dengan optimasi learning rate, dropout, batch size, dan konfigurasi fine-tuning melalui Tree-structured Parzen Estimator. Hasil eksperimen menunjukkan accuracy 93,06%, precision 92,26%, recall 92,55%, dan F1-score 91,91%, lebih unggul dibanding machine learning tradisional, CNN konvensional, dan beberapa CNN ringan modern. Target accuracy 90% dicapai pada trial keempat. Dengan 3.253.676 parameter dan waktu inferensi 63,35 ms per citra, model ini terbukti akurat, efisien, dan berpotensi diterapkan pada digitalisasi manuskrip serta OCR aksara daerah.
KeywordsAksara Bima; Lightweight CNN; Bayesian Optimization; Klasifikasi Citra; Pelestarian Digital;
|
Full Text:PDF |
Article MetricsAbstract view: 107 timesPDF view: 42 times |
Digital Object Identifier https://doi.org/10.33096/busiti.v7i2.3462
|
Cite |
References
H. Assemlali, S. Bouhsissin, and N. Sael, “Green Energy and Intelligent Transportation Deep learning-driven CNN model for detection and classification of dynamic obstacles,” Green Energy Intell. Transp., vol. 5, no. 3, p. 100334, 2026, doi: 10.1016/j.geits.2025.100334.
N. Paul, G. C. Sunil, D. Horvath, and X. Sun, “Deep learning for plant stress detection : A comprehensive review of technologies , challenges , and future directions,” Comput. Electron. Agric., vol. 229, no. December 2024, p. 109734, 2025, doi: 10.1016/j.compag.2024.109734.
A. A. Handoko, “Implementasi Convolutional Neural Network ( CNN ) Untuk Pengenalan Tulisan Tangan Aksara Bima,” vol. 14, no. 1, pp. 96–110, 2024, doi: 10.32664/smatika.v14i01.1196.
F. F. Imron Ichwani, “Sejarah Perkembangan Ilmu Pengetahuan Dan Teknologi Dalam Islam,” UJII, vol. 13, no. No. 2, pp. 313–326, 2023, doi: https://doi.org/10.47200/ulumuddin.v13i2.2085.
P. Karthika and M. Premkumar, “Advances in Biomarker Sciences and Technology An in-depth exploration of CNN-based deep learning models in cervical carcinoma analysis,” Adv. Biomark. Sci. Technol., vol. 8, no. October 2025, pp. 19–33, 2026, doi: 10.1016/j.abst.2025.11.007.
R. Raju and T. M. Thasleema, “Franklin Open BO-CNN : A deep learning framework with Bayesian hyperparameter tuning for nutrient stress classification in Piper nigrum,” Franklin Open, vol. 13, no. October, p. 100444, 2025, doi: 10.1016/j.fraope.2025.100444.
D. Xinjie et al., “ScienceDirect A Lightweight Deep Learning Model for Aerial Image Classification A Lightweight Deep Learning Model for Aerial Image Classification and Its Application to UAV-based Disaster Management and Its Application to UAV-based Disaster Management,” 2024, doi: 10.1016/j.procs.2024.09.395.
P. Mishra, “Chemometrics and Intelligent Laboratory Systems A tutorial on automatic hyperparameter tuning of deep spectral modelling for regression and classi fi cation tasks,” vol. 223, no. February, 2022, doi: 10.1016/j.chemolab.2022.104520.
T. Zheng, X. Yang, J. Lv, M. Li, S. Wang, and W. Li, “Engineering Science and Technology , an International Journal An efficient mobile model for insect image classification in the field pest management,” Eng. Sci. Technol. an Int. J., vol. 39, p. 101335, 2023, doi: 10.1016/j.jestch.2023.101335.
A. Syauqi and A. Prasetya, “Advances in machine transliteration methods , limitations , challenges , applications and future directions,” Nat. Lang. Process. J., vol. 11, no. December 2024, p. 100158, 2025, doi: 10.1016/j.nlp.2025.100158.
Y. Wang, Y. Su, Z. Zheng, Z. Zhou, and X. Wang, “Developments in the Built Environment Bayesian-optimized CNN-LSTM neural network for predicting road construction dust concentrations,” Dev. Built Environ., vol. 25, no. October 2025, p. 100843, 2026, doi: 10.1016/j.dibe.2026.100843.
A. Allazem and E. Mohamedelhassan, “Geodata and AI A hybrid deep learning-Bayesian optimization model for enhanced slope stability classification,” Geod. AI, vol. 5, no. July, p. 100030, 2025, doi: 10.1016/j.geoai.2025.100030.
M. Joy, M. Santhosh, T. Park, and R. Mallipeddi, “Heliyon Bayesian optimization of convolutional neural network for identifying red wines using colorimetric sensors,” Heliyon, vol. 12, no. 2, p. e44387, 2026, doi: 10.1016/j.heliyon.2025.e44387.
J. Omor, M. Abu, T. Rony, and M. Shariful, “BNVGLENET : Hypercomplex Bangla handwriting character recognition with hierarchical class expansion using Convolutional Neural Networks,” Nat. Lang. Process. J., vol. 7, no. June 2023, p. 100068, 2024, doi: 10.1016/j.nlp.2024.100068.
