MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting

doi:10.1007/s11783-023-1677-1

Front. Environ. Sci. Eng.

2023, Vol. 17

Issue (6) : 77 https://doi.org/10.1007/s11783-023-1677-1

RESEARCH ARTICLE

MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting

Kunsen Lin¹, Youcai Zhao^1,², Lina Wang^3,⁴(

), Wenjie Shi¹, Feifei Cui⁵, Tao Zhou^1,²

¹. The State Key Laboratory of Pollution Control and Resource Reuse, College of Environmental Science and Engineering, Tongji University, Shanghai 200092, China
². Shanghai Institute of Pollution Control and Ecological Security, Shanghai 200092, China
³. Shanghai Key Laboratory of Atmospheric Particle Pollution and Prevention (LAP3), Department of Environmental Science and Engineering, Fudan University, Shanghai 200433, China
⁴. Institute of Eco-Chongming (IEC), Shanghai 202150, China
⁵. Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China, Chengdu 610054, China

Download: PDF(7471 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

● MSWNet was proposed to classify municipal solid waste.

● Transfer learning could promote the performance of MSWNet.

● Cyclical learning rate was adopted to quickly tune hyperparameters.

An intelligent and efficient methodology is needed owning to the continuous increase of global municipal solid waste (MSW). This is because the common methods of manual and semi-mechanical screenings not only consume large amount of manpower and material resources but also accelerate virus community transmission. As the categories of MSW are diverse considering their compositions, chemical reactions, and processing procedures, etc., resulting in low efficiencies in MSW sorting using the traditional methods. Deep machine learning can help MSW sorting becoming into a smarter and more efficient mode. This study for the first time applied MSWNet in MSW sorting, a ResNet-50 with transfer learning. The method of cyclical learning rate was taken to avoid blind finding, and tests were repeated until accidentally encountering a good value. Measures of visualization were also considered to make the MSWNet model more transparent and accountable. Results showed transfer learning enhanced the efficiency of training time (from 741 s to 598.5 s), and improved the accuracy of recognition performance (from 88.50% to 93.50%); MSWNet showed a better performance in MSW classsification in terms of sensitivity (93.50%), precision (93.40%), F1-score (93.40%), accuracy (93.50%) and AUC (92.00%). The findings of this study can be taken as a reference for building the model MSW classification by deep learning, quantifying a suitable learning rate, and changing the data from high dimensions to two dimensions.

Keywords Municipal solid waste sorting Deep residual network Transfer learning Cyclic learning rate Visualization

Corresponding Author(s): Lina Wang

Issue Date: 03 January 2023

Cite this article:

Kunsen Lin,Youcai Zhao,Lina Wang, et al. MSWNet: A visual deep machine learning method adopting transfer learning based upon ResNet 50 for municipal solid waste sorting[J]. Front. Environ. Sci. Eng., 2023, 17(6): 77.

URL:

https://academic.hep.com.cn/fese/EN/10.1007/s11783-023-1677-1
https://academic.hep.com.cn/fese/EN/Y2023/V17/I6/77

Fig.1 Structure of ResNet 50.

Fig.2 Example of transfer learning employed in MSW classification.

Fig.3 Research flow chart for MSWNet.

Fig.4 Learning rate vs. loss in ResNet 50-ImageNet based on ImageNet.

Fig.5 Example of feature maps obtained from MSWNet model: (a) Input image; (b) Convolutional layer in stage 0; (c) Batch normalization layer in stage 0; (d) ReLu layer in stage 0; (e) Max pooling layer in stage 0; (f) Stage 1; (g) Stage 2; (h) Stage 3; (i) Stage 4; (j) Fully connected layer; (k) Output result.

Fig.6 Distribution of feature maps exacted from the last layer of MSWNet: (a) PCA; (b) t-SNE.

Fig.7 Examples in which MSWNet failed to MSW classification.

Tab.1 Performance evaluation of ResNet 50 and MWSNet model on MSW test dataset.

