Analisis Komparatif YOLOv11 Dan CNN Untuk Segmentasi Sampah Organik, Anorganik, Dan B3
DOI:
https://doi.org/10.29407/nmxkbg61Abstract
Pemilahan sampah rumah tangga masih menjadi persoalan karena sampah organik, non-organik, dan B3 sering tercampur sehingga menghambat pengolahan dan meningkatkan risiko pencemaran. Penelitian ini bertujuan merancang sistem segmentasi sampah menggunakan YOLOv11n-seg serta membandingkan hasil klasifikasinya dengan CNN EfficientNetB0. Dataset yang digunakan berformat YOLO segmentation dengan 2.893 citra dan 3.431 objek anotasi pada kelas organik, non-organik, dan B3. Tahapan penelitian meliputi analisis dataset, anotasi instance segmentation, pelatihan model, evaluasi, dan implementasi prototipe Streamlit. Hasil pengukuran evaluasi metrik YOLO dirancang menggunakan precision sebesar 92,5%, recall sebesar 91,2%, F1-score sebesar 91,9%, mAP-50 sebesar 95,6%, dan mAP 50-95 sebesar 84,4%. Sedangkan untuk pengukuran hasil metrik CNN menggunakan nilai akurasi sebesar 99,28%, precision sebesar 98,92%, recall sebesar 99,6%, F1-score sebesar 99,25%. Hasil analisis dataset menunjukkan kelas non-organik dominan dengan 1.922 objek, diikuti organik 862 objek dan B3 647 objek. Sistem ini diharapkan membantu identifikasi sampah rumah tangga secara cepat dan interaktif.
Keywords:
Segmentasi, Sampah, Machine Learning, YOLO, CNN##plugins.themes.default.displayStats.downloads##
References
[1] M. N. Fiqih and S. Syaiful, "PENEMPATAN BAK SAMPAH ORGANIK, ANORGANIK, DAN B3 DENGAN KONSEP GO GREEN PERUMAHAN BUDI AGUNG RW 03/RT 05," Jurnal Pengabdian Masyarakat, vol. 1, no. 2, pp. 71-81, 2023, doi: 10.32832/jpmuj.v1i2.
[2] M. S. Nabila, H. Herlawati, and A. Hidayat, "Pendeteksian dan Klasifikasi Sampah pada Bank Sampah Berbasis Web Menggunakan YOLOv11," J. Students Res. Comput. Sci., vol. 6, no. 1, pp. 99-112, 2025, doi: 10.31599/r5me0z35.
[3] B. A. Wisesa, V. M. Putri, E. Faristasari, S. A. J. D. Duli, and R. Lionza, "Optimizing Waste Classification Model using YOLOv11 Architecture," Int. J. Informatics Comput., vol. 7, no. 2, 2025, doi: 10.35842/ijicom.
[4] P. H. M. Mu'arif, R. Ridwan, and S. Marti'ah, "Klasifikasi Jenis Sampah Menggunakan Metode Convolutional Neural Network," J. Ris. dan Apl. Mhs. Inform., vol. 6, no. 4, pp. 886-895, 2025, doi: 10.33020/jsimtek.v3i1.795.
[5] P. N. Dacipta and R. E. Putra, "Sistem Klasifikasi Limbah Menggunakan Metode Convolutional Neural Network (CNN) Pada Web Service Berbasis Framework Flask," JINACS (Journal Informatics Comput. Sci.), vol. 3, no. 4, pp. 394-402, 2022, doi: 10.26740/jinacs.v3n04.p394-402.
[6] L. K. Ramadhani and B. N. Widyaningrum, "Implementation of YOLO v11 for Image-Based Litter Detection and Classification in Environmental Management Efforts," J. Appl. Informatics Comput., vol. 9, no. 3, pp. 617-624, 2025, doi: 10.30871/jaic.v9i3.9213.
[7] D. A. Saputra, Istiadi, and A. Y. Rahman, "DETEKSI KESEGERAN IKAN LAYUR BERDASARKAN CITRA MATA MENGGUNAKAN YOLOV8," JATI (Jurnal Mhs. Tek. Inform.), vol. 8, no. 5, pp. 10263-10270, 2024, doi: 10.36040/jati.v8i5.11020.
[8] A. Lusman, R. Devita, O. E. Putra, E. Rianti, and F. Islami, "IMPLEMENTASI COMPUTER VISION DALAM DETEKSI DAN KLASIFIKASI SAMPAH OTOMATIS PADA SISTEM PENGOLAHAN LIMBAH PERKOTAAN," J. Sains Inform. Terap., vol. 5, no. 1, pp. 115-121, 2026, doi: 10.62357/jsit.v5i1.956.
[9] J. Anggara, E. Ryansyah, and B. A. Dermawan, "IMPLEMENTASI OBJECT DETECTION DALAM KLASIFIKASI SAMPAH UNTUK MENINGKATKAN EFISIENSI PENGELOLAAN LIMBAH," JATI (Jurnal Mhs. Tek. Inform.), vol. 9, no. 3, pp. 4923-4930, 2025, doi: 10.36040/jati.v9i3.13813.
[10] N. Fajria, Lifwarda, Ramiati, and Yulindon, "Deteksi Jamur Beracun dan Tidak Beracun Menggunakan CNN dan YOLO," Elektron J. Ilm., vol. 16, no. 1, pp. 14-21, 2024, doi: 10.30630/eji.0.0.453.
[11] A. Ramdan and Asriyanik, "Implementasi Deteksi Objek Real-Time Sebagai Media Edukasi dengan Algoritma YOLOv8 pada Objek Sampah," J. SAINTEKOM, vol. 14, no. 2, pp. 142-153, 2024, doi: 10.33020/saintekom.v14i2.638.
[12] P. D. K. Sari, U. Mahdiyah, and R. Wulanningrum, "Klasifikasi Sampah Menggunakan Algoritma EfficientNet," INOTEK, vol. 9, no. 3, pp. 2074-2081, 2025, doi: 10.29407/alzq6810.
[13] R. W. L. Therry, A. Junaidi, and A. N. Sihananto, "PROGRAM PENERJEMAH BAHASA ISYARAT INDONESIA (BISINDO) SECARA REAL TIME MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN MEDIAPIPE," 2024, doi: 10.36040/jati.v8i6.11582.
[14] O. E. Karlina and D. Indarti, "PENGENALAN OBJEK MAKANAN CEPAT SAJI PADA VIDEO DAN REAL TIME WEBCAM MENGGUNAKAN METODE YOU LOOK ONLY ONCE (YOLO)," J. Ilm. Inform. Komput., vol. 24, no. 3, pp. 199-208, 2019, doi: 10.35760/ik.2019.v24i3.2362.
[15] R. I. Firdaus, W. H. Sugiharto, and M. I. Ghozali, "Implementasi Convolutional Neural Network Dalam Sistem Otomatis Pemilahan Sampah Infeksius Berbasis Citra Digital," vol. 7, no. 1, pp. 11-22, 2025, doi: 10.37278/sisinfo.v7i1.1052.
[16] F. Rifaldy, L. S. Harahap, and M. I. Prayoga, "PENGEMBANGAN SISTEM KLASIFIKASI SAMPAH UNTUK DAUR ULANG OTOMATIS BERBASIS CITRA MENGGUNAKAN MODEL CNN," Melek IT (Information Technol. Journal), vol. 11, no. 1, pp. 11-20, 2025, doi: 10.30742/melekitjournal.v11i1.397.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants 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 acknowledgment 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 acknowledgment 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
