COMPARATİVE ANALYSİS OF THE CLASSİFİCATİON OF RECYCLABLE WASTES

Abstract

The classification of recycling wastes is of great importance both environmentally and economically. Correct classification of recyclable wastes such as packaging wastes increases the efficiency of the recycling process. This classification process can be done according to the raw material type, colour, shape, size and source of the waste. Correct classification of recycling wastes also provides economic benefits by ensuring more efficient use of resources. The traditional waste classification method involves manually sorting waste into different categories. This method requires a lot of labour and is time consuming. The traditional waste classification method is also prone to human error, which can lead to contamination of recyclable materials. Deep neural networks can quickly identify different types of recyclable materials by analysing images of waste materials. Thus, it can increase efficiency and reduce pollution by sorting them appropriately. In this study, an experimental study was carried out on a data set consisting of 6 classes and 2527 images under the name of "Garbage classification". In this study, a comparative analysis was carried out using the Convolutional Neural Network architectures Resnet101, Convnext and Densenet121. As a result of this study, Resnet101 architecture was more successful than other architectures with an accuracy rate of 98.41%.

Keywords

• Classification of waste
• Resnet101
• Densenet121
• deep learning
• artificial intelligence
• CNN

References

1. [1] C. Hark and S. Kiziloluk, ‘Geri Dönüştürülebilir Atiklarin Siniflandirilmasi’, Accessed: May 11, 2023. [Online]. Available: https://www.researchgate.net/publication/366153733
2. [2] E. N. Yildiz et al., ‘Önerilen Derin Öğrenme ve Makine Öğrenmesi Tabanlı Hibrit Model ile Çevresel Atıkların Sınıflandırılması’, Fırat Univ. J. Eng. Sci., vol. 35, no. 1, pp. 353–361, Mar. 2023, doi: 10.35234/FUMBD.1230982.
3. [3] Z. Yang and D. Li, ‘WasNet: A Neural Network-Based Garbage Collection Management System’, IEEE Access, vol. 8, pp. 103984–103993, 2020, doi: 10.1109/ACCESS.2020.2999678.
4. [4] S. Meng and W. T. Chu, ‘A Study of Garbage Classification with Convolutional Neural Networks’, Indo - Taiwan 2nd Int. Conf. Comput. Anal. Networks, Indo-Taiwan ICAN 2020 - Proc., pp. 152–157, Feb. 2020, doi: 10.1109/Indo-TaiwanICAN48429.2020.9181311.
5. [5] Y. Lecun, Y. Bengio, and G. Hinton, ‘Deep learning’, Nat. 2015 5217553, vol. 521, no. 7553, pp. 436–444, May 2015, doi: 10.1038/nature14539.
6. [6] J. Yang, Z. Zeng, K. Wang, H. Zou, and L. Xie, ‘GarbageNet: A Unified Learning Framework for Robust Garbage Classification’, IEEE Trans. Artif. Intell., vol. 2, no. 4, pp. 372–380, Aug. 2021, doi: 10.1109/TAI.2021.3081055.
7. [7] S. Meng, N. Zhang, and Y. Ren, ‘X-DenseNet: Deep Learning for Garbage Classification Based on Visual Images’, J. Phys. Conf. Ser., vol. 1575, no. 1, p. 012139, Jun. 2020, doi: 10.1088/1742-6596/1575/1/012139.
8. [8] A. Makalesi, S. Sürücü, and İ. N. Ecemiş, ‘Garbage Classification Using Pre-Trained Models’, Mayıs 2022 Eur. J. Sci. Technol. Spec. Issue, vol. 36, no. 36, pp. 73–77, 2022, doi: 10.31590/ejosat.1103628.