Fig.8 Confusion matrix and ROC from ResNet 50 without TL and MSWNet measured on the waste test dataset: (a) Confusion matrix from ResNet 50 without TL; (b) Confusion matrix from MSWNet (ResNet-50 with TL); (c) ROC from ResNet 50 without TL; (d) ROC from MSWNet.

1	M Z Alom, T M Taha, C Yakopcic, S Westberg, P Sidike, M S Nasrin, M Hasan, B C Van Essen. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics (Basel), 8(3): 292–358 https://doi.org/10.3390/electronics8030292
2	Y Ding, J Zhao, J W Liu, J Zhou, L Cheng, J Zhao, Z Shao, Ç Iris, B Pan, X Li, Z T Hu. (2021). A review of China’s municipal solid waste (MSW) and comparison with international regions: Management and technologies in treatment and resource utilization. Journal of Cleaner Production, 293: 126144 https://doi.org/10.1016/j.jclepro.2021.126144
3	B Fu, S Li, J Wei, Q Li, Q Wang, J Tu. (2021). A novel intelligent garbage classification system based on deep learning and an embedded linux system. IEEE Access: Practical Innovations, Open Solutions, 9: 131134–131146 https://doi.org/10.1109/ACCESS.2021.3114496
4	S P Gundupalli, S Hait, A Thakur. (2017). A review on automated sorting of source-separated municipal solid waste for recycling. Waste Management (New York, N.Y.), 60: 56–74 https://doi.org/10.1016/j.wasman.2016.09.015
5	Y Guo, Z Zhu, Y Zhao, T Zhou, B Lan, L Song. (2021). Simultaneous annihilation of microorganisms and volatile organic compounds from municipal solid waste storage rooms with slightly acidic electrolyzed water. Journal of Environmental Management, 297: 113414 https://doi.org/10.1016/j.jenvman.2021.113414
6	K He, X Zhang, S Ren, J Sun. (2015). Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. Santiago, Chile: IEEE, 1026–1034
7	K He, X Zhang, S Ren, J Sun. (2016). Deep residual learning for image recognition. Las Vegas, NV, USA: CVPR, 770–778 https://doi.org/10.1109/CVPR.2016.90
8	Y Huang, J Chen, Q Duan, Y Feng, R Luo, W Wang, F Liu, S Bi, J Lee. (2022). A fast antibiotic detection method for simplified pretreatment through spectra-based machine learning. Frontiers of Environmental Science & Engieering, 16(3): 38 https://doi.org/10.1007/s11783-021-1472-9
9	S Kaza, L Yao, P Bhada-Tata, F Van Woerden. (2018). What a waste 2.0: A global snapshot of solid waste management to 2050. Washington DC: World Bank Publications, 1–295
10	C Kwan, B Chou, J Yang, A Rangamani, T Tran, J Zhang, R Etienne-Cummings. (2019). Deep learning-based target tracking and classification for low quality videos using coded aperture cameras. Sensors (Basel), 19(17): 3702–3734 https://doi.org/10.3390/s19173702
11	N S Leslie. (2017). Cyclical learning rates for training neural networks. Santa Rosa, CA, USA: IEEE, 464–472
12	J Li, L Pan, M Suvarna, X Wang. (2021a). Machine learning aided supercritical water gasification for H2-rich syngas production with process optimization and catalyst screening. Chemical Engineering Journal, 426: 131285 https://doi.org/10.1016/j.cej.2021.131285
13	J Li, M Suvarna, L Li, L Pan, J Pérez-Ramírez, Y S Ok, X Wang. (2022a). A review of computational modeling techniques for wet waste valorization: Research trends and future perspectives. Journal of Cleaner Production, 367: 133025 https://doi.org/10.1016/j.jclepro.2022.133025
14	J Li, L Zhang, C Li, H Tian, J Ning, J Zhang, Y W Tong, X Wang. (2022b). Data-driven based in-depth interpretation and inverse design of anaerobic digestion for CH4-rich biogas production. ACS ES&T Engineering, 2(4): 642–652
