灰色马尔可夫模型在交通事故预测中的应用

Application of Gray Markov Model to the Prediction of Road Traffic Accidents

采用传统灰色GM（1,1）模型预测道路交通事故这类随机性、波动性较大的数据,存在拟合较差、精度不足等问题。运用马尔可夫模型对预测结果进行优化,并建立灰色马尔可夫预测模型。将该模型应用于1998~2007年全国道路交通事故数据来预测2008年事故次数,结果表明采用该模型预测精度达到96.9%,明显优于单独使用GM（1,1）模型的预测结果。

Random and volatile data of road traffic accidents show poor fitness and low accuracy if forecast by means of the traditional grey model GM（1,1）.If improvement is made on this model and the forecasting result is optimized by using Markov Model,Gray Markov Forecast Model is thereby established and applied to 1998~2007 national road traffic accident data to predict the number of accidents in 2008.The results show that when the model is used,the prediction accuracy reaches 96.9%,largely superior to the forecasting results by means of GM（1,1） model alone.