Predictive study of forest fires based on MIVBP-SVM
Liu Ming, Shuangquan Zhang, Yude He, Ziyi Liu · 2017
In this paper, we take the average impact value method as the evaluation of neural network variable correlation indicators, analysis the data provided by Professor P. Cortez and A. Morais from University of Minho (Portugal) using the MIVBP algorithm to filtrate 13 characterization factors to get 7 characterization parameters affect forest fires, construct the simulation model of the prediction of forest fires based on the support vector machine algorithm, using a test set for testing, the accuracy rate reached 91.89%.