Waste Image Classification Using Fine-Tuned MobileNetV2 under Imbalanced Data Conditions
DOI:
https://doi.org/10.30871/jaic.v10i2.12218Keywords:
Deep Learning, Fine-Tuning, Imbalanced Data, MobileNetV2, Waste ClassificationAbstract
Ineffective waste management is a critical global environmental issue where manual sorting is often inefficient and prone to human error. Deep Learning technology, specifically Convolutional Neural Networks (CNN), offers automated solutions to improve classification performance. This study aims to optimize waste image classification by evaluating the effectiveness of the Fine-Tuned MobileNetV2 architecture, specifically addressing the challenges of imbalanced data distribution where recyclable items significantly outnumber residuals. Experiments compared six training scenarios including Basic CNN, CNN with Class Weight, and Transfer Learning using VGG16 and MobileNetV2 with frozen and fine-tuning strategies. Evaluation metrics included Accuracy, Precision, Recall, F1-Score, and Confusion Matrix analysis. Results indicated that the Basic CNN model struggled with the minority class, yielding a low F1-Score of 0.49. Conversely, the optimized MobileNetV2 Fine-Tuned model achieved superior performance, recording a testing accuracy of 96.49% and an F1-Score of 0.92. It is concluded that the fine-tuning strategy on MobileNetV2 is the most effective approach to mitigate data imbalance, providing an optimal balance between high sensitivity toward the minority class and computational efficiency for real-time implementation.
Downloads
References
[1] L. J. Lingga, M. Yuana, N. A. Sari, H. N. Syahida, and C. S. Shahron, “Sampah di Indonesia : Tantangan dan Solusi Menuju Perubahan Positif,” vol. 4, pp. 12235–12247, 2024.
[2] H. Zhang, H. Cao, Y. Zhou, C. Gu, and D. Li, “Urban Climate Hybrid deep learning model for accurate classification of solid waste in the society,” Urban Clim., vol. 49, no. February, p. 101485, 2023, doi: 10.1016/j.uclim.2023.101485.
[3] A. T. Setiawan, “Identifikasi Jenis Sampah Secara Otomatis Menggunakan Metode Convolutional Neural Network ( CNN ),” pp. 345–357.
[4] Z. Li, F. Liu, W. Yang, S. Peng, J. Zhou, and S. Member, “A Survey of Convolutional Neural Networks : Analysis , Applications , and Prospects,” IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 12, pp. 6999–7019, 2022, doi: 10.1109/TNNLS.2021.3084827.
[5] F. Ahamed, M. Naznine, and J. Karim, “Knowledge-Based Systems An automated waste classification system using deep learning techniques : Toward efficient waste recycling and environmental sustainability,” Knowledge-Based Syst., vol. 310, no. May 2024, p. 113028, 2025, doi: 10.1016/j.knosys.2025.113028.
[6] E. T. Y. M. Koklu, “A comparative analysis of machine learning algorithms for waste classification : inceptionv3 and chi ‑ square features,” Int. J. Environ. Sci. Technol., vol. 22, no. 10, pp. 9415–9428, 2025, doi: 10.1007/s13762-024-06233-z.
[7] S. Poudel, “Classification of Waste Materials using CNN Based on Transfer Learning,” pp. 29–33, 2022, doi: 10.1145/3574318.3574345.
[8] T. Soni, “MobileNet-Based Garbage Classification : Enhancing Recycling with Machine Learning,” 2024 Int. Conf. Intell. Comput. Emerg. Commun. Technol., pp. 1–4, 2024, doi: 10.1109/ICEC59683.2024.10837152.
[9] S. Sahibu and I. Taufik, “Implementation of the Convolutional Neural Network Algorithm for Classifying Types of Organic and Non-Organic Waste Implementasi Algoritma Convolutional Neural Network untuk Klasifikasi Jenis Sampah Organik dan Non Organik,” vol. 4, no. July, pp. 840–852, 2024.
[10] T. Sulistyowati, F. Al Zami, and R. A. Pramunendar, “VGG16 Deep Learning Architecture Using Imbalance Data Methods For The Detection Of Apple Leaf Diseases,” vol. 11, no. 1, pp. 41–53, 2023.
[11] A. Irshad, A. S. Almalaise, Y. B. Abushark, F. Alsolami, A. Almalawi, and A. Marish, “Chemosphere Recycling waste classification using emperor penguin optimizer with deep learning model for bioenergy production,” Chemosphere, vol. 307, no. P3, p. 136044, 2022, doi: 10.1016/j.chemosphere.2022.136044.
[12] E. Oktayessofa, C. A. Sari, E. H. Rachmawanto, and N. M. Yaacob, “Classification Of Organic And Non-Organic Waste With CNN-,” vol. 5, no. 4, pp. 1173–1180, 2024.
[13] U. Kumar, S. Simaiya, S. Dalal, M. Radulescu, and D. Balsalobre-lorente, “Intelligent waste sorting for sustainable environment : A hybrid deep learning and transfer learning model,” Gondwana Res., no. xxxx, 2024, doi: 10.1016/j.gr.2024.07.014.
[14] P. N. Dacipta and R. E. Putra, “Sistem Klasifikasi Limbah Menggunakan Metode Convolutional Neural Network ( CNN ) Pada Web Service Berbasis Framework Flask,” vol. 03, pp. 394–402, 2022.
[15] A. S. Ouedraogo, A. Kumar, and N. Wang, “Landfill Waste Segregation Using Transfer and Ensemble Machine Learning : A Convolutional Neural Network Approach,” 2023.
[16] N. Li and Y. Chen, “Urban Climate Municipal solid waste classification and real-time detection using deep learning methods,” Urban Clim., vol. 49, no. February, p. 101462, 2023, doi: 10.1016/j.uclim.2023.101462.
[17] T. H. Yan, S. Nazrah, M. Azam, Z. Sani, and A. Azizan, “Accuracy study of image classification for reverse vending machine waste segregation using convolutional neural network,” vol. 14, no. 1, pp. 366–374, 2024, doi: 10.11591/ijece.v14i1.pp366-374.
[18] R. A. Kumala, C. A. Sari, and E. H. Rachmawanto, “A Comparison of MobileNetV2 and VGG16 Architectures with Transfer Learning for Multi-Class Image-Based Waste Classification,” vol. 9, no. 4, pp. 1610–1624, 2025.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Rahmadini Cahya Demora, Muljono Muljono
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
