摘要
为预测更精确的客流量数据,达到公交出行的最佳效果。首先结合小波变换理论及BP神经网络的相关知识,建立一种基于小波神经网络的预测模型;其次选取某个城市的公交IC卡刷卡数据作为样本来源,应用小波神经网络模型,以及传统的BP神经网络模型对其进行预测与对比分析。结果发现小波神经网络预测模型预测精度、拟合度均有所提高,具备适用性。
In order to predict more accurate passenger flow data,the best effect of transit travel is achieved.Firstly,combining wavelet transform theory and relevant knowledge of BP neural network,a prediction model based on wavelet neural network is established;secondly,the bus IC card swiping data of a certain city is selected as the sample source,and the wavelet neural network model and the traditional BP neural network model are used to make prediction and comparative analysis.It is found that the wavelet neural network prediction model not only has better prediction accuracy,but also has a high degree of fit and more applicability.
作者
贾庆林
晋民杰
张涛
孙帆
JIA Qing-lin;JIN Min-jie;ZHANG Tao;SUN Fan(School of Transportation and Logistics, Taiyuan University of Science and Technology, Taiyuan 030024, China)
出处
《武汉轻工大学学报》
2020年第3期50-54,共5页
Journal of Wuhan Polytechnic University
基金
山西省重点研发计划项目(No.201803D31076)
太原科技大学科研启动基金项目(No.20192050)。
关键词
客流量
传统的BP神经网络模型
小波神经网络预测模型
预测
passenger flow
traditional BP neural network model
wavelet neural network prediction model
prediction
