Comparative performance analysis of support vector regression and artificial neural network for prediction of municipal solid waste generation

Abstract

The evolution of machine learning (ML) algorithms provides researchers and engineers with state-of-the-art tools to dynamically model complex relationships. The design and operation of municipal solid waste (MSW) management systems require accurate estimation of generation rates. In this study, we applied rapid, non-linear and non-parametric data driven ML algorithms independently, multi-layer perceptron artificial neural network (MLP-ANN) and support vector regression (SVR) models to predict annual MSW generation rates in Bahrain. Models were trained and tested with MSW generation data for period of 1997–2019. The population, gross domestic product, annual tourist numbers, annual electricity consumption and total annual CO2 emissions were selected as explanatory variables and incorporated into developed models. The zero score normalization (ZSN) and minimum maximum normalization (MMN) methods were utilized to improve the quality of data and subsequently enhances the performance of ML algorithms. Statistical metrics were employed to discriminate performance of MLP-ANN and SVR models. The linear, polynomial, radial basis function (RBF) and sigmoid kernel functions were investigated to find the optimal SVR model. Results showed that RBF-SVR model with R2 value of 0.97% and 4.82% and absolute forecasting error (AFE) for the period of 2008 and 2019 exhibits superior prediction and robustness in comparison to MLP-ANN. The efficacy of MLP-ANN model was also reasonably successful with R2 value of 0.94. It was shown that MMN pre-processing generated optimal MLP-ANN model while ZSN pre-processing produced optimal RBF-SVR model. This work also highlights the importance of application of ML modelling approaches to plan and implement their roadmap for waste management systems by policymakers.

Parameter Identification of 3D Elastic-Plastic Model for Tunnel Engineering Based on Improved Genetic Algorithm

“…The burial depth of grade II-III surrounding rock tunnel is 20-220 m, the thickness of shotcrete is 2-6 cm, the length of bolt is 1.5-2 m, and the dilatation angle is 10 °-18 °. The horizontal side pressure coefficient is taken as 0.5∼1.5, the bolt spacing is taken as 1 m, the bolt diameter is taken as 18∼22 mm, the surrounding rocks of grades II-III are divided into 11 levels, and the surrounding rocks of grades IV-V are divided into 26 levels; according to the uniform experimental design method, 37 numerical test schemes are combined [15,16].…”

The use of a recurrent neural network model with separated time-series and lagged daily inputs for waste disposal rates modeling during COVID-19

“… Kontokosta et al (2018) , on the other hand, concluded that climatic variables were vital features in their ANN waste prediction models at New York. Recently, Jassim et al (2021) used various environmental related parameters such as annual tourist numbers, annual electricity consumption, and total annual CO2 emissions to model MSW generation rates in Bahrain.…”

Classification Algorithm for Multiple Image Formats Suorting Complex Neural Network Models

“…When the model performs inference, it will take up more memory. However, the amount of calculation puts a load on the computing resources of the mobile phone processor, and a large amount of calculation will keep the mobile phone in working state, which will have a certain impact on the battery life of the mobile phone [11,12]. Therefore, focusing on the amount of parameters and calculation can directly affect the size of the model, thereby indirectly affecting the memory, battery life, performance and other issues of the mobile phone [13,14].…”