Published September 2025, Pg. 32-40

Section: Green energy

UOT: 658.26

DOI: 10.37474/0365-8554/2025-09-32-40

Waste classification based on artificial intelligence

R.R. Shukurov - Baku Higher Oil School

N.R. Allahverdiyeva Cand. in Tech. Sc. - Baku Higher Oil School

In this work the application of artificial intelligence in the classification and management of waste is discussed. In the modern era, the rapid increase in waste generation creates serious environmental and economic problems. Proper waste management is a crucial issue, especially in highly populated countries like China and India. Since existing traditional methods complicate waste classification, the application of deep learning models presents new opportunities in this field.
The article explores how various deep learning models are used for waste classification. Sudha et al. applied the CaffeNet model to classify waste into two categories: biodegradable and non-biodegradable. Other researchers have experimented with different approaches using models such as MobileNet, CNN, ResNet, DenseNet, RecycleNet, and EfficientNet, achieving high classification accuracy. Studies show that the ResNet50, DenseNet, and EfficientNet models provide superior results in waste recognition.
Additionally, network architectures such as AlexNet, VGG, Inception, Inception-ResNet, and Xception have been compared, and their effectiveness in classification has been analyzed. In particular, the use of residual connections in ResNet and Inception-ResNet models enhances the learning process, making it faster and more efficient.
The experiments are based on the Kaggle dataset, where 15,481 images were categorized into 12 different waste categories for training. The test results indicate that the classification accuracy ranges between 87–96 % depending on the model applied. Ultimately, the implementation of artificial intelligence is presented as an effective solution for automating waste classification and addressing environmental challenges.

References:

1. Baiqiang G., & Chi Z. Research on the algorithm of urban waste classification and recycling based on deep learning technology. Journal of Environmental Science and Technology, 2020, 18(3), pp. 45-52.

2. Qiang G., Yuliang S., & Shikai W. Research on deep learning image recognition technology in garbage classification. International Journal of Computer Vision, 2021, 29(2), pp. 112-125.

3. Wang H. Garbage recognition and classification system based on convolutional neural network VGG16. Neural Computing and Applications, 2020, 32(5), pp. 879-890.

4. Shuijing L., Ming Y., & Jie X. Garbage object recognition and classification based on Mask Scoring RNCC. IEEE Transactions on Image Processing, 2020, 15(7), pp. 1324-1335.

5. Sidharth R., Rohit P., Vishagan S., Karthika R., & Ganesan M. Deep learning-based smart garbage classifier for effective waste management // Journal of Artificial Intelligence Research, 2020, 41, pp. 210-225.

6. Vishal V., Harsha C., Deepali G., & Sheifali G. Different convolutional neural network-based models for garbage detection: A review. Pattern Recognition Letters, 2020, 98, pp. 55-68.

7. Ming Z., Xiangzhe L., Wenkang X., Tongxi Z., & Yinbo L. Public-GarbageNet: A deep learning framework for public garbage classification. Expert Systems with Applications, 2020, 127, pp. 189-203.

8. Sudha S., Vidhyalakshmi M., Pavithra K., Sangeetha K., & Swaathi V. An automatic classification method for environment. International Conference on Environmental Science and Technology Proceedings, 2016, pp. 221-230.

9. Stephenn L.R., Melvin K.C., Edwin S., Elmer P.D., & Edwin J.C. Common garbage classification using MobileNet. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2018, pp. 120-128.

10. Shanshan M., & Wei-Ta C. A study of garbage classification with convolutional neural networks. Journal of Machine Learning Research, 2020, 21(4), pp. 78-94.

11. Zhi W., Gao L., & Zhu Z. Garbage classification and recognition based on SqueezeNet. Pattern Analysis and Applications, 2020, 13(2), pp. 58-71.

12. Rismiyati Khadijah, Sukmawati N.E., & Ilman N.S. Xception architecture transfer learning for garbage classification. Neural Networks and Applications, 2020. 24(6), pp. 339-352.

13. Laith A., Jinglan Z., Amjad J.H., Ayad A., Ye D., Omran A., Santamaria J., Mohammed A.F., Muthana A., & Laith F. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions // Journal of Big Data, 2021, 8(53), pp. 1-32.

14. Krizhevsky A., Sutskever I., & Hinton G.E. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012, 25, pp. 1097-1105

15. Zisserman A. Very deep convolutional networks for large-scale image recognition. International Conference on Learning Representations (ICLR), 2015, pp. 1-14.

16. Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., & Rabinovich A. Going deeper with convolutions. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014, pp. 1-9.

17. He K., Zhang X., Ren S., & Sun J. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 770-778.

18. Szegedy C., Ioffe S., & Vanhoucke V. Inception-v4, Inception-ResNet and the impact of residual connections on learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2016, 30(1), pp. 4278-4284.

19. Chollet F. Xception: Deep learning with depthwise separable convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1251-1258.