Artificial Intelligence for Detecting Illegal Waste Dumping in River
DOI:
https://doi.org/10.31851/ampere.v11.i1.20704Keywords:
Artificial Intelligence, Waste Detection, Illegal Waste Dumping, River Monitoring, Image ProcessingAbstract
This study developed a river waste detection system using the YOLOv8 algorithm to recognize human and waste objects in real time. The dataset was obtained from CCTV recordings of the Sekanak River, then underwent annotation and augmentation processes to improve the model's resilience to variations in lighting and environmental conditions. The model was trained with several configurations, and the best results were obtained at 100 epochs with a mAP@0.5 of 0.88 and stable validation. The system was tested
on 10 daytime and nighttime image samples to assess its detection performance in the field. Based on the testing, the system detected human objects with a precision of 90.9% and trash with a precision of 81.8%, with an overall accuracy of 86.3%. Although the results were quite accurate, detection at night showed increased noise due to minimal light and water reflections, which could lead to false detection. Overall, the application of this technology can be a solution to support automatic and sustainable river monitoring in
a smart environmental monitoring system. However, improvements in dataset quality and methods for handling visual disturbances are still needed to achieve more optimal.
References
[1] R. Theofilus and R. Kurniawan, “Deteksi Sampah di Permukaan Sungai menggunakan Convolutional Neural Network dengan Algoritma YOLOv8 Studi Kasus: Sungai Ciliwung (Detection of Floating Wastes on River Surface using Convolutional Neural Network with YOLOv8 Algorithm (Case Study: Ciliwung River)).”
[2] Rifqi Fadhila Shandi, Meta Kallista, and Casi Setianingsih, “Penggunaan Algoritma YOLOv8 untuk Deteksi Jenis Sampah: Studi Implementasi di Website Bank Sampah Bersinar,” 2024.
[3] B. Fang et al., “Artificial intelligence for waste management in smart cities: a review,” Aug. 01, 2023, Springer Science and Business Media Deutschland GmbH. doi: 10.1007/s10311-023-01604-3.
[4] F. M. Assef, M. T. A. Steiner, and E. P. de Lima, “A review of clustering techniques for waste management,” Jan. 01, 2022, Elsevier Ltd. doi: 10.1016/j.heliyon.2022.e08784.
[5] D. B. Olawade, O. Z. Wada, A. O. Ige, B. I. Egbewole, A. Olojo, and B. I. Oladapo, “Artificial intelligence in environmental monitoring: Advancements, challenges, and future directions,” Dec. 01, 2024, Elsevier B.V. doi: 10.1016/j.heha.2024.100114.
[6] M. Hussain, “YOLO-v1 to YOLO-v8, the Rise of YOLO and Its Complementary Nature toward Digital Manufacturing and Industrial Defect Detection,” Jul. 01, 2023, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/machines11070677.
[7] I. Purwita Sary, E. Ucok Armin, S. Andromeda, E. Engineering, and U. Singaperbangsa Karawang, “Performance Comparison of YOLOv5 and YOLOv8 Architectures in Human Detection Using Aerial Images,” Ultima Computing : Jurnal Sistem Komputer, vol. 15, no. 1, 2023.
[8] L. Chen and J. Zhu, “Water surface garbage detection based on lightweight YOLOv5,” Sci. Rep., vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-55051-3.
[9] P. Sharma, K. Srinivasan, M. M. Azizan, K. Hasikin, A. Salwa, and M. Khairuddin, “An automated solid waste detection using the optimized YOLO model for riverine management.”
[10] J. Gunaseelan, S. Sundaram, and B. Mariyappan, “A Design and Implementation Using an Innovative Deep-Learning Algorithm for Garbage Segregation,” Sensors, vol. 23, no. 18, Sep. 2023, doi: 10.3390/s23187963.
[11] I. E. Agbehadji, A. Abayomi, K. H. N. Bui, R. C. Millham, and E. Freeman, “Nature-Inspired Search Method and Custom Waste Object Detection and Classification Model for Smart Waste Bin,” Sensors, vol. 22, no. 16, Aug. 2022, doi: 10.3390/s22166176.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Nyayu Latifah Husni, Husnawati, Rossi Passarella, Sopian Soim, Deden Lasmana, Sabilal Rasyad, Ade silvia Handayani
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Jurnal Ampere is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
