Hybrid Squeeze-and-Excitation Convolutional Neural Network  with Elastic Weight Consolidation for Longitudinal Learning in High-Accuracy Waste Classification

Raj Gaurang Tiwari; Vinod Kumar Shukla

doi:10.15575/join.v10i2.1628

Authors

Raj Gaurang Tiwari Post Doctoral Research Fellow, School of Engineering Architecture Interior Design, Amity University Dubai, United Arab Emirates and Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India
Vinod Kumar Shukla School of Engineering Architecture Interior Design, Amity University Dubai, United Arab Emirates

DOI:

https://doi.org/10.15575/join.v10i2.1628

Keywords:

Classification, Convolutional Neural Networks, Hybrid Squeezing Techniques, Squeeze-and-Excitation , Waste management practices

Abstract

Waste management has become a global issue. Increased urbanization and per capita consumption have caused unprecedented garbage growth. Sustainability has always been about proper waste management within the ecological framework. Recently, numerous studies have been conducted on automating the identification of waste items. In this study, a Convolutional Neural Network (CNN) model equipped with Squeeze and Excitation (SE) module is proposed based on hybrid squeezing methods for waste item classification. The core aim of this research is to improve the accuracy of classification by highlighting intricate relations between various features encoded within the dataset. Based on extensive tests on a waste dataset, the CNN model with the SE module using hybrid squeezing outperforms all other models. The suggested method's 99.63% accuracy proves its efficacy and robustness. Furthermore, we incorporate Elastic Weight Consolidation (EWC) to enable longitudinal learning, allowing the model to adapt to emerging waste types (e.g., e-waste, biodegradable materials) while retaining prior knowledge with minimal forgetting (<1%). Ablation studies validate the critical role of hybrid squeezing, showing a 1.5% accuracy drop when spatial-wise components are omitted. This revelation affects automated recycling, waste sorting, and intelligent waste management. The proposed technology's accuracy shows its applicability and dependability, advancing sustainable waste management. By automating waste classification with unprecedented precision, the proposed framework can reduce landfill reliance, enhance recycling rates, and inform policy decisions for sustainable urban planning.

References

[1] J. Hsu, J. Wang, and M. Stern, “E-Waste: A Global Problem, Its Impacts, and Solutions,” Journal of Global Information Management, vol. 32, no. 1, 2024, doi: 10.4018/JGIM.337134.

[2] R. Seif, F. Z. Salem, and N. K. Allam, “E-waste recycled materials as efficient catalysts for renewable energy technologies and better environmental sustainability,” Environment, development and sustainability, 2024. doi: 10.1007/s10668-023-02925-7.

[3] C. Bircanoglu, M. Atay, F. Beser, O. Genc, and M. A. Kizrak, “RecycleNet: Intelligent Waste Sorting Using Deep Neural Networks,” 2018 IEEE (SMC) International Conference on Innovations in Intelligent Systems and Applications, INISTA 2018, Sep. 2018, doi: 10.1109/INISTA.2018.8466276.

[4] D. Kannan, S. Khademolqorani, N. Janatyan, and S. Alavi, “Smart waste management 4.0: The transition from a systematic review to an integrated framework,” Waste Management, vol. 174, pp. 1–14, Feb. 2024, doi: 10.1016/j.wasman.2023.08.041.

[5] M. Toğaçar, B. Ergen, and Z. Cömert, “Waste classification using AutoEncoder network with integrated feature selection method in convolutional neural network models,” Measurement (Lond), vol. 153, Mar. 2020, doi: 10.1016/j.measurement.2019.107459.

[6] N. K. Trivedi et al., “Early Detection and Classification of Tomato Leaf Disease Using High-Performance Deep Neural Network,” Sensors 2021, Vol. 21, Page 7987, vol. 21, no. 23, p. 7987, Nov. 2021, doi: 10.3390/S21237987.

[7] M. K. Chegeni, A. Rashno, and S. Fadaei, “Convolution-layer parameters optimization in Convolutional Neural Networks,” Knowl Based Syst, vol. 261, 2023, doi: 10.1016/j.knosys.2022.110210.

[8] A. D. Kulkarni, “Convolution Neural Networks for Phishing Detection,” International Journal of Advanced Computer Science and Applications, vol. 14, no. 4, 2023, doi: 10.14569/IJACSA.2023.0140403.

[9] M. Mudemfu and F. Wayne, “Intelligent Solid Waste Classification System Using Deep Learning,” MS thesis. Purdue University, Jul. 2023, doi: 10.25394/PGS.23786484.V1.

