Prediction of Passenger Flow in Urban Rail Transit Based on Big Data Analysis and Deep Learning

Passenger flow prediction is the key to operation efficiency and safety of urban rail transit (URT). This paper combines the deep learning (DL) theory and support vector machine (SVM) into the DL-SVM model for URT passenger flow prediction. Firstly, the deep belief network (DBN) was adopted to extract the features and inherent variation of passenger flow data. On this basis, an SVM regression model was constructed to predict passenger flow. Then, the proposed model was compared with three shallow prediction models through experiments on Qingdao Metro. The results show that the DL-SVM outperformed the other models in accuracy and stability. The research findings shed important new light on the passenger flow prediction in the URT system.

[1]  Adel W. Sadek,et al.  A k Nearest Neighbor based Local Linear Wavelet Neural Network Model for On-line Short-term Traffic Volume Prediction , 2013 .

[2]  Huaping Ye,et al.  'N-Day' Average Volume Based Analysis and Forecasting for Daily Passenger Flow of Shanghai URT , 2009 .

[3]  Yao Wang,et al.  The Research of Railway Passenger Flow Prediction Model Based on BP Neural Network , 2012 .

[4]  Jiaqiu Wang,et al.  Local online kernel ridge regression for forecasting of urban travel times , 2014 .

[5]  Praveen Edara,et al.  Traffic Flow Forecasting for Urban Work Zones , 2015, IEEE Transactions on Intelligent Transportation Systems.

[6]  Gengxin Sun,et al.  Router-Level Internet Topology Evolution Model based on Multi-Subnet Composited Complex Network Model , 2017 .

[7]  Gengxin Sun,et al.  A new opinion leaders detecting algorithm in multi-relationship online social networks , 2018, Multimedia Tools and Applications.

[8]  Yang Jun,et al.  A Wavelet Analysis Based LS-SVM Rail Transit Passenger Flow Prediction Method , 2013 .

[9]  Giulio Lorenzini,et al.  Makespan reduction using dynamic job sequencing combined with buffer optimization applying genetic algorithm in a manufacturing system , 2019 .

[10]  Fei-Yue Wang,et al.  Traffic Flow Prediction With Big Data: A Deep Learning Approach , 2015, IEEE Transactions on Intelligent Transportation Systems.

[11]  Chen Xiao-feng.  Passenger Flow Forecast of Urban Rail Transit Based on Support Vector Regression , 2008 .

[12]  Arepalli Peda Gopi,et al.  Dynamic load balancing for client server assignment in distributed system using genetical gorithm , 2018, Ingénierie des Systèmes d Inf..

[13]  Wenhao Huang,et al.  Deep Architecture for Traffic Flow Prediction: Deep Belief Networks With Multitask Learning , 2014, IEEE Transactions on Intelligent Transportation Systems.

[14]  Sun Yang,et al.  Kalman Filter-Based Short-Term Passenger Flow Forecasting on Bus Stop , 2011 .

[15]  Mu-Chen Chen,et al.  Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks , 2012 .

[16]  Lei Zhang,et al.  Short-term forecasting of high-speed rail demand: A hybrid approach combining ensemble empirical mode decomposition and gray support vector machine with real-world applications in China , 2014 .

[17]  Biao Leng,et al.  A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system , 2015, Neurocomputing.

[18]  Lelitha Vanajakshi,et al.  Short-term traffic flow prediction using seasonal ARIMA model with limited input data , 2015, European Transport Research Review.

[19]  Mu-Chen Chen,et al.  Exploring time variants for short-term passenger flow , 2011 .

[20]  Yanhui Wang,et al.  The modeling of attraction characteristics regarding passenger flow in urban rail transit network based on field theory , 2017, PloS one.

[21]  Mohammad Mehdi Keshtkar,et al.  Sensitivity analysis and thermal performance optimization of evacuated U-tube solar collector using genetic algorithm , 2018, International Journal of Heat and Technology.