Implementasi Algoritma YOLOv5 dalam Desain Sistem Pintar untuk Identifikasi Objek pada Conveyor Pemilah Sampah
DOI:
https://doi.org/10.22441/jitkom.v9i1.005Kata Kunci:
conveyor pemilah sampah, identifikasi objek, machine learning, sistem pintar, YOLOv5Abstrak
Penelitian ini mengevaluasi penerapan algoritma YOLOv5 dalam sistem pintar untuk identifikasi objek pada conveyor pemilah sampah, dengan tujuan meningkatkan efisiensi dan akurasi pemilahan sampah organik dan anorganik. Eksperimen ini menemukan beberapa kendala, termasuk resolusi gambar yang tidak optimal dan variasi data yang terbatas, yang berdampak pada kinerja model. Untuk mengatasi kendala tersebut, disarankan untuk meningkatkan kualitas gambar dan memperluas variasi serta jumlah data latih, termasuk penggunaan teknik augmentasi data untuk memperkaya dataset. Dengan peningkatan ini, diharapkan sistem dapat lebih efektif dalam otomatisasi pemilahan sampah, mengurangi ketergantungan pada tenaga kerja manual, dan meningkatkan efisiensi pengelolaan sampah. Penelitian ini menunjukkan potensi penerapan teknologi ini tidak hanya dalam skala industri, tetapi juga di kota-kota besar yang memerlukan solusi efisien dalam pengelolaan limbah. Dataset yang digunakan mencakup 17.365 gambar sampah organik dan anorganik, dengan model YOLOv5 dilatih menggunakan 50 epochs dan batch size 16. Model ini mencapai nilai mAP@0,5 sebesar 55,8% dan akurasi total 64%, menunjukkan kemampuan yang cukup baik dalam identifikasi dan klasifikasi sampah, meskipun ada ruang untuk perbaikan lebih lanjut.
Referensi
N. A. Pamungkas, E. Y. R. R., "Efektivitas Dinas Lingkungan Hidup dalam Pengelolaan Sampah di Provinsi Daerah Khsusus Ibukota Jakarta," 2022. [Online]. Available: https://doi.org/10.5281/zenodo.6301634.
M. Yunus, "Rancangan Bangun Prototipe Tempat Sampah Pintar Pemilah Sampah Organik dan Anorganik Menggunakan Arduino," 2019. [Online]. Available: https://journal-iasssf.com/index.php/JWSC.
Q. Zhou, H. Liu, Y. Qiu, and W. Zheng, "Object Detection for Construction Waste Based on an Improved YOLOv5 Model," Sustainability (Switzerland), vol. 15, no. 1, 2023. [Online]. Available: https://doi.org/10.3390/su15010681.
F. Akhyar, L. Novamizanti, and T. Riantiarni, "Sistem Inspeksi Cacat pada Permukaan Kayu menggunakan Model Deteksi Obyek YOLOv5," ELKOMIKA: Jurnal Teknik Energi Elektrik, Teknik Telekomunikasi, & Teknik Elektronika, vol. 10, no. 4, pp. 990, 2022. [Online]. Available: https://doi.org/10.26760/elkomika.v10i4.990.
L. Cheng, Y. Ji, C. Li, X. Liu, and G. Fang, "Improved SSD network for fast concealed object detection and recognition in passive terahertz security images," Scientific Reports, vol. 12, no. 1, 2022. [Online]. Available: https://doi.org/10.1038/s41598-022-16208-0.
E. N. Staf Pengajar, L. H. Prof Soedarto SH, and T., "Perancangan Sistem Kontrol Pembangkit Listrik Tenaga Hybrid (PLN dan PLTS) Kapasitas 800 WP," Vol. 17, Issue 3, 2021. [Online]. Available: https://rakhman.net/power-plantsid/jenis.
H. Purwantoro, "Penerapan Algoritma YoloV5 Dalam Pendeteksian Objek Merek Sampah Botol Plastik," 2024. [Online]. Available: www.makesense.ai.
D. A. Rumansyah, S. Amini, and S. Mulyati, "Rancangan Alat Pemilah Sampah Otomatis Menggunakan Sensor Ultrasonik HC-SR04, Microcontroller Nodemcu, dan Sensor Proximity," SKANIKA: Sistem Komputer dan Teknik Informatika, vol. 5, no. 1, 2022
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that this paper has not been published in the same form elsewhere.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above-mentioned paper as a whole to UMB. The copyright transfer covers the right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
Our Articles are licensed under CC BY-NC
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
