Future Waste Management Optimization: Kepler Algorithm and Motif-Based Heterogeneous Graph Attention Network Integrated with Deep Learning

Paper ID: EIJTEM_2019_6_3_27-33

Author's Name: Dileep Kumar Ghattamaneni

Volume: 6

Issue: 3

Year: 2019

Page No: 27-33

Abstract:

Municipal Solid Waste (MSW) management is an essential challenge in current urban areas due to fast-paced urbanization, population growth, and high consumption. MSW generation prediction is required for effective waste collection, resource handling, and environmentally friendly environmental control. This study proposes a novel deep-learning model for municipal solid waste prediction by combining sophisticated preprocessing, feature extraction, classification, and optimization. Raw waste data is normalized beforehand by Min-Max Scaler Normalization to gain standardized data scaling. Feature extraction is carried out by the Scale-aware Modulation Meet Transformer (SMTr) that extracts both local and global features at several scales, promoting the model to better understand temporal and spatial patterns in the data. The extracted features are subsequently input into a Gates-Controlled Deep Unfolding Network (GCDUNet) to make accurate classification and prediction of waste quantities. For enhanced model performance and convergence, the classification is optimized using the Pied Kingfisher Optimizer (PKO), an evolutionary algorithm inspired by kingfisher hunting patterns. Experimental results demonstrate a significant boost in prediction accuracy, a Mean Absolute Percentage Error (MAPE) of 1.70, a Root Mean Square Error (RMSE) of 1.20, and an R2 score of 0.98, with high predictive precision and good generalization over various waste generation patterns.

Keywords: Deep Learning, Feature Extraction, Municipal Solid Waste, Pied Kingfisher Optimizer, Time-series analysis

References:

1. Shatnawi, R.S., 2018. Solid waste management: classification and public perception on management options at Applied
Science University. Jordan journal of civil engineering, 12(3).
2. Nie, Y., Wu, Y., Zhao, J., Zhao, J., Chen, X., Maraseni, T. and Qian, G., 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, 79, pp.472-480.
3. Gundupalli, S.P., Hait, S. and Thakur, A., 2017. Multi-material classification of dry recyclables from municipal solid
waste based on thermal imaging. Waste Management, 70, pp.13-21.
4. Tisserant, Alexandre, Stefan Pauliuk, Stefano Merciai, Jannick Schmidt, Jacob Fry, Richard Wood, and Arnold Tukker.
"Solid waste and the circular economy: a global analysis of waste treatment and waste footprints." Journal of Industrial
Ecology 21, no. 3 (2017): 628-640.
5. You, H., Ma, Z., Tang, Y., Wang, Y., Yan, J., Ni, M., Cen, K. and Huang, Q., 2017. Comparison of ANN (MLP), ANFIS,
SVM, and RF models for the online classification of heating value of burning municipal solid waste in circulating
fluidized bed incinerators. Waste management, 68, pp.186-197.
6. Ramalingam, B., Lakshmanan, A.K., Ilyas, M., Le, A.V. and Elara, M.R., 2018. Cascaded machine-learning technique for
debris classification in floor-cleaning robot application. Applied Sciences, 8(12), p.2649.
7. Younes, M.K., Nopiah, Z.M., Basri, N.A., Basri, H., Abushammala, M.F. and Younes, M.Y., 2016. Landfill area estimation
based on integrated waste disposal options and solid waste forecasting using modified ANFIS model. Waste
Management, 55, pp.3-11.
8. Pandey, D.S., Das, S., Pan, I., Leahy, J.J. and Kwapinski, W., 2016. Artificial neural network based modelling approach
for municipal solid waste gasification in a fluidized bed reactor. Waste management, 58, pp.202-213.
9. Campisano, A., Creaco, E. and Modica, C., 2016. Application of real-time control techniques to reduce water volume
discharges from quality-oriented CSO devices. Journal of Environmental Engineering, 142(1), p.04015049.
10. Nabholz, B., Lanfear, R. and Fuchs, J., 2016. Body mass‐corrected molecular rate for bird mitochondrial
DNA. Molecular ecology, 25(18), pp.4438-4449.
11. Li, X., Peng, L., Yao, X., Cui, S., Hu, Y., You, C. and Chi, T., 2017. Long short-term memory neural network for air
pollutant concentration predictions: Method development and evaluation. Environmental pollution, 231, pp.997-1004.

View PDF