Forecasting the All-Weather Short-Term Metro Passenger Flow Based on Seasonal and Nonlinear LSSVM

  • Xin Huang School of Civil Engineering and Transportation, South China University of Technology
  • Yimin Wang School of Civil Engineering and Transportation, South China University of Technology
  • Peiqun Lin School of Civil Engineering and Transportation, South China University of Technology
  • Heng Yu School of Civil Engineering and Transportation, South China University of Technology
  • Yue Luo School of Civil Engineering and Transportation, South China University of Technology
Keywords: seasonal and nonlinear least square support vector machine, short-term subway passenger flow prediction, multi-model fusion prediction, time series

Abstract

Accurate metro ridership prediction can guide passengers in efficiently selecting their departure time and simultaneously help traffic operators develop a passenger organization strategy. However, short-term passenger flow prediction needs to consider many factors, and the results of the existing models for short-term subway passenger flow forecasting are often unsatisfactory. Along this line, we propose a parallel architecture, called the seasonal and nonlinear least squares support vector machine (SN-LSSVM), to extract the periodicity and nonlinearity characteristics of passenger flow. Various forecasting models, including auto-regressive integrated moving average, long short-term memory network, and support vector machine, are employed for evaluating the performance of the proposed architecture. Moreover, we first applied the method to the Tiyu Xilu station which is the most crowded station in the Guangzhou metro. The results indicate that the proposed model can effectively make all-weather and year-round passenger flow predictions, thus contributing to the management of the station.

References

Urban Rail Transit Technical Working Committee of China Civil Engineering Society. Proposal for Urban Rail Transit Technology Development Outline (2010-2015). Urban Rapid Transit Traffic. 2010;23(06): 3-8. DOI: 10.3969/j.issn.1672-6073.2010.06.002

He Y, Sheng WW, Luo AH. Track extension, you and I travel more smoothly. People's Daily. February 3, 2019. Available from: http://paper.people.com.cn/rmrb/html/2019-02/13/nw.D110000renmrb_20190213_2-07.htm [Accessed 23rd March 2020].

Yang J. Research on Metro Passenger Flow Short-time Prediction and Evacuation Simulation. PhD thesis. Beijing Jiaotong University; 2013.

Smith BL, Demetsky MJ. Traffic flow forecasting: Comparison of modeling approaches. Journal of Transportation Engineering. 1997;123(4): 261. DOI: 10.1061/(ASCE)0733-947X(1997)123:4(261)

Yang ZS, Wang Y, Guan Q. Short-time traffic flow prediction method based on support vector machine method. Journal of Jilin University (Engineering and Technology Edition). 2006;26(6): 881-884. DOI: 10.13229/j.cnki.jdxbgxb2006.06.010

Vanajakshi L, Rilett LR. Support Vector Machine Technique for the Short Term Prediction of Travel Time. In: IEEE Intelligent Vehicles Symposium, 13-15 June 2007, Istanbul. IEEE; 2007. p. 600-605. DOI: 10.1109/IVS.2007.4290181

Wang Y, Zheng D, Luo S, Zhan DM. The research of railway passenger flow prediction model based on BP neural network. Advanced Materials Research. 2013; 605–607: 2366-2369. DOI: 10.4028/www.scientific.net/AMR.605-607.2366

Guo SY, Li WQ, Bai W, Zhang D. Prediction of Short-term Passenger Flow on a Bus Stop Based on LSSVM. Journal of Wuhan University of Technology (Transportation Science & Engineering). 2013;37(03): 603-607. DOI: 10.3963/j.issn.2095-3844.2013.03.037

Guo JY, Wang ZJ, Chen HW. On-line multi-step prediction of short term traffic flow based on GRU neural network. Proceedings of the 2nd International Conference on Intelligent Information Processing; 2017. p. 7-12. DOI: 10.1145/3144789.3144804

Wang XM, Zhang N, Zhang YL, Shi ZB. Forecasting of Short-Term Metro Ridership with Support Vector Machine Online Model. Journal of Advanced Transportation. 2018. DOI: 10.1155/2018/3189238

Kong WC, Dong ZY, Jia YW, Hill DJ. Short-Term Residential Load Forecasting Based on LSTM Recurrent Neural Network. IEEE Transactions on Smart Grid. 2019;10(1): 841-851. DOI: 10.1109/TSG.2017.2753802

