Deteksi Sampah Organik dan Anorganik Menggunakan Model YOLO Berbasis Dataset Roboflow

Miftahuddin Fahmi, Faisal Reza Pradhana, Muhammad Daffa Nurahman

Abstract


Upaya memilah sampah organik dan anorganik di Indonesia masih jauh dari ideal, terutama karena keterbatasan sarana pendukung dan rendahnya partisipasi masyarakat. Kondisi ini menunjukkan perlunya pendekatan yang lebih otomatis agar proses identifikasi jenis sampah tidak sepenuhnya bergantung pada interaksi manusia. Penelitian ini mengeksplorasi kemampuan algoritma deteksi objek YOLOv8 dalam membedakan dua kategori sampah melalui citra. Sebanyak 3.169 gambar dari platform Roboflow digunakan sebagai dataset, kemudian model dilatih menggunakan skema transfer learning dengan bobot awal YOLOv8n pada resolusi 640×640 piksel selama 100 epoch. Kinerja model dinilai menggunakan metrik Precision, Recall, serta mean Average Precision (mAP). Model menghasilkan Precision 0,968, Recall 0,970, mAP@0,5 sebesar 0,986, dan mAP@0,5:0,95 mencapai 0,922. Hasil tersebut mengindikasikan bahwa YOLOv8 mampu melakukan identifikasi objek sampah secara akurat dan stabil, sehingga berpotensi menjadi komponen inti dalam pengembangan sistem pengelolaan sampah berbasis visi komputer di masa depan.

Keywords


YOLOv8; Deteksi Objek; Sampah Organik; Sampah Anorganik; Smart Waste Management

Full Text:

PDF

References


R. Puspita, “KLHK: Jumlah Timbunan Sampah di Indonesia Capai 29,8 Juta Ton pada 2021,” 27 September. Accessed: Apr. 29, 2025. [Online]. Available: https://news.republika.co.id/berita/riv7wa428/klhk-jumlah-timbunan-sampah-di-indonesia-capai-298-juta-ton-pada-2021

P. Rainer, “Alasan Separuh Masyarakat RI Tidak Memilah Sampah,” 22 Agustus. Accessed: Apr. 29, 2025. [Online]. Available: https://data.goodstats.id/statistic/alasan-separuh-masyarakat-ri-tidak-memilah-sampah-5Dm7e

D. S. Al-Fajri, “Mereka yang Tidak Memilah Sampah: 71,3% Merasa Merepotkan dan Bukan Tanggung Jawab,” 30 November. Accessed: Apr. 29, 2025. [Online]. Available: https://goodstats.id/article/mereka-yang-tidak-memilah-sampah-67-3-merasa-merepotkan-dan-bukan-sebuah-tanggung-jawab-OgWBK

H. Khalid, “Buruknya Kebiasaan Buang Sampah Masyarakat Indonesia.” Accessed: Nov. 18, 2025. [Online]. Available: https://environment-indonesia.com/buruknya-kebiasaan-buang-sampah-masyarakat-indonesia/

B. Prasetio and N. Pratiwi, “Deteksi sampah organik dan anorganik menggunakan model yolov8,” vol. 10, no. 1, pp. 494–506, 2025.

Y. Arvio, D. T. Kusuma, I. B. Sangadji, and S. Karmila, “Aplikasi Sistem Deteksi Sampah Organik dan Non Organik Menggunakan Algoritma YOLO V8,” 2023. [Online]. Available: https://snekti.jurnal-puslitbangpln.id/submit/index.php/snekti2023/article/view/265

M. Fuchs, “The Data Science Process (CRISP-DM),” 21 Agustus. Accessed: Oct. 31, 2025. [Online]. Available: https://michael-fuchs-python.netlify.app/2020/08/21/the-data-science-process-crisp-dm/

Ultralytics, “Brief summary of YOLOv8 model structure,” 10 January. Accessed: Oct. 31, 2025. [Online]. Available: https://github.com/ultralytics/ultralytics/issues/189

Z. Piao, J. Wang, L. Tang, B. Zhao, and S. Zhou, “Anchor-Free Object Detection with Scale-Aware Networks for Autonomous Driving,” pp. 1–15, 2022.

B. Zhao, Q. Cui, R. Song, Y. Qiu, and J. Liang, “Decoupled Knowledge Distillation,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 11943–11952, 2022, doi: 10.1109/CVPR52688.2022.01165.

Ultralytics, “Ultralytics/ultralytics – Ultralytics YOLO.” Accessed: Oct. 31, 2025. [Online]. Available: https://github.com/ultralytics/ultralytics

J. Terven, D. M. Córdova-Esparza, and J. A. Romero-González, “A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Mach. Learn. Knowl. Extr., vol. 5, no. 4, pp. 1680–1716, 2023, doi: 10.3390/make5040083.

IBM, “Data Leakage in Machine Learning.” Accessed: Nov. 11, 2025. [Online]. Available: https://www.ibm.com/think/topics/data-leakage-machine-learning

A. Megantara and E. Utami, “Object Detection Using YOLOv8 : A Systematic Review,” vol. 14, pp. 1186–1193, 2025.

J. Bento, T. Paixão, and A. B. Alvarez, “Performance Evaluation of YOLOv8 , YOLOv9 , YOLOv10 , and YOLOv11 for Stamp Detection in Scanned Documents,” 2025.

G. Yao, S. Zhu, L. Zhang, and M. Qi, “HP-YOLOv8 : High-Precision Small Object Detection Algorithm for Remote Sensing Images HP-YOLOv8 : High-Precision Small Object Detection,” 2024, doi: 10.20944/preprints202406.1963.v1.

Z. Han, Y. Cai, A. Liu, Y. Zhao, and C. Lin, “MS-YOLOv8-based object detection method for pavement diseases,” Sensors, vol. 24, no. 4569, 2024.

C. Consortium, “COCO (Common Objects in Context) dataset.” Accessed: Nov. 01, 2025. [Online]. Available: https://cocodataset.org/#home

A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” 2020, [Online]. Available: http://arxiv.org/abs/2004.10934

M. R. Ridha, S. Syafrijon, Y. Hendriyani, and A. Hadi, “Implementasi Model Yolov8 untuk Deteksi Jenis Sampah Organik dan Anorganik Berbasis Android,” Abdimas Indones. J., vol. 5, no. 1, pp. 419–426, 2025, doi: 10.59525/aij.v5i1.655.

Y. Arvio, D. T. Kusuma, and I. BM Sangadji, “Inorganic Waste Detection Application Using Smart Computing Technology with YOLOv8 Method,” Sinkron, vol. 8, no. 4, pp. 2389–2396, 2024, doi: 10.33395/sinkron.v8i4.14117.

A. S. J, J. S. R, R. V. M, and M. P. G, “Real-Time Organic And Inorganic Object Detection Using Yolo Model,” pp. 1968–1970, 2025.




DOI: http://dx.doi.org/10.36448/jsit.v16i2.4600

Refbacks

  • There are currently no refbacks.


About the JournalJournal PoliciesAuthor Information

Explore: Jurnal Sistem Informasi dan Telematika (Telekomunikasi, Multimedia dan Informatika)
e-ISSN: 2686-181X
Website: http://jurnal.ubl.ac.id/index.php/explore
Email: explore@ubl.ac.id
Published by: Pusat Studi Teknologi Informasi, Fakultas Ilmu Komputer, Universitas Bandar Lampung
Office: Jalan Zainal Abidin Pagar Alam No 89, Gedong Meneng, Bandar Lampung, Indonesia

This work is licensed under a Creative Commons Attribution 4.0 International License
Technical Support by:  RYE Education Hub