基于灰色BP神经网络模型的道路交通事故预测

Prediction of Road Traffic Accidents Based on Grey BP Neural Network Models

预防道路交通事故是道路交通安全的重要环节,通过对未来交通事故发生次数的准确预测,能够为交通管理和规划工作提供重要依据.本文以2006年至2016年山东省交通事故发生次数为样本,分别使用灰色GM(1,1)模型和灰色BP神经组合模型进行预测并对比数据,结果表明,灰色BP神经网络模型预测精度更高,预测结果相对误差为4.45%,符合实际情况,证明该模型合理可靠,能为道路安全的管理提供依据.

Road traffic accidents are an important link of road traffic safety.Through the accurate prediction of the number of traffic accidents in the future,it can provide an important basis for traffic management and planning.Taking the number of traffic accidents in Shandong Province from 2006 to 2015 as a sample,this paper uses grey GM(1,1)model and grey BP neural network combination model to predict and compare the data.The results show that the grey GM(1,1)model and grey BP neural network combination model can be used to predict and compare the data.Grey BP neural network model has higher prediction accuracy;the relative error of prediction results is 4.45%,which accords with the actual situation.It proves that the model is reasonable and reliable and can provide a basis for road safety management.