9. [9] Rismiyati, S. N. Endah, Khadijah, and I. N. Shiddiq, ‘Xception Architecture Transfer Learning for Garbage Classification’, ICICoS 2020 - Proceeding 4th Int. Conf. Informatics Comput. Sci., Nov. 2020, doi: 10.1109/ICICoS51170.2020.9299017.
10. [10] B. Fu, S. Li, J. Wei, Q. Li, Q. Wang, and J. Tu, ‘A Novel Intelligent Garbage Classification System Based on Deep Learning and an Embedded Linux System’, IEEE Access, vol. 9, pp. 131134–131146, 2021, doi: 10.1109/ACCESS.2021.3114496.
11. [11] G. Yang et al., ‘Garbage Classification System with YOLOV5 Based on Image Recognition’, 2021 6th Int. Conf. Signal Image Process. ICSIP 2021, pp. 11–18, 2021, doi: 10.1109/ICSIP52628.2021.9688725.
12. [12] L. Cao and W. Xiang, ‘Application of Convolutional Neural Network Based on Transfer Learning for Garbage Classification’, Proc. 2020 IEEE 5th Inf. Technol. Mechatronics Eng. Conf. ITOEC 2020, pp. 1032–1036, Jun. 2020, doi: 10.1109/ITOEC49072.2020.9141699.
13. [13] ‘Garbage Classification | Kaggle’. https://www.kaggle.com/datasets/asdasdasasdas/garbage-classification (accessed May 21, 2023).
14. [14] G. Çınarer , K. Kılıç and T. Parlar , "A Deep Transfer Learnıng Framework For The Stagıng Of Dıabetıc Retınopathy", Journal of Scientific Reports-A, no. 051, pp. 106-119, Dec. 2022 [15] F. Chollet, ‘Deep Learning with Python, Second Edition’, Deep Learning with Python, 2021. https://www.manning.com/books/deep-learning-with-python-second-edition (accessed May 21, 2023).
15. [16] E. Somuncu and N. A. Atasoy, ‘Realization of character recognition application on text images by convolutional neural network’, J. Fac. Eng. Archit. Gazi Univ., vol. 37, pp. 17–27, 2022, doi: 10.17341/gazimmfd.866552.
16. [17] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, ‘A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects’, IEEE Trans. Neural Networks Learn. Syst., vol. 33, no. 12, pp. 6999–7019, Dec. 2022, doi: 10.1109/TNNLS.2021.3084827.
17. [18] M. Shafiq and Z. Gu, ‘Deep Residual Learning for Image Recognition: A Survey’, Appl. Sci. 2022, Vol. 12, Page 8972, vol. 12, no. 18, p. 8972, Sep. 2022, doi: 10.3390/APP12188972.
18. [19] F. Li et al., ‘Deep learning-based automated detection of glaucomatous optic neuropathy on color fundus photographs’, Graefe’s Arch. Clin. Exp. Ophthalmol., vol. 258, no. 4, pp. 851–867, Apr. 2020, doi: 10.1007/S00417-020-04609-8/FIGURES/4.
19. [20] A. Demir, F. Yilmaz, and O. Kose, ‘Early detection of skin cancer using deep learning architectures: Resnet-101 and inception-v3’, TIPTEKNO 2019 - Tip Teknol. Kongresi, vol. 2019-January, Oct. 2019, doi: 10.1109/TIPTEKNO47231.2019.8972045.
20. [21] Z. Liu, H. Mao, C.-Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, ‘A ConvNet for the 2020s’. pp. 11976–11986, 2022. Accessed: Jul. 20, 2023. [Online]. Available: https://github.com/facebookresearch/ConvNeXt
21. [22] X. Zhai, A. Kolesnikov, N. Houlsby, and L. Beyer, ‘Scaling Vision Transformers’. pp. 12104–12113, 2022.
22. [23] E. Yüzgeç et al., ‘Alzheimer ve Parkinson Hastalıklarının Derin Öğrenme Teknikleri Kullanılarak Sınıflandırılması Classification of Alzheimer’s and Parkinson’s Diseases Using Deep Learning Techniques’, Fırat Üniversitesi Müh. Bil. Derg. Araştırma Makal., vol. 35, no. 2, pp. 473–482, 2023, doi: 10.35234/fumbd.1234638.
23. [24] ‘ConvNeXt’. https://tech.bertelsmann.com/en/blog/articles/convnext (accessed Jul. 26, 2023).
24. [25] G. Huang, Z. Liu, L. van der Maaten, and K. Q. Weinberger, ‘Densely Connected Convolutional Networks’. pp. 4700–4708, 2017. Accessed: Jul. 25, 2023. [Online]. Available: https://github.com/liuzhuang13/DenseNet.
25. [26] N. Radwan, ‘Leveraging Sparse and Dense Features for Reliable State Estimation in Urban Environments’, 2019, doi: 10.6094/UNIFR/149856.
26. [27] M. Chhabra and R. Kumar, ‘A Smart Healthcare System Based on Classifier DenseNet 121 Model to Detect Multiple Diseases’, Lect. Notes Networks Syst., vol. 339, pp. 297–312, 2022, doi: 10.1007/978-981-16-7018-3_23/FIGURES/6.
27. [28] X. Zhang, X. Chen, W. Sun, and X. He, ‘Vehicle Re-Identiication Model Based on Optimized DenseNet121 with Joint Loss’, doi: 10.32604/cmc.2021.016560.