Analysis and prediction of vehicle exhaust emission using ANN

This paper focused on the analysis of vehicle emission based on the Hefei remote sensing data during the last three years. And we propose a three-layer artificial neural network model for predicting vehicle exhaust emission using remote sensing data. Firstly, we take adaptive-lasso algorithm to analyze the various factors from the emission data, and determine the principal factors. Secondly, after doing principal components analysis and selecting algorithm and architecture, the Back-Propagation neural network model with 7-12-1 architecture was established as the optimal approach. Finally, we give the prediction results on the testing data-set and prove the potentiality and validity of the proposed method in the prediction of vehicle exhaust emission.