基于小波分解和长短时记忆网络的地铁进站量短时预测

doi:10.3976/j.issn.1002-4026.2019.04.008

山东科学 ›› 2019, Vol. 32 ›› Issue (4): 56-63.doi: 10.3976/j.issn.1002-4026.2019.04.008

基于小波分解和长短时记忆网络的地铁进站量短时预测

高梦琦，昌锡铭，王欢

北京交通大学交通运输学院，北京 100044

收稿日期:2019-01-10 出版日期:2019-08-20 发布日期:2019-08-07
作者简介:高梦琦（1994—），女，硕士研究生，研究方向为交通运输规划与管理。E-mail:17120795@bjtu.edu.cn
基金资助:
中央高校基本科研业务费专项资金（2018YJS192）

Short-term forecasting of the subway passenger flow based on wavelet decomposition and long short-term memory network

GAO Meng-qi,CHANG Xi-ming,WANG Huan

School of traffic and transportation,Beijing Jiaotong University,Beijing 100044,China

Received:2019-01-10 Online:2019-08-20 Published:2019-08-07

摘要/Abstract

摘要： 针对城市地铁车站进站客流量短时预测问题，提出了小波分解和长短时记忆网络(LSTM)相结合的组合预测模型，小波分解和重构可以有效处理数据的波动性，长短时记忆网络可以学习时序信息。以北京地铁西直门站为实例，实现了组合模型对进站量的预测，发现本方法能够得到比较准确的预测效果，平均绝对百分误差为5.48%，与单独使用LSTM和经验模态分解与LSTM结合这两种方法相比分别下降了8.59%和2.94%，表明本方法有更好的预测精度。

关键词: 地铁进站量, 短时预测, 小波分解, 长短时记忆网络, 组合模型

Abstract: In this study,we develop a two-stage passenger flow forecasting model by combining wavelet decomposition and the long short-term memory (LSTM) neural network.Further,the wavelet decomposition and reconstruction can effectively process the fluctuating data,and the LSTM network may be used to learn the time series data.The passenger flow was evaluated by the developed model based on a prediction case study in the Xizhimen subway station in Beijing.In this study,this method was observed to obtain accurate predication results;the mean absolute percentage error was 5.48% and decreased by 8.59% and 2.94%,respectively,when compared with those associated with the single use of LSTM and the use of a combination of empirical mode decomposition with LSTM.Therefore,the proposed method is observed to exhibit improved forecasting accuracy.

Key words: subway passenger flow, short-term forecasting, wavelet decomposition, long short-term memory (LSTM) network, combination model

中图分类号:

U293.13

高梦琦, 昌锡铭, 王欢. 基于小波分解和长短时记忆网络的地铁进站量短时预测[J]. 山东科学, 2019, 32(4): 56-63.

GAO Meng-qi, CHANG Xi-ming, WANG Huan. Short-term forecasting of the subway passenger flow based on wavelet decomposition and long short-term memory network[J]. Shandong Science, 2019, 32(4): 56-63.

参考文献 13

1	陈秀昌.广州地铁客流预测模型研究[J].中国高新技术企业,2008(16):3-4. doi: 10.3969/j.issn.1009-2374.2008.16.006
2	LI L,SU X N,WANG Y W,et al.Robust causal dependence mining in big data network and its application to traffic flow predictions[J].Transportation Research Part C,2015,58:292-307. doi: 10.1016/j.trc.2015.03.003
3	DING C ,DUAN J X,ZHANG Y R,et al.Using an ARIMA-GARCH modeling approach to improve subway short-term ridership forecasting accounting for dynamic volatility[J].IEEE Transactions on Intelligent Transportation Systems,2017，19(4):1-11. doi: 10.1109/TITS.2017.2711046
4	MA T,ZHOU Z,ABDULHAI B.Nonlinear multivariate time-space threshold vector error correction model for short term traffic state prediction[J].Transportation Research Part B: Methodological,2015,76: 27-47. doi: 10.1016/j.trb.2015.02.008
5	MA Z,XING J,MESBAH M,et al.Predicting short-term bus passenger demand using a pattern hybrid approach [J].Transportation Research Part C: Emerging Technologies,2014,39:148-163. doi: 10.1016/j.trc.2013.12.008
6	ZHANG Y Y,HUANG G.Traffic flow prediction model based on deep belief network and genetic algorithm[J].IET Intelligent Transport Systems,2018,12(6):533-541. doi: 10.1049/iet-its.2017.0199
7	ZHAO S Z,NI T H,WANG Y,et al.A new approach to the prediction of passenger flow in a transit system[J].Computers & Mathematics with Applications,2011,61(8):1968-1974. doi: 10.1016/j.camwa.2010.08.023
8	OUYANG L W,ZHU F H,XIONG G,et al.Short-term traffic flow forecasting based on wavelet transform and neural network[C]// 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).Yokohama,Japan: IEEE,2017. doi: 10.1109/ITSC.2017.8317895
9	LI Y,WANG X D,SUN S,et al.Forecasting short-term subway passenger flow under special events scenarios using multiscale radial basis function networks[J].Transportation Research Part C Emerging Technologies,2017,77:306-328. doi: 10.1016/j.trc.2017.02.005
10	KANG D Q,LV Y S,CHEN Y Y.Short-term traffic flow prediction with LSTM recurrent neural network[C]// 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).Yokohama,Japan: IEEE,2017. doi: 10.1109/ITSC.2017.8317872
11	STPHANE M.A Wavelet Tour of Signal Processing[M/OL].[2018-12-20].https://doi.org/10.1016/B978-0-12-374370-1.X0001-8. doi: 10.1016/B978-0-12-374370-1.X0001-8
12	陆凯韬,董红召,陈宁.基于LSTM的公共自行车服务点租还需求量预测[J].计算机测量与控制,2017,25(9):178-181. doi: 10.16526/j.cnki.11-4762/tp.2017.09.046
13	何九冉,四兵锋.EMD-RBF组合模型在城市轨道交通客流预测中的应用[J].铁道运输与经济,2014,36(10):87-92. doi: 10.3969/j.issn.1003-1421.2014.10.017

[1]	姜嘉伟, 赵金宝, 刘文静, 徐月娟, 李明星. 基于SSA-LSTM组合模型的城市轨道交通短时客流预测[J]. 山东科学, 2023, 36(5): 75-84.
[2]	庄皓, 李杨, 陶明坤. 基于Attention机制的CNN-LSTM驾驶人意图识别方法研究[J]. 山东科学, 2023, 36(2): 103-111.
[3]	蒋怡玥，董蜀黔，周淑敏. 基于集成算法的路段短时行驶时间预测[J]. 山东科学, 2018, 31(4): 118-125.
[4]	朱立勤, 高康林, 高明俊. 基于小波分析的蚁群算法在图像边缘提取中的应用[J]. J4, 2011, 24(2): 51-55.

基于小波分解和长短时记忆网络的地铁进站量短时预测

Short-term forecasting of the subway passenger flow based on wavelet decomposition and long short-term memory network

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

参考文献 13

相关文章 4

Metrics

本文评价

推荐阅读 0