基于数据融合的地铁客流量预测方法

为了更加准确地预测城市地铁交通中动态变化的客流量 ,通过分析城市地铁交通客流量的特点 ,提出了一种基于神经网络数据融合的预测方法。这种方法根据预测数据各属性的特点 ,将采集的数据提取出多个相关序列。在此基础上对各序列采取不同的处理、预测方法 ,再利用神经网络进行融合。这种方法可用于数据动态预测的各种领域。实验表明 ,采用这种方法可以有效地改善数据预测的误差。

Subway Traffic Prediction Based on Data-fusion

In this paper, an improved method of dynamic data prediction, based on data-fusion by the artificial neural network, is proposed to obtain a more precise prediction of the varying traffic in subway-stations. Multiple correlative series distilled from the data are treated with respective methods, from which the end-result is predicted on the basis of data-fusion by the artificial neural network. The accurate prediction applies effectively in the field of dynamic data statistics and prediction. Experimental results have shown that the method is able to evidently decrease error.