Lu WX, Li C. Forecasting of Short-Time Tourist Flow Based on Improved PSO Algorithm Optimized LSSVM Model. Computer Engineering and Applications. 2019;55(18): 247-255. DOI: 10.3778/j.issn.1002-8331.1807-0063

Boto GD, Díaz PFJ, González OD, et al. Wavelet-based denoising for traffic volume time series forecasting with self-organizing neural networks. Computer-Aided Civil and Infrastructure Engineering. 2010;25(7): 530-545. DOI: 10.1111/j.1467-8667.2010.00668.x

Pan L. Short-time Forecasting of High-speed Railway Passenger Flow Based on Ensemble Empirical Mode Decomposition-Gray Support vector Machine. PhD thesis. Beijing Jiaotong University; 2012.

Wei Y, Chen MC. Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C: Emerging Technologies. 2012;21(1): 148-162. DOI: 10.1016/j.trc.2011.06.009

Bouzerdoum M, Mellit A, Massi PA. A hybrid model (SARIMA-SVM) for short-term power forecasting of a small-scale grid-connected photovoltaic plant. Solar Energy. 2013;98: 226-235. DOI: 10.1016/j.solener.2013.10.002

Sun YX, Leng B, Guan W. A novel wavelet-SVM short-time passenger flow prediction in Beijing subway system. Neurocomputing. 2015;166: 109-121. DOI: 10.1016/j.neucom.2015.03.085

Tang LY, Zhao Y, Cabrera J, Ma J. Forecasting Short-Term Passenger Flow: An Empirical Study on Shenzhen Metro. IEEE Transactions on Intelligent Transportation Systems. 2019;20(10): 3613-3622. DOI: 10.1109/TITS.2018.2879497

Ma XL, Zhang JY, Du BW, Ding C. Parallel Architecture of Convolutional Bi-Directional LSTM Neural Networks for Network-Wide Metro Ridership Prediction. IEEE Transactions on Intelligent Transportation Systems. 2019;20(6): 2278-2288. DOI: 10.1109/TITS.2018.2867042

Bates JM, Granger CWJ. The Combination of Forecasts. Journal of the Operational Research Society. 1969:20(4): 451-468. DOI: 10.1057/jors.1969.103

People's Network. 360 big data release Spring Festival ‘empty city index’ Beijing and Shanghai have not entered the top five. Available from: http://www.sohu.com/a/125388616_114731 [Accessed 23rd March 2020].

Sain SR, Vapnik VN. The Nature of Statistical Learning Theory. Technometrics. 1996;38(4): 409. DOI: 10.1080/00401706.1996.10484565

Vapnik VN. An overview of statistical learning theory. IEEE Transactions on Neural Networks.1999;10(5): 988-999. DOI: 10.1109/72.788640

Cherkassky V, Ma YQ. Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks. 2004;17(1): 113-126. DOI: 10.1016/S0893-6080(03)00169-2

Eberhart R, Kennedy J. A New optimizer using particle swarm theory. In: Proceedings of the Sixth International Symposium on Micro Machine and Human Science, 4-6 October 1995, Nagoya, Japan. IEEE; 1995. p. 39-43. DOI: 10.1109 / MHS.1995.494215

Zhu W, Wang W, Huang ZD. Estimating train choices of rail transit passengers with real timetable and automatic fare collection data. Journal of Advanced Transportation. 2017. DOI: 10.1155/2017/5824051

Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003;50: 159-175. DOI: 10.1016/S0925-2312(01)00702-0

Chapelle O. Training a support vector machine in the primal. Neural Computation. 2007;19(5): 1155-1178. DOI: 10.1162/neco.2007.19.5.1155

Published
2021-03-30
How to Cite
1.
Huang X, Wang Y, Lin P, Yu H, Luo Y. Forecasting the All-Weather Short-Term Metro Passenger Flow Based on Seasonal and Nonlinear LSSVM. Promet [Internet]. 2021Mar.30 [cited 2024Mar.29];33(2):217-31. Available from: http://traffic.fpz.hr/index.php/PROMTT/article/view/3561
Section
Articles