Air pollution greatly reduces the visibility of the air, leading to frequent traffic accidents (TA), and the resulting economic losses cannot be ignored. In order to better control and mitigate the traffic accident economic losses of air pollution, this paper proposes a novel assessment and forecasting system for TA economic loss of air pollution, which contains assessment module and forecasting module. In the assessment module, a reasonable assessment of TA economic loss is provided which also analyzes the efficiency of air pollution control based on data envelope analysis directional distance function. In the forecasting module, this system develops a rolling nonlinear optimized initial self-adapting grey model based on multi-objective optimization algorithm to forecast the TA economic loss of air pollution. The results from the proposed system indicate that the proposed system has outstanding performance which can provide great information assistant for a decision-maker.
Keywords: Artificial intelligence; Economic loss assessment; Machine learning; Multi-objective optimization; Self-adapting grey model; Time series forecasting.
© 2021. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.