T. Saleh et al., “Knowledge-Based Systems A vision transformer-based hybrid neural architecture for automated handwritten Bangla character recognition and braille conversion,” Knowledge-Based Syst., vol. 330, no. PB, p. 114546, 2025, doi: 10.1016/j.knosys.2025.114546.
M. S. Elhadidy, A. T. Elgohr, A. Mousa, A. Safwat, R. Ismail, and H. M. Kasem, “Results in Engineering Benchmarking Pre-trained CNNs and Vision Transformers for Mpox-related Dermatological Image Classification on MSLD v2 . 0,” Results Eng., vol. 28, no. October, p. 108071, 2025, doi: 10.1016/j.rineng.2025.108071.
M. Faisal et al., “Utilizing Machine Learning-Based Decision-Making to Align Higher Education Curriculum with Industry Requirements,” Int. J. Mod. Educ. Comput. Sci., vol. 17, no. 4, pp. 1–25, Aug. 2025, doi: 10.5815/ijmecs.2025.04.01.
L. Kang, X. Fu, L. Gomez, A. Fornés, and E. Valveny, “Preserving privacy without compromising accuracy : Machine unlearning for handwritten text recognition,” Pattern Recognit., vol. 172, no. PA, p. 112411, 2026, doi: 10.1016/j.patcog.2025.112411.
W. Xu et al., “Smart Agricultural Technology Real-time pest monitoring with RSCDet : Deploying a novel lightweight detection model on embedded systems,” Smart Agric. Technol., vol. 12, no. May, p. 101280, 2025, doi: 10.1016/j.atech.2025.101280.
D. Guo et al., “Smart Agricultural Technology SMA-YOLO : An enhanced architecture for the detection of corn diseases based on YOLOv12,” vol. 12, no. October, 2025, doi: https://doi.org/10.1016/j.atech.2025.101502.
N. Deluxni and P. Sudhakaran, “Results in Engineering Underwater debris detection using YOLOv12 with enhanced feature extraction using R-ELAN and FlashAttention network,” Results Eng., vol. 28, no. September, p. 107282, 2025, doi: 10.1016/j.rineng.2025.107282.
J. Zhu, L. Liu, W. Kou, G. Chen, and X. Li, “Smart Agricultural Technology YOLO-CDD : Real-time and accurate detection of latex collection bowl and flow states with enhanced multi-scale feature fusion,” Smart Agric. Technol., vol. 12, no. August, p. 101305, 2025, doi: 10.1016/j.atech.2025.101305.
V. G. Dhanya et al., “Arti fi cial Intelligence in Agriculture Deep learning based computer vision approaches for smart agricultural applications,” Artif. Intell. Agric., vol. 6, pp. 211–229, 2022, doi: 10.1016/j.aiia.2022.09.007.
F. Olubusola and M. Olusoji, “Heliyon Deep learning and content-based filtering techniques for improving plant disease identification and treatment recommendations : A comprehensive review,” Heliyon, vol. 10, no. 9, p. e29583, 2024, doi: 10.1016/j.heliyon.2024.e29583.
Y. Saini, V. Somani, and N. Khatri, “Critical Analysis of Advanced Machine Learning and Deep Learning Models for Crop Disease Detection: Challenges, Innovations, and Future Directions,” Franklin Open, p. 100584, 2026, doi: 10.1016/j.fraope.2026.100584.
J. A. Paulson and C. Tsay, “ScienceDirect Bayesian optimization as a flexible and efficient design framework for sustainable process systems,” Curr. Opin. Green Sustain. Chem., vol. 51, p. 100983, 2025, doi: 10.1016/j.cogsc.2024.100983.
T. Kawabata, T. Tsuzuki, T. Tatsukawa, and K. Matsui, “Allergology International Black-box optimization in immunology and beyond : A practical guide to algorithms and future directions,” Allergol. Int., vol. 74, no. 4, pp. 549–562, 2025, doi: 10.1016/j.alit.2025.08.006.
X. Wen, X. Guo, S. Wang, Z. Lu, and Y. Zhang, “Biocybernetics and Biomedical Engineering Breast cancer diagnosis : A systematic review,” Biocybern. Biomed. Eng., vol. 44, no. 1, pp. 119–148, 2024, doi: 10.1016/j.bbe.2024.01.002.
H. Deshpande, D. Chaudhari, T. Sarode, A. Kamath, and D. Khan, “ScienceDirect ScienceDirect LeanConv-SENet : A A novel novel lightweight lightweight Neural Neural Network Network Architecture for for Handwritten Handwritten character character recognition recognition Architecture,” Procedia Comput. Sci., vol. 258, pp. 2826–2836, 2025, doi: 10.1016/j.procs.2025.04.543.
M. Jumarlis et al., “A hybrid hue saturation lightness, gray level co-occurrence matrix, and k-nearest neighbour for palm-sugar classification,” IAES Int. J. Artif. Intell., vol. 13, no. 3, p. 2934, Sep. 2024, doi: 10.11591/ijai.v13.i3.pp2934-2945.
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Buletin Sistem Informasi dan Teknologi Islam (BUSITI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.