Intrinsic Mode Decomposition and Combined Deep Learning Prediction of Urban Rail Transit Passenger Flow at Variable Time Scales

被引：2

作者：

Zhu, Guangyu ^{[1
]}

Sun, Xinni ^{[1
]}

Yang, Rongzheng ^{[1
]}

Liu, Kanglin ^{[1
]}

Wei, Yun ^{[2
]}

Wu, Bo ^{[3
]}

机构：

[1] Beijing Jiaotong Univ, Beijing Res Ctr Urban Traff Informat Sensing & Ser, Beijing 100044, Peoples R China

[2] Beijing Mass Transit Railway Operat Corp Ltd, Beijing 100014, Peoples R China

[3] Taiyuan China Railway Rail Transit Construct & Ope, Taiyuan 030006, Peoples R China

来源：

JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY | 2023年 / 45卷 / 12期

基金：

中国国家自然科学基金; 中央高校基本科研业务费专项资金资助;

关键词：

Urban railway transit; Short-term passenger flow time series; Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN); Bidirectional Long Short Term Memory (BiLSTM); Combined prediction;

D O I：

10.11999/JEIT221300

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Different operational states of urban rail transit usually correspond to different Intrinsic Mode Functions (IMFs) and time-scale characteristics in passenger flow time series. A combined deep learning prediction model for short-term passenger flow time series of subway is proposed based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) and Bidirectional Long Short Term Memory network (BiLSTM), including: mode decomposition of passenger flow time series based on the CEEMDAN algorithm. The sample entropy and hierarchical clustering are used respectively to analyze the complexity and similarity of IMFs. The IMFs are then classified, merged and reconstructed on this basis. The hyper-parameters of the model are optimized using the Tree-structured Parzen Estimator (TPE) in the Optuna framework, and the combined prediction model CEEMDAN-TPE-BiLSTM is established. Actual data are used to validate the model. The results show that the accuracy and validity indicators of the model all reach the optimum for passenger flow time series data with specific characteristics.

引用

页码：4421 / 4430

页数：10

共 20 条

[1]

CHEN Enhui, YE Zhirui, WANG Chao, Et al., Subway passenger flow prediction for special events using smart card data[J], IEEE Transactions on Intelligent Transportation Systems, 21, 3, pp. 1109-1120, (2020)

[2]

RYU U, WANG Jian, KIM T, Et al., Construction of traffic state vector using mutual information for short-term traffic flow prediction[J], Transportation Research Part C:Emerging Technologies, 96, pp. 55-71, (2018)

[3]

LIANG Shidong, MA Minghui, HE Shengxue, Et al., Short-term passenger flow prediction in urban public transport: Kalman filtering combined k-Nearest Neighbor approach[J], IEEE Access, 7, pp. 120937-120949, (2019)

[4]

WANG Xuemei, ZHANG Ning, ZHANG Yunlong, Et al., Forecasting of short-term metro ridership with Support Vector Machine online model, Journal of Advanced Transportation, 2018, (2018)

[5]

CHEN Zhonghui, LING Xianyao, FENG Xinxin, Et al., Short-term traffic state prediction approach based on FCM and random forest[J], Journal of Electronics & Information Technology, 40, 8, pp. 1879-1886, (2018)

[6]

SUN Bo, SUN Tuo, JIAO Pengpeng, Spatio-temporal segmented traffic flow prediction with ANPRS data based on improved XGBoost, Journal of Advanced Transportation, 2021, (2021)

[7]

YANG Dan, CHEN Kairun, YANG Mengning, Et al., Urban rail transit passenger flow forecast based on LSTM with enhanced long-term features[J], IET Intelligent Transport Systems, 13, 10, pp. 1475-1482, (2019)

[8]

Liang DAI, MEI Yang, QIAN Chao, Et al., Traffic flow forecasting algorithm for large-scale road network based on GAN[J], Control and Decision, 36, 12, pp. 2937-2945, (2021)

[9]

QIN Chao, GAO Xiaoguang, WAN Kaifang, Deep spatio-temporal convolutional long-short memory network[J], Acta Automatica Sinica, 46, 3, pp. 451-462, (2020)

[10]

Cheng ZENG, WU Jiayuan, LUO Xia, Literature review of short-term passenger flow forecast for urban rail transit[J], Railway Transport and Economy, 43, 8, pp. 105-111, (2021)

← 1 2 →