摘要
将主成分分析及BP神经网络模型引入到道路交通安全性预测中,从微观层面分析影响交通事故的因素,重点分析道路参数,并形成文中的原始数据。对原始数据进行主成分分析,将结果作为神经网络模型的输入,建立BP神经网络模型,对道路交通安全性进行预测。结果表明,基于主成分分析的BP神经网络模型比一般BP神经网络模型精度更高,而且从微观的层面进行分析可以得到道路参数对交通事故的影响。
The principal component analysis and BP neural network were introduced into the prediction of traffic safety.Factors influencing traffic accidents were analyzed from microcosmic perspective.The road parameters were analyzed and the original data were obtained.The obtained data were then analyzed by principal component analysis,which later would be used as the input of BP neural network to predict the traffic safety.The result shows that the BP neural network based on principal component analysis has a higher accuracy than general BP neural network.Furthermore,the impact of road parameters on traffic accidents from the microcosmic perspective is achieved.
出处
《交通信息与安全》
2011年第3期79-83,共5页
Journal of Transport Information and Safety
基金
国家自然科学基金项目(批准号:50908155)资助
关键词
主成分分析
BP神经网络
道路安全性预测
principal component analysis
BP neural network
prediction of road safety
