IMPLEMENTASI OBJECT DETECTION KLASIFIKASI SAMPAH ORGANIK DAN ANORGANIK MENGGUNAKAN RASPBERRY PI DENGAN ALGORITMA YOLO

Article Sidebar

pdf
Published: 2025-08-13
DOI: https://doi.org/10.2238/hshqzw90
Keywords:
YOLOv8, Raspberry Pi, waste classification, deep learning, NCNN, real-time

Main Article Content

Devano Arayudha Adlim
Universitas Esa Unggul
Iksan Ramadhan
Universitas Esa Unggul
Bambang Irawan
Universitas Esa Unggul
Sawali Wahyu
Universitas Esa Unggul

Abstract

Waste management, particularly the separation of organic and inorganic waste, remains a challenge in campus environments. This study aims to develop an automatic waste classification system using the YOLOv8 algorithm and Raspberry Pi 5. The YOLOv8n model was selected for its lightweight and high efficiency, making it suitable for edge devices with limited resources. The dataset consists of 2,623 images divided into two classes: organic and inorganic. Training was conducted on the Kaggle platform, and model evaluation yielded a precision of 0.93, recall of 0.852, and mAP50 of 0.929. The model was then converted into NCNN format and deployed on the Raspberry Pi 5. The system successfully performed real-time object detection at an average speed of 6.5 FPS and controlled a servo motor based on classification results. Testing showed that the system operates accurately and efficiently, with potential application as an IoT-based smart waste sorting tool in real-world environments.


Keyword: YOLOv8, Raspberry Pi, waste classification, deep learning, NCNN, real-time.

Article Details

Issue

Vol. 10 No. 3 (2025): Kohesi: Jurnal Multidisiplin Saintek

Section

Articles

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Author Biographies

Devano Arayudha Adlim, Universitas Esa Unggul

Teknik Informatika, Universitas Esa Unggul

Iksan Ramadhan, Universitas Esa Unggul

Teknik Informatika, Universitas Esa Unggul

Bambang Irawan, Universitas Esa Unggul

Teknik Informatika, Universitas Esa Unggul

Sawali Wahyu, Universitas Esa Unggul

Teknik Informatika, Universitas Esa Unggul

How to Cite

IMPLEMENTASI OBJECT DETECTION KLASIFIKASI SAMPAH ORGANIK DAN ANORGANIK MENGGUNAKAN RASPBERRY PI DENGAN ALGORITMA YOLO. (2025). Kohesi: Jurnal Sains Dan Teknologi, 10(3), 81-90. https://doi.org/10.2238/hshqzw90

References

[1] Abdillah, H., Naufal Syahbana, A., Ishaq, G., Husain, A., & Agustin, S. (2024). Detektif Sampah : Klasifikasi Jenis Sampah Organik dan Anorganik Menggunakan Metode YOLOv5 Berbasis Website. In Agustus (Vol. 3, Issue 2).

[2] Sri Wisna, J. H., Matulatan, T., Hayaty, N., Informatika, J., Teknik, F., Maritim Raja Ali Haji Jl Politeknik Senggarang, U., & Author, C. (2020). Jurnal Sustainable: Jurnal Hasil Penelitian dan Industri Terapan. 09(01), 8–14

[3] Surbakti, N. M., Angelyca Angelyca, Anita Talia, Cecilia Br Perangin-Angin, Dina Olivia Nainggolan, Nia Devi Friskauly, & Sikap Ruth Br Tumorang. (2024). Penggunaan Bahasa Pemrograman Python dalam Pembelajaran Kalkulus Fungsi Dua Variabel. Algoritma : Jurnal Matematika, Ilmu Pengetahuan Alam, Kebumian Dan Angkasa, 2(3), 98–107. https://doi.org/10.62383/algoritma.v2i3.67

[4] Wijaya Kusuma, A., & Eric Faustin, J. (2023). SISTEM PENGAMANAN PINTU RUMAH DENGAN RASPBERRY PI BERBASIS INTERNET OF THINGS. Jurnal Publikasi Riset Bersama Dosen Dan Mahasiswa, 2(6). https://www.raspberrypi.org/

[5] Ali Hafid, M., & Ade Kurniawan, M. (2024). Deteksi Akun Kaggle Bot Menggunakan Linear Regression. Journal Homepage: Journal of Electrical Engineering and Computer (JEECOM), 6(2). https://doi.org/10.33650/jeecom.v4i2.

[6] Aprisia Bahagia, G., Akbar Teknik Informatika, M., & buana Yogyakarta Gejayan Jembatan Merah Yogyakarta, M. (2024). KLASIFIKASI SAMPAH ORGANIK DAN ANORGANIK MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK (CNN). In Jurnal Mahasiswa Teknik Informatika (Vol. 8, Issue 5)

[7] Cynthia, G., Hasibuan, R., & Dalimunthe, N. F. (n.d.). Penyuluhan Mengenai Pentingnya Pemilahan Sampah Organik dan Non-Organik ke Anak-anak SD Muhammadiyah 02 Medan..

[8] Dwi Prasetya, B., Putri Amalia, E., Devita Juliana, P., & Kumalasari Niswatin, R. (2025). Implementasi Object Detection Berbasis Web untuk Klasifikasi Jenis Sampah Menggunakan YOLOv8 (Vol. 4)..

[9] Haris, M., Pustaka, T., Diponegoro, M. H., Kusumawardani, S., & Hidayah, I. (2021). Tinjauan Pustaka Sistematis: Implementasi Metode Deep Learning pada Prediksi Kinerja Murid (Implementation of Deep Learning Methods in Predicting Student Performance: A Systematic Literature Review). In Jurnal Nasional Teknik Elektro dan Teknologi Informasi | (Vol. 10, Issue 2)..

[10] Hayati, N. J., Singasatia, D., Muttaqin, M. R., Informatika, T., Tinggi, S., & Wastukancana, T. (2023). OBJECT TRACKING MENGGUNAKAN ALGORITMA YOU ONLY LOOK ONCE (YOLO)v8 UNTUK MENGHITUNG KENDARAAN. KOMPUTA : Jurnal Ilmiah Komputer Dan Informatika, 12(2). https://universe.roboflow.com//

[11] Malik, M., Sharma, S., Uddin, M., Chen, C. L., Wu, C. M., Soni, P., & Chaudhary, S. (2022). Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models. Sustainability (Switzerland), 14(12). https://doi.org/10.3390/su14127222F

[12] Ramadhan Hendri, F., & Utaminingrum, F. (2022). Rancang Bangun Sistem Pengklasifikasi Jenis Sampah Organik dan Anorganik menggunakan metode You Only Look Once versi 3 berbasis Raspberry Pi (Vol. 6, Issue 7). http://j-ptiik.ub.ac.id.

[13] Rasyid, M., & Hasibuan, R. (n.d.). MANFAAT DAUR ULANG SAMPAH ORGANIK DAN ANORGANIK UNTUK KESEHATAN LINGKUNGAN..

[14] Reza Fahcruroji, A., Yunita Wijaya, M., Fauziah, I., Sains dan Teknologi, F., Syarif Hidayatullah Jakarta Jl Ir Juanda No, U. H., Ciputat Tim, K., & Tangerang Selatan, K. (n.d.). IMPLEMENTASI ALGORITMA CNN MOBILENET UNTUK KLASIFIKASI GAMBAR SAMPAH DI BANK SAMPAH

Similar Articles

You may also start an advanced similarity search for this article.