Comparative Optimization of EfficientNetB3, MobileNetV2, and ResNet50 for Waste Classification
DOI:
https://doi.org/10.31294/Keywords:
Deep Learning, Optimization, Waste ClassificationAbstract
Waste management is an important challenge in protecting the environment and public health. Improperly managed waste can cause pollution and hinder the recycling process. This study aims to classify waste based on images by optimizing three deep learning architectures, namely EfficientNetB3, MobileNetV2, and ResNet50, to determine the model with the best performance. The dataset comes from the Kaggle platform, consisting of 4,650 images in six categories: battery, glass, metal, organic, paper, and plastic. The research stages include preprocessing, data augmentation, model development, and evaluation using accuracy, precision, recall, and F1-score metrics. The results show that EfficientNetB3 with the Adam optimizer achieved the best performance with 93% accuracy, followed by ResNet50 with 91%, while MobileNetV2 ranged from 70–73% depending on the optimizer. Variations in optimizers were found to affect model performance, while data augmentation improved generalization capabilities, especially in classes with limited samples. This research confirms the potential of deep learning methods in supporting automatic waste classification systems and provides a basis for the development of technology-based waste management systems in the future.
Downloads
References
Agustin, R., Nurlailli, M., Yuanda, K. P., & Sudamto, B. A. (2025). Deteksi Penyakit Daun Padi Menggunakan Mobilenetv2 : Pendekatan Deep Learning Untuk Meningkatkan Ketahanan Produksi Pangan. Prosiding Semnas Inotek (Seminar Nasional Inovasi Teknologi) 2025, 9, 1294–1303.
Agustina, N. P. D. (2025). Klasifikasi Subtipe Leukemia Limfoblastik Akut (Lla) Pada Citra Mikroskopis Sel Darah Menggunakan Arsitektur Efficientnet-B3 Dengan Dataset Seimbang. Jurnal Locus Penelitian Dan Pengabdian, 4(6), 1–16. Https://Doi.Org/10.58344/Locus.V4i6.4321
Akbar, W. F. (2024). Implementasi Transfer Learning Model Densenet169 Untuk Klasifikasi Citra Jenis Sampah. Jatisi (Jurnal Teknik Informatika Dan Sistem Informasi), 11(4).
Anggara, D., Suarna, N., & Arie Wijaya, Y. (2023). Analisa Perbandingan Performa Optimizer Adam, Sgd, Dan Rmsprop Pada Model H5. Networking Engineering Research Operation, 8(1), 53–64. Https://Doi.Org/10.21107/Nero.V8i1.19226
Aziz, S. I. P., Aini, M. N., Puspitasari, & Prasetya, B. D. (2025). Manajemen Pengelolaan Sampah : Panduan Pengelolaan Sampah Berbasis Digital Upaya Menuju Desa Sidomulyo Yang Bebas Sampah. Seminar Nasional Penelitian Dan Pengabdian Masyarakat -2025, 87–92.
Fathurrahman, A. A., & Akbar, F. (2024). Perancangan Sistem Identifikasi Jenis Sampah Menggunakan Tensorflow Object Detection Dan Transfer Learning. Jurnal Nasional Teknologi Dan Sistem Informasi, 10(1), 64–71. Https://Doi.Org/10.25077/Teknosi.V10i1.2024.64-71
Irfan, D., Rosnelly, R., Wahyuni, M., Samudra, J. T., & Rangga, A. (2022). Comparison Of Sgd, Adadelta, And Adam Optimization In Hydrangea Classification Using Cnn. Journal Of Science And Social Research, 5(2), 244–253. Https://Jurnal.Goretanpena.Com/Index.Php/Jssr/Article/View/789
Jannah, Z., Kurniawan, R., & Anwar, S. (2025). Studi Algoritma Neural Network Dalam Klasifikasi Sentimen Pengguna Shopee: Peningkatan Akurasi Model. Jurnal Informatika Dan Teknik Elektro Terapan, 13(2). Https://Doi.Org/10.23960/Jitet.V13i2.6113
Julia Lingga, L., Yuana, M., Aulia Sari, N., Nur Syahida, H., & Sitorus, C. (2024). Sampah Di Indonesia: Tantangan Dan Solusi Menuju Perubahan Positif. Innovative: Journal Of Social Science Research, 4, 12235–12247.
Khadafi, F., & Zer, P. P. P. A. N. W. F. I. R. H. (2025). Jurnal Jisiilkom ( Jurnal Inovasi Sistem Informasi & Ilmu Komputer ) Optimasi Akurasi Backpropagation Dengan Adaptive Moment Estimation Terhadap Kasus Prediksi Deteksi Penyakit Paru-Paru. 3(1).
Munthe, T. P., & Akbar, M. (2025). Klasifikasi Citra Biji Kopi Temangung Menggunakan Residual Network (Resnet-50). Jurnal Pustaka Data (Pusat Akses Kajian Database, Analisa Teknologi, Dan Arsitektur Komputer), 5(1), 94–102.
Muslihati, M., Sahibu, S., & Taufik, I. (2024). Implementasi Algoritma Convolutional Neural Network Untuk Klasifikasi Jenis Sampah Organik Dan Non Organik. Malcom: Indonesian Journal Of Machine Learning And Computer Science, 4(3), 840–852. Https://Doi.Org/10.57152/Malcom.V4i3.1346
Pieters, L. S. (2025). Development Of Automatic Waste Classification System Using Cnn Based Deep Learning To Support Smart Waste Management Otomatis Menggunakan Deep Learning Berbasis. Jurnal Inovtek Polbeng - Seri Informatika, 10(1), 214–224.
Pranatha, M. D. A., Setiawan, G. H., & Maricar, M. A. (2024). Utilization Of Resnet Architecture And Transfer Learning Method In The Classification Of Faces Of Individuals With Down Syndrome. Journal Of Applied Informatics And Computing, 8(2), 434–442. Https://Doi.Org/10.30871/Jaic.V8i2.8474
Rianto, & Santosa, P. I. (2025). Data Preparation Untuk Machine Learning & Deep Learning. Penerbit Andi. Https://Books.Google.Co.Id/Books?Id=Y5u9eqaaqbaj
Saptadi, N. T. S., Kristiawan, H., Nugroho, A. Y., Rahayu, N., Suwarmiyati, Waseso, B., Intan, I., Khairunnas, Martono, Saputra, P. Y., Sutriawan, Soekarman, Mahatma, K., Yunianto, I., Soleh, O., Sutoyo, M. N., Siswoyo, B., & Aliyah. (2025). Deep Learning Teori, Algoritma, Dan Aplikasi (Issue March).
Sarasuartha Mahajaya, N., Desiana, P., Ayu, W., & Huizen, R. R. (2024). Pengaruh Optimizer Adam, Adamw, Sgd, Dan Lamb Terhadap Model Vision Transformer Pada Klasifikasi Penyakit Paru-Paru. Spinter 2024, 1(2), 818–823. Https://Www.Kaggle.Com/Datasets/Tawsifurrahman/Covid19-Radiography-Database,
Sihabillah, A., Tholib, A., & Basit, I. I. (2025). Optimasi Model Resnet50 Untuk Klasifikasi Sampah. Indexia, 6(2), 102. Https://Doi.Org/10.30587/Indexia.V6i2.9342
Syaifudin, S. (2024). Generative Adversarial Networks (Gan) Dalam Fotografi: Menciptakan Imaji Dari Nol. Specta, 8(2), 169–180.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Sarifah Agustiani, Haryani, Agus Junaidi, Rizky Rachma Putri, Meutia Raissa Emiliana (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