15	Z Li, F Liu, W Yang, S Peng, J Zhou. (2021b). A survey of convolutional neural networks: analysis, applications, and prospects. IEEE Transactions on Neural Networks and Learning Systems, 2(1): 1–21 https://doi.org/10.1109/TNNLS.2021.3084827
16	Y Liang, Q Song, N Wu, J Li, Y Zhong, W Zeng. (2021). Repercussions of COVID-19 pandemic on solid waste generation and management strategies. Frontiers of Environmental Science & Engieering, 15(6): 115 https://doi.org/10.1007/s11783-021-1407-5
17	K Lin, Y Zhao, X Gao, M Zhang, C Zhao, L Peng, Q Zhang, T Zhou. (2022a). Applying a deep residual network coupling with transfer learning for recyclable waste sorting. Environmental Science and Pollution Research International, 10(2): 1–15 https://doi.org/10.1007/s11356-022-22167-w
18	K Lin, Y Zhao, J H Kuo. (2022c). Deep learning hybrid predictions for the amount of municipal solid waste: a case study in Shanghai. Chemosphere, 307(4): 136119 https://doi.org/10.1016/j.chemosphere.2022.136119
19	K Lin, Y Zhao, J H Kuo, H Deng, F Cui, Z Zhang, M Zhang, C Zhao, X Gao, T Zhou, T Wang. (2022b). Toward smarter management and recovery of municipal solid waste: a critical review on deep learning approaches. Journal of Cleaner Production, 346: 130943 https://doi.org/10.1016/j.jclepro.2022.130943
20	K Lin, Y Zhao, L Tian, C Zhao, M Zhang, T Zhou. (2021). Estimation of municipal solid waste amount based on one-dimension convolutional neural network and long short-term memory with attention mechanism model: a case study of Shanghai. Science of the Total Environment, 791: 148088 https://doi.org/10.1016/j.scitotenv.2021.148088
21	J Liu, P Yue, N Zang, C Lu, X Chen. (2021). Removal of odors and VOCs in municipal solid waste comprehensive treatment plants using a novel three-stage integrated biofilter: Performance and bioaerosol emissions. Frontiers of Environmental Science & Engieering, 15(3): 48 https://doi.org/10.1007/s11783-021-1421-7
22	H Long, Y Liao, C Cui, M Liu, Z Liu, L Li, W Hu, D Yan. (2022). Assessment of popular techniques for co-processing municipal solid waste in Chinese cement kilns. Frontiers of Environmental Science & Engieering, 16(4): 51 https://doi.org/10.1007/s11783-021-1485-4
23	J W Lu, S Zhang, J Hai, M Lei. (2017). Status and perspectives of municipal solid waste incineration in China: a comparison with developed regions. Waste Management (New York, N.Y.), 69: 170–186 https://doi.org/10.1016/j.wasman.2017.04.014
24	W Lu, W Huo, H Gulina, C Pan. (2022). Development of machine learning multi-city model for municipal solid waste generation prediction. Frontiers of Environmental Science & Engineering, 16(9): 119 https://doi.org/10.1007/s11783-022-1551-6
25	S H Miraei Ashtiani, S Javanmardi, M Jahanbanifard, A Martynenko, F J Verbeek. (2021). Detection of mulberry ripeness stages using deep learning models. IEEE Access: Practical Innovations, Open Solutions, 9: 100380–100394 https://doi.org/10.1109/ACCESS.2021.3096550
26	Y Nie, Y Wu, J Zhao, J Zhao, X Chen, T Maraseni, G Qian. (2018). Is the finer the better for municipal solid waste (MSW) classification in view of recyclable constituents? A comprehensive social, economic and environmental analysis. Waste Management (New York, N.Y.), 79: 472–480 https://doi.org/10.1016/j.wasman.2018.08.016
27	K Özkan, S Ergin, S Isik, I Isikli. (2015). A new classification scheme of plastic wastes based upon recycling labels. Waste Management (New York, N.Y.), 35: 29–35 https://doi.org/10.1016/j.wasman.2014.09.030
