Short-Term Passenger Flow Prediction Based on a Hybrid Model of Support Vector Machine and Long Short-Term Memory Network

Yuting Tian; Jinbing Ha

doi:10.54097/d8m4qd60

Authors

Yuting Tian
Jinbing Ha

DOI:

https://doi.org/10.54097/d8m4qd60

Keywords:

Urban rail transit, passenger flow prediction, passenger flow analysis, support vector machine, long short-term memory neural network, BP neural network.

Abstract

This study focuses on Line 10 of the Nanjing subway system, analyzing the spatiotemporal distribution characteristics of passenger flow data from the perspectives of network layout and station functionality. The research summarizes the unevenness, temporal variability, periodicity, and similarity characteristics of passenger flows along this line. Addressing these characteristics, a preprocessing method combining Self-Organizing Map (SOM) algorithm with Isolation Forest is proposed for handling passenger flow data, which involves data classification and anomaly detection. Input features such as periodic flows, weekday identification, weather conditions, and passenger flow categories are constructed. A Short-Term Passenger Flow Prediction Model (PSO-SVM) is developed, employing Support Vector Machine (SVM) algorithm optimized by Particle Swarm Optimization (PSO) for enhanced parameter tuning capability. The integrated predictive model is applied within the operational decision-making framework of Line 10, facilitating data storage, retrieval, and analysis of future station passenger flows. This enables rail transit operators to adjust operational strategies more accurately based on predicted passenger flows, thereby improving overall energy efficiency.

Downloads

Download data is not yet available.

References

[1] Han Linfei, Zhang Shenghai, Gao Meng Review and Reflection: The Impact of Soviet Urban Planning on Beijing Urban Planning in the 1950s Beijing Planning and Construction, 2009 (5): 15-20.

[2] Zhong Jiru Research on the Impact of Urban Built Environment on the Passenger Flow Characteristics of Rail Transit [D] Dalian University of Technology, 2019.

[3] Singhal A, Kamga C, Yazici A. Impact of weather on urban transit ridership[J]. Transportation research part A: policy and practice, 2014,69:379-391.

[4] Ding Shichao Research on the Impact of Weather Factors on High Speed Rail Passenger Flow [D] Beijing Jiaotong University, 2019.

[5] Dong H, Ye J. Passenger Flow Analysis Based on AFC Data of Shanghai Urban Rail Transit in People's Square Station[M]//ICTE 2013: Safety, Speediness, Intelligence, Low-Carbon, Innovation. 2013:736-744.

[6] Kitamura R, Fujii S, Pas E I. Time-use data, analysis and modeling: toward the next generation of transportation planning methodologies[J]. Transport Policy, 1997,4(4):225-235.

[7] Litman T. Generated traffic and induced travel[M]. Victoria Transport Policy Institute Victoria, BC, Canada, 2017.

[8] Jian J, De-ming Y. Analysis of Bus Diversity Fare Vote System and Passenger Flow Effect[J]. Journal of Transportation Systems Engineering and Information Technology, 2010,10(3):115.

[9] Zhang Y, Xie Y. Forecasting of short-term freeway volume with v-support vector machines[J]. Transportation Research Record, 2007,2024(1):92-99.

[10] Jianjun M, Pengfang C, Decang L I, et al. Summary of Research on Railway Freight Volume Forecast.[J]. Railway Standard Design, 2022,66(10).

[11] Guo Wen Research on Short term Passenger Flow Prediction Method for Rail Transit Based on Support Vector Machine [D] Suzhou University, 2019.

[12] Zhu Bingjie Application of Improved K-Nearest Neighbor Algorithm in Urban Rail Transit Passenger Flow Prediction [D] Beijing Jiaotong University, 2019.

[13] Cha Min Research on Public Transport Passenger Flow Prediction Method Based on Spark Platform [D] University of Electronic Science and Technology of China, 2017.

[14] Kennedy J, Eberhart R. Particle swarm optimization: Proceedings of ICNN'95-international conference on neural networks[C], 1995. ieee.

[15] Ahmed M S, Cook A R. Analysis of freeway traffic time-series data by using Box-Jenkins techniques[M]. 1979.

[16] Graves A, Mohamed A, Hinton G. Speech recognition with deep recurrent neural networks: 2013 IEEE international conference on acoustics, speech and signal processing[C], 2013. Ieee.

[17] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural computation, 1997,9(8):1735-1780.

[18] He K, Zhang X, Ren S, et al. Delving deep into rectifiers: Surpassing human-level performance on imagenet classification: Proceedings of the IEEE international conference on computer vision [C], 2015.

[19] Zhang Y, Xie Y. Forecasting of short-term freeway volume with v-support vector machines [J]. Transportation Research Record, 2007,2024(1):92-99.

[20] Zhu J Z, Cao J X, Zhu Y. Traffic volume forecasting based on radial basis function neural network with the consideration of traffic flows at the adjacent intersections [J]. Transportation Research Part C: Emerging Technologies, 2014,47:139-154.

[21] Jian J, De-ming Y. Analysis of Bus Diversity Fare Vote System and Passenger Flow Effect[J]. Journal of Transportation Systems Engineering and Information Technology, 2010,10(3):115.

[22] Kalkstein A J, Kuby M, Gerrity D, et al. An analysis of air mass effects on rail ridership in three US cities[J]. Journal of transport geography, 2009,17(3):198-207.

[23] Guo Z, Wilson N H, Rahbee A. Impact of weather on transit ridership in Chicago, Illinois[J]. Transportation Research Record, 2007,2034(1):3-10.

[24] Stover V W, McCormack E D. The impact of weather on bus ridership in Pierce County, Washington[J]. Journal of Public Transportation, 2012,15(1):95-110.