Forecasting the Amount of Recyclables Using an Improved Differential Evolution-based Neural Network

Forecasting the amount of recyclables accurately affects succeeding activities such as the allocation and dispatch of resources and the manufacturing of recycled products, and thus plays an essential role in building a successful municipal recycling system. In this paper, the logistic chaotic map and differential evolution algorithm are used to provide optimal initial weights and thresholds for the back-propagation neural network to improve its prediction accuracy. A case study with real data collected from four communities in Shanghai demonstrates the performance of the proposed model. Results show that the proposed model can reduce the average mean absolute error by 27.17% compared to the traditional back-propagation neural network model.