论文部分内容阅读
道路交通事故预测是道路交通安全研究的一项重要内容,针对灰色GM(1,1)预测模型对波动性较大道路交通事故序列预测精度较低的缺点,引入小波分析理论,在小波分析理论的基础上建立灰色GM(1,1)预测模型.通过小波分析将某省2002-2009年道路交通事故起数分解成多层近似平稳的数据序列,然后对低频重构序列建立GM(1,1)模型进行预测.仿真结果表明,方法的预测结果比直接用灰色GM(1,1)模型更拟合原始数据,预测效果更好.预测结果可以为交通部门科学监管和制定决策提供一定的指导.
Road traffic accident prediction is an important part of road traffic safety research. Aiming at the shortcomings of gray GM (1,1) forecasting model, the prediction accuracy of low-priority road traffic accidents with low volatility is low. By introducing the theory of wavelet analysis, The gray GM (1, 1) prediction model is established based on wavelet analysis, the road traffic accidents in a certain province from 2002 to 2009 are decomposed into multi-layer near-stable data sequence by wavelet analysis, and then GM (1, 1) model.The simulation results show that the forecasting result of the method is more accurate than the original gray GM (1,1) model, and the forecasting result is better than the gray GM (1,1) model.The forecasting results can provide some scientific control and decision-making for the transportation department guide.