中文摘要：

根据交通流的时空关联性和非线性,提出一种基于时空分析的短时交通流量预测模型.在相关系数的基础上扩展时空语义,提出时空相关分析算法,并以支持向量机为预测工具进行预测.弥补现有模型在预测因子选取方面的不足,提高预测精度并避免预测的人为主观性.实验结果表明了算法和模型的有效性.

英文摘要：

Short-term traffic flow forecasting is one of the important issues for intelligent transportation systems（ITS）.There are various methods have been developed to forecast traffic flow so far,but most of the forecasting models are constructed according to analysis of the historical and current traffic flow series in selected section or crossing,without considering the spatial information of related traffic network.Actually,there are many spatio-temporal information such as spatial connectivity of the traffic network and time latency of traffic flow series,these characteristics can be used to improve the efficiency of forecasting.A short-term traffic flow forecasting method based on spatio-temporal analysis is proposed here.Firstly,spatio-temporal correlation coefficient is defined to reflect the relationship of different traffic flow series,a quick calculation method of spatio-temporal correlation coefficient is proposed after analyzing the corresponding properties.Secondly,a spatio-temporal analysis algorithm based on spatio-temporal correlation coefficient matrix is proposed to choose the proper predictor.At last,a forecasting model is built based on support vector machine due to the nonlinear characteristics of traffic flow.To evaluate the proposed method and forecasting model,temporal correlation analysis,spatial correlation analysis and principal component analysis are utilized and tested on synthetic traffic datasets named DynaCHINA.Experimental results show that the proper spatio-temporal characteristics of the traffic flows can be selected as input variables of the forecasting model effectively and the forecasting accuracy is improved.