28	S Serranti, A Gargiulo, G Bonifazi. (2012). Classification of polyolefins from building and construction waste using NIR hyperspectral imaging system. Resources, Conservation and Recycling, 61: 52–58 https://doi.org/10.1016/j.resconrec.2012.01.007
29	H C Shin, H R Roth, M Gao, L Lu, Z Xu, I Nogues, J Yao, D Mollura, R M Summers. (2016). Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Transactions on Medical Imaging, 35(5): 1285–1298 https://doi.org/10.1109/TMI.2016.2528162
30	Q Tong, G Liang, J Bi. (2022). Calibrating the adaptive learning rate to improve convergence of ADAM. Neurocomputing, 481: 333–356 https://doi.org/10.1016/j.neucom.2022.01.014
31	M D Vaverková, E K Paleologos, A Dominijanni, E Koda, C S Tang, W Małgorzata, Q Li, N Guarena, A M O Mohamed, C S Vieira. et al.. (2021). Municipal solid waste management under Covid-19: challenges and recommendations. Environmental Geotechnics, 8(3): 217–232 https://doi.org/10.1680/jenge.20.00082
32	C Wang, Z Chu, W Gu. (2021a). Participate or not: impact of information intervention on residents’ willingness of sorting municipal solid waste. Journal of Cleaner Production, 318: 128591 https://doi.org/10.1016/j.jclepro.2021.128591
33	Y Wang, Y Shi, J Zhou, J Zhao, T Maraseni, G Qian. (2021b). Implementation effect of municipal solid waste mandatory sorting policy in Shanghai. Journal of Environmental Management, 298: 113512 https://doi.org/10.1016/j.jenvman.2021.113512
34	J Wei, H Li, J Liu. (2022). Curbing dioxin emissions from municipal solid waste incineration: China’s action and global share. Journal of Hazardous Materials, 435: 129076 https://doi.org/10.1016/j.jhazmat.2022.129076
35	X Wen, Q Luo, H Hu, N Wang, Y Chen, J Jin, Y Hao, G Xu, F Li, W Fang. (2014). Comparison research on waste classification between China and the EU, Japan, and the USA. Journal of Material Cycles and Waste Management, 16(2): 321–334 https://doi.org/10.1007/s10163-013-0190-1
36	J Wu, X Zhou, X Yan, F Wang, X Bai, Y Li, Y Wang, J Zhou. (2016). Effects and improvement suggestions of green account system for waste classification and reduction in Shanghai. Journal of Shanghai University (Natural Science Edition), 22(2): 197–202
37	B Yan, R Liang, B Li, J Tao, G Chen, Z Cheng, Z Zhu, X Li. (2021). Fast identification and characterization of residual wastes via laser-induced breakdown spectroscopy and machine learning. Resources, Conservation and Recycling, 174: 105851 https://doi.org/10.1016/j.resconrec.2021.105851
38	M D Zeiler, R Fergus. (2014). Visual and understanding convolutional networks. In: Proceedings of the 13th European Conference on Computer Vision (ECCV 2014), Zurich, Switzerland. Heidelberg: Springer, 8689: 818–883 https://doi.org/10.1007/978-3-319-10590-1_53
39	M D Zeiler, G W Taylor, R Fergus. (2011). Adaptive deconvolutional networks for mid and high level feature learning. Barcelona, Spain: IEEE, 2018–2025
40	J Zhang, Z Zhang, J Zhang, G Fan, D Wu. (2021). A quantitative study on the benefit of various waste classifications. Advances in Civil Engineering, 2021: 1–15 https://doi.org/10.1155/2021/6660927

[1]

FSE-22119-of-LKS_suppl_1

Download

[1]

Wenwei Yang, Yun Zhu, Carey Jang, Shicheng Long, Che-Jen Lin, Bin Yu, Zachariah Adelman, Shuxiao Wang, Jia Xing, Long Wang, Jiabin Li. Development and case study of a new-generation model-VAT for analyzing the boundary conditions influence on atmospheric mercury simulation[J]. Front. Environ. Sci. Eng., 2018, 12(1): 13-.

Viewed

Full text

Abstract

Cited

Shared

Discussed