In order to improve the computational performance and robustness of the random forest model,and overcome the adverse effects of parameter selection on the performance of the random forest model,this study uses the improved raccoon algorithm(ICOA)to optimize the random forest model(RF),establishes the ICOA-RF model,and applies the ICOA-RF hybrid model to validate the classification of accidents in civil aviation history.The results show that:the raccoon algorithm is improved by wavelet function perturbation strategy and mutualistic symbiosis strategy,which improves the searching ability of the raccoon algorithm and increases the diversity of the populations,avoids blind searching,and improves the overall solution accuracy of the algorithm;the ICOA-RF model fits the civil aviation historical accident data better,and the classification accuracy is good.It can be seen that the ICOA-RF model has a strong global optimization ability,the classification accuracy meets the requirements,and the model can be used for the classification of civil aviation accidents.
关键词
小波函数扰动策略/互利共生策略/浣熊算法/随机森林/模型优化/民航事故等级分类
Key words
wavelet function perturbation strategy/mutual benefit and symbiosis strategy/raccoon algorithm/random forest/model optimization/classification of civil aviation accidents
维普
万方数据