铁路客运量数据挖掘预测方法及应用研究

在分析铁路客票数据特征的基础上,提出采用分段模糊BP神经网络对铁路客运量进行数据挖掘预测。通过对铁路客票数据的分段处理,提高了网络学习的收敛速度和预测精度,并在MATLAB环境下建立了分段模糊BP神经网络模型,在仿真试验中各分段的期望输出和实际输出之间吻合较好,从而证明了分段模糊的数据处理方法是有效的;同时,预测的客运量和实际客运量数值非常接近,说明分段模糊BP神经网络得到的数据挖掘预测模型对铁路客运量有很好的预测效果,该预测模型可信,为预测铁路客运量提出了一种新思路。

Study on Prediction Method of Data Mining of the Passenger Traffic Volume of Railways and Its Application

The segment fuzzy BP Neural Network is adopted to predict the passenger traffic volume of railways in data mining based on analyzing the data feature of railway passenger tickets. The convergence speed and prediction precision of the neural network are both improved by segmentation of the passenger ticket data. The model of the segment fuzzy BP Neural Network is set up using Matlab software. The emulation results show that the anticipant and the actual output results of all the segments are very similar, which proves that data processing of segment fuzzy is effective; at the same time, the anticipant and the actual output results of the passenger traffic volume are very proximate, which shows that the prediction model of data mining is reliable to predict the passenger traffic volume. This research provides a new thought to forecast the passenger traffic volume in data mining.