[10] C. Wang, J. Qin, C. Qu, X. Ran, C. Liu, and B. Chen, “A smart municipal waste management system based on deep-learning and Internet of Things,” Waste Management, vol. 135, pp. 20–29, Nov. 2021, doi: 10.1016/J.WASMAN.2021.08.028.

[11] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,” IEEE Trans Neural Netw Learn Syst, pp. 1–21, Jun. 2021, doi: 10.1109/TNNLS.2021.3084827.

[12] O. Russakovsky et al., “ImageNet Large Scale Visual Recognition Challenge,” Int J Comput Vis, vol. 115, no. 3, 2015, doi: 10.1007/s11263-015-0816-y.

[13] K. Brindhadevi, D. Barceló, N. T. Lan Chi, and E. R. Rene, “E-waste management, treatment options and the impact of heavy metal extraction from e-waste on human health: Scenario in Vietnam and other countries,” Environ Res, vol. 217, 2023, doi: 10.1016/j.envres.2022.114926.

[14] J. Hu, L. Shen, and G. Sun, “Squeeze-and-Excitation Networks,” Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 7132–7141, Dec. 2018, doi: 10.1109/CVPR.2018.00745.

[15] J. Ji, B. Zhong, Q. Wu, and K. K. Ma, “A Channel-Wise Multi-Scale Network for Single Image Super-Resolution,” IEEE Signal Process Lett, vol. 31, 2024, doi: 10.1109/LSP.2024.3372781.

[16] B. T. Nguyen, S. T. Nguyen, and A. H. Vo, “Channel and spatial attention mechanism for fashion image captioning,” International Journal of Electrical and Computer Engineering, vol. 13, no. 5, 2023, doi: 10.11591/ijece.v13i5.pp5833-5842.

[17] A. G. Roy, N. Navab, and C. Wachinger, “Recalibrating Fully Convolutional Networks With Spatial and Channel ‘Squeeze and Excitation’ Blocks,” IEEE Trans Med Imaging, vol. 38, no. 2, 2019, doi: 10.1109/TMI.2018.2867261.

[18] Y. Pan and P. Zhan, “The Impact of Sample Attrition on Longitudinal Learning Diagnosis: A Prolog,” Front Psychol, vol. 11, 2020, doi: 10.3389/fpsyg.2020.01051.

[19] S. Mondesire and R. P. Wiegand, “Mitigating Catastrophic Forgetting with Complementary Layered Learning,” Electronics (Switzerland), vol. 12, no. 3, 2023, doi: 10.3390/electronics12030706.

[20] J. Kirkpatrick et al., “Overcoming catastrophic forgetting in neural networks,” Proc Natl Acad Sci U S A, vol. 114, no. 13, 2017, doi: 10.1073/pnas.1611835114.

[21] Y. Zhou, X. Tian, C. Zhang, Y. Zhao, and T. Li, “Elastic weight consolidation-based adaptive neural networks for dynamic building energy load prediction modeling,” Energy Build, vol. 265, 2022, doi: 10.1016/j.enbuild.2022.112098.

[22] Y. Zhang, Z. Lu, F. Zhang, H. Wang, and S. Li, “Machine Unlearning by Reversing the Continual Learning,” Applied Sciences (Switzerland), vol. 13, no. 16, 2023, doi: 10.3390/app13169341.

[23] “Garbage classification.” Accessed: Oct. 30, 2023. [Online]. Available: https://www.kaggle.com/datasets/yashkangale20/garbage-classification

[24] C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J Big Data, vol. 6, no. 1, pp. 1–48, Dec. 2019, doi: 10.1186/S40537-019-0197-0/FIGURES/33.

[25] P. P. Malla, S. Sahu, and A. I. Alutaibi, “Classification of Tumor in Brain MR Images Using Deep Convolutional Neural Network and Global Average Pooling,” Processes, vol. 11, no. 3, 2023, doi: 10.3390/pr11030679.

[26] R. Azadnia, M. M. Al-Amidi, H. Mohammadi, M. A. Cifci, A. Daryab, and E. Cavallo, “An AI Based Approach for Medicinal Plant Identification Using Deep CNN Based on Global Average Pooling,” Agronomy, vol. 12, no. 11, 2022, doi: 10.3390/agronomy12112723.

[27] Y. Dogan, “A New Global Pooling Method for Deep Neural Networks: Global Average of Top-K Max- Pooling,” Traitement du Signal, vol. 40, no. 2, 2023, doi: 10.18280/ts.400216.