基于支持向量机的交通事故影响因素分析

Analysis of influencing factors of traffic accident severity based on support vector machine

以某市城市道理交通事故数据为基础,以事故严重程度为因变量,通过随机森林对各项特征进行重要性分析,选取12个重要性指标进行分析,利用模型对比选择最优的支持向量机进行分析。研究表明,利用随机森林可以将事故严重程度的重要影响因素筛选出来,同时利用高斯核函数SVM可以预测,交通事故严重程度且具有95.72%较高准确度。为验证高斯核函数SVM的最优性,通过决策树与朴素贝叶斯神经网络也进行预测,其结果都显示高斯核函数SVM效果最佳。最后为减轻事故提出相应的解决措施,并提出不足之处。

Based on the municipal city reasonable traffic accident data,the accident severity as the dependent variable,and through the analysis of the importance of the characteristics of random forest choosing 12 indexes of importance were analyzed,and the comparison of models to choose the most optimal support vector machine(SVM)is analyzed,research has shown that use of random forests can be important influencing factors of screening out the severity of accidents,At the same time,gaussian kernel SVM can be used to predict the severity of traffic accidents with a high accuracy of 95.72%.In order to verify the optimality of Gaussian kernel function SVM,decision tree and naive Bayesian neural network are also used to predict,and the results show that gaussian kernel function SVM has the best effect.Finally,the corresponding solutions to reduce the accident are proposed,and the shortcomings are proposed.