论文部分内容阅读
交通状态预测是交通流诱导和交通信息发布系统的重要依据.本文提出了一种基于能力区域的城市快速路交通状态预测方法,该方法通过构建神经网络分类器的能力区域,根据样本数据与交通状态类簇之间的空间距离,预测道路交通状态等级.神经网络分类器的能力区域能够有效融合时间、空间等多种特征,并且不需要考虑各特征之间的相关性,具有很强的适应性.实验结果表明,与经典的预测方法相比,其预测误差明显降低,均等系数增大,基于能力区域的方法预测交通状态具有较高的准确性.
Traffic status prediction is an important basis for traffic flow guidance and traffic information release system.This paper presents a traffic area prediction method based on the ability area, which is based on the ability of the neural network classifier to construct a traffic classification system based on the sample data and traffic The distance between the state clusters and the prediction of the road traffic status.Nerve network classifier’s ability region can effectively integrate many features such as time and space without the need to consider the correlation between the features and has strong adaptability The experimental results show that compared with the classical prediction method, the prediction error is obviously reduced and the equal coefficient is increased, and the traffic area based on the ability area is more accurate.