【摘要】 为了提高城市道路短时交通流的预测精度,提出一种基于时空变化特性和灰色神经网络的短时交通流预测模型。通过对道路短时交通流时间和空间特性的分析,将预测路段与相邻路段进行灰色关联度分析,深度挖掘道路交通流的空间信息,并利用灰色神经网络组合模型对预测路段进行短时交通流预测。以合肥市的道路实测数据进行实例分析,结果表明,相比单一时间序列预测模型,该方法有效提高了道路短时交通流的预测精度。更多还原

【Abstract】 In order to improve the prediction accuracy of short-term traffic flow on urban roads,a short-term traffic flow prediction model based on spatio-temporal variation characteristics and grey neural network is proposed.Through the analysis of the time and space characteristics of short-term traffic flow on the road,the gray relational degree analysis of the predicted road section and the adjacent road section is carried out,the spatial information of the road traffic flow is deeply excavated,and the grey neural network is used to predict the short-term traffic flow of the predicted road segment.Based on the actual measured data of Hefei City,the results show that compared with the single time series prediction model,this method effectively improves the prediction accuracy of short-term traffic flow.更多还原