Pengembangan Sistem Deteksi Digit pada Meteran Air PDAM Menggunakan Model Deep Learning YOLOv5
Keywords:
PDAM, YOLO, Python, Augmentasi, Deep Learning, AutomasiAbstract
The use of PDAM (Regional Drinking Water Company) water meters has become the standard for measuring water consumption by customers in Indonesia. However, the process of reading water meters is still mostly done manually by officers, which can cause various problems. For example, reading errors can occur due to human factors or environmental conditions, such as poor lighting or a dirty water meter. Additionally, this process requires a lot of time and effort and has the potential to lead to fraud. To overcome this challenge, this research focuses on developing a digit detection system for PDAM water meters using the YOLOv5 deep learning model. Using a dataset covering various lighting conditions and viewing angles, the model is trained to recognize and classify the digits on water meters. Initial results show that this model can produce accurate predictions, with high levels of precision and recall. However, more testing and evaluation are needed to ensure that these systems can perform well in real-world conditions.
References
[1] Hermawan, Indra. "Rancang Bangun Sistem Pendeteksi dan Pengenalan Angka Pada Meteran Air PDAM Menggunakan Metode Template Matching Correlation." Jurnal Teknologi Terpadu 1.2 (2015).
[2] Juwiantho, Hans, Esther Irawati Setiawan, and Joan Santoso. "Image Sentiment Analysis Menggunakan Deep Convolutional Neural Network Dengan Fitur Konsep." The 12th National Conference on Information Technology and Electrical Engineering. 2019.
[3] Widiasari, Cyntia, and Laxsmana Anugrah Zulkarnain. "Rancang Bangun Sistem Monitoring Penggunaan Air PDAM Berbasis IoT." Jurnal Komputer Terapan 7.2 (2021): 153-162.
[4] GARDAMUKTI, M. GALANG. Metode You Only Look Once (YOLO) untuk Sistem Pengenalan Rambu Lalu Lintas. Diss. Universitas Gadjah Mada, 2021.
[5] Redmon, Joseph, et al. "You only look once: Unified, real-time object detection." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
[6] Aini, Q., et al. "Deteksi dan Pengenalan Objek Dengan Model Machine Learning: Model Yolo. CESS (Journal of Computer Engineering, System and Science), 6 (2), 192." (2021).
[7] Ganda, Lukas Hansel, and Hendra Bunyamin. "Penggunaan Augmentasi Data pada Klasifikasi Jenis Kanker Payudara dengan Model Resnet-34." Jurnal STRATEGI-Jurnal Maranatha 3.1 (2021): 187-193.
[8] Lin, Moule, Changxi Chen, and Chunchi Lai. "Object detection algorithm based AdaBoost residual correction Fast R-CNN on network." Proceedings of the 2019 3rd International Conference on Deep Learning Technologies. 2019.
[9] Lusiana, Lusiana, Ari Wibowo, and Tika Kartika Dewi. "Implementasi Algoritma Deep Learning You Only Look Once (YOLOv5) Untuk Deteksi Buah Segar Dan Busuk." Paspalum: Jurnal Ilmiah Pertanian 11.1 (2023): 123-130.
[10] Darmawan, Refianto Damai. Optimasi Deep Learning untuk Prediksi Drug-Target Interaction dengan Graphic Processing Unit. Diss. IPB University.
[11] Horvat, Marko, and Gordan Gledec. "A comparative study of YOLOv5 models performance for image localization and classification." Central European Conference on Information and Intelligent Systems. Faculty of Organization and Informatics Varazdin, 2022.
[12] Tu, Xiaoguang, et al. "An improved YOLOv5 for object detection in visible and thermal infrared images based on contrastive learning." Frontiers in Physics 11 (2023): 354.
[13] Aldughayfiq, Bader, et al. "YOLOv5-FPN: A Robust Framework for Multi-Sized Cell Counting in Fluorescence Images." Diagnostics 13.13 (2023): 2280.
[14] Oraño, Jannie Fleur V., et al. "Automated Coral Lifeform Classification Using YOLOv5: A Deep Learning Approach." Novel & Intelligent Digital Systems Conferences. Cham: Springer Nature Switzerland, 2023.
