Performance Evaluation of a Machine Learning for Image-Based Waste Management Using Convolutional Neural Networks

Dandy Cahyo Purnomo; Eka Aprilia Saputri; Ahmad Hasib Satiri; Luluk Khatimah; Hartono

doi:10.33019/jurnalecotipe.v13i2.4593

Authors

Dandy Cahyo Purnomo Mechatronics Engineering Department, Swiss German University
Eka Aprilia Saputri Computerized Accounting, Department of Accounting, Semarang State Polytechnic
Ahmad Hasib Satiri Automation Engineering, Faculty of Technology, University State of Jakarta
Luluk Khatimah Directorate of Planning, Information Systems, and Digital Transformation, Padjadjaran University
Hartono Mechatronics Engineering Department, Swiss German University,

DOI:

https://doi.org/10.33019/jurnalecotipe.v13i2.4593

Keywords:

Convolutional Neural Network, Machine Learning, Smart Waste Management, Transfer Learning, Waste Classification

Abstract

Waste management is still a significant environmental problem, especially in developing countries with high population density. The waste sorting process, which is still mostly done manually, causes low efficiency and consistency of sorting. Previous studies generally focused on binary classification, while research on lightweight CNN architectures for multi-class waste classification, particularly in simulation-based scenarios with per-class performance analysis, remained relatively limited. This study aims to evaluate the performance of the waste image classification model using a lightweight Convolutional Neural Network architecture, namely MobilNetV2 based on the transfer learning approach. The dataset used consists of four categories of waste (metal, plastic, paper, organic) obtained from public datasets. The flow of this research includes the dataset collection stage, preprocessing in the form of resize and rescale, training model and evaluation model using accuracy, confusion matrix, precision, recall, and F1-Score metrics. The test results showed that the model achieved an accuracy of 92.02% with relatively consistent performance in each class. The misclassification that appears is limited and shows a similar pattern between classes. These findings show that MobileNetV2 is able to provide stable classification performance and has the potential to be used as a supporting model in the development of automated waste sorting systems in the future.

Downloads

Download data is not yet available.

References

[1] G. Ahmad et al., “Intelligent Waste Sorting for Urban Sustainability Using Deep Learning,” Scientific Reports 2025 15:1, vol. 15, no. 1, pp. 27078-, Jul. 2025, doi: 10.1038/s41598-025-08461-w.

[2] "SIPSN - National Waste Management Information System." Accessed: Feb. 21, 2026. [Online]. Available: https://portal-sipsn.kemenlh.go.id/

[3] X. R. Huang, S. S. Yang, W. S. Chen, Y. Q. Zhang, C. Te Lee, and L. B. Chen, “An IoT-Based Smart Trash Cans Monitoring System,” in 2021 IEEE 10th Global Conference on Consumer Electronics, GCCE 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 623–624. doi: 10.1109/GCCE53005.2021.9621358.

[4] Md. W. Rahman, R. Islam, A. Hasan, N. I. Bithi, Md. M. Hasan, and M. M. Rahman, “Intelligent waste management system using deep learning with IoT,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 5, pp. 2072–2087, 2022, doi: https://doi.org/10.1016/j.jksuci.2020.08.016.

[5] N. Nnamoko, J. Barrowclough, and J. Procter, “Solid Waste Image Classification Using Deep Convolutional Neural Network,” Infrastructures (Basel)., vol. 7, no. 4, 2022, doi: 10.3390/infrastructures7040047.

[6] T. Zheng, X. Yang, J. Lv, M. Li, S. Wang, and W. Li, “An efficient mobile model for insect image classification in the field pest management,” Engineering Science and Technology, an International Journal, vol. 39, Mar. 2023, doi: 10.1016/J.JESTCH.2023.101335.

[7] G. Ahmad et al., “Intelligent waste sorting for urban sustainability using deep learning,” Sci. Rep., vol. 15, Jul. 2025, doi: 10.1038/s41598-025-08461-w.

[8] “Garbage Classification.” Accessed: Feb. 10, 2026. [Online]. Available: https://www.kaggle.com/datasets/hassnainzaidi/garbage-classification.

[9] “Garbage Classification EcoSort.” Accessed: Feb. 28, 2026. [Online]. Available: https://www.kaggle.com/datasets/itskindastrange/garbage-classification-ecosort?select=garbage_classification.

[10] H. Yuliansyah, R. A. Saputro, I. I. Khoirunnisa, W. N. S. W. Ali, Y. S. R. Nur, and N. F. M. Radzuan, “Plastic bottle defect detection based on convolutional neural network with MobileNetV2 architecture,” Franklin Open, vol. 14, p. 100522, Mar. 2026, doi: 10.1016/j.fraope.2026.100522.

[11] A. R. Hermanto, A. Aziz, and S. Sudianto, "Comparison of MobileNetV2 and RestNet50 Architectures for Classification of Date Types," JUSTIN (Journal of Information Systems and Technology), vol. 12, no. 4, pp. 630–637, Nov. 2024, doi: 10.26418/justin.v12i4.80358.

[12] A. Siti, "Comparison of the Performance of Mobilenetv2 and Resnet50 Architecture in the Classification of Herbal Plants Based on Leaf Image," Jun. 2025.

[13] Y. Gulzar, “Fruit Image Classification Model Based on MobileNetV2 with Deep Transfer Learning Technique,” Sustainability 2023, Vol. 15, Page 1906, vol. 15, no. 3, p. 1906, Jan. 2023, doi: 10.3390/su15031906.

[14] Z. Q. Zhao, P. Zheng, S. T. Xu, and X. Wu, “Object Detection with Deep Learning: A Review,” IEEE Trans. Neural Netw. Learn. Syst., vol. 30, no. 11, pp. 3212–3232, Nov. 2019, doi: 10.1109/TNNLS.2018.2876865.

[15] “Building powerful image classification models using very little data.” Accessed: Feb. 10, 2026. [Online]. Available: https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html.

[16] S. A. Hicks et al., “On evaluation metrics for medical applications of artificial intelligence,” Scientific Reports 2022 12:1, vol. 12, no. 1, pp. 5979-, Apr. 2022, doi: 10.1038/s41598-022-09954-8.