摘要
客流量预测是城市智能交通系统的重要组成部分。为实现客流量的准确预测,首先采用变分模态分解(VMD)将时序客流数据分解成不同时间尺度下的本征模态函数(IMF),降低数据噪声对客流预测模型的影响,再结合长短时记忆神经网络(LSTM)进行预测,提出VMD-LSTM预测模型。采集明尼苏达州州际轨道交通客流数据对模型进行验证。结果表明:相对传统LSTM预测模型,VMD改进LSTM使平均绝对百分误差(MAPE)减少8.38%,均方根误差(RMSE)减小256.99,有效提高LSTM神经网络的预测精度与鲁棒性。
Passenger flow prediction is an important part of urban intelligent transportation system.In order to realize accurate prediction of passenger flow,variational mode decomposition was adopted to decompose the time series into intrinsic mode function in different time scales,the long short-term memory neural network of deep learning was used to predict,and the VMD-LSTM prediction model was proposed.Data of minnesota interstate subway passenger flow were collected to validate the model.The results show that compared with the traditional LSTM prediction model,the average absolute percentage error and the root mean square error decreases by 8.38%and 256.99%respectively after improved by VMD,the prediction accuracy and robustness of LSTM neural network are improved effectively.
作者
黄海超
陈景雅
孙睿
Huang Haichao;Chen Jingya;Sun Rui(College of Civil Engineering and Transportation,Hohai University,Nanjing 210098,China)
出处
《华东交通大学学报》
2021年第1期95-99,共5页
Journal of East China Jiaotong University
基金
国家自然科学基金项目(52078190)。
关键词
轨道交通
客流预测
变分模态分解
长短时记忆神经网络
深度学习
rail transit
passenger flow prediction
variational mode decomposition
long short-term memory network
deep learning
