|Table of Contents|

[1] Shen Jin, Zhao Jiandong, Gao Yuan, et al. Probabilistic interval prediction of metro-to-bus transferpassenger flow in the trip chain [J]. Journal of Southeast University (English Edition), 2022, 38 (4): 408-417. [doi:10.3969/j.issn.1003-7985.2022.04.010]
Copy

Probabilistic interval prediction of metro-to-bus transferpassenger flow in the trip chain()
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
38
Issue:
2022 4
Page:
408-417
Research Field:
Traffic and Transportation Engineering
Publishing date:
2022-12-20

Info

Title:
Probabilistic interval prediction of metro-to-bus transferpassenger flow in the trip chain
Author(s):
Shen Jin1;  Zhao Jiandong1;  2;  Gao Yuan3;  Feng Yingzi1;  Jia Bin1
1School of Traffic and Transportation, Beijing Jiaotong University, Beijing 100044, China
2Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport, Beijing Jiaotong University, Beijing 100044, China
3School of Traffic and Transportation, Northeast Forestry University, Harbin 150040, China
Keywords:
urban traffic;  probabilistic interval prediction;  deep learning;  metro-to-bus transfer passenger flow;  trip chain
PACS:
U491.1
DOI:
10.3969/j.issn.1003-7985.2022.04.010
Abstract:
To accurately analyze the fluctuation range of time-varying differences in metro-to-bus transfer passenger flows, the application of a probabilistic interval prediction model is proposed to predict transfer passenger flows. First, bus and metro data are processed and matched by association to construct the basis for public transport trip chain extraction. Second, a reasonable matching threshold method to discriminate the transfer relationship is used to extract the public transport trip chain, and the basic characteristics of the trip based on the trip chain are analyzed to obtain the metro-to-bus transfer passenger flow. Third, to address the problem of low accuracy of point prediction, the DeepAR model is proposed to conduct interval prediction, where the input is the interchange passenger flow, the output is the predicted median and interval of passenger flow, and the prediction scenarios are weekday, non-workday, and weekday morning and evening peaks. Fourth, to reduce the prediction error, a combined particle swarm optimization(PSO)-DeepAR model is constructed using the PSO to optimize the DeepAR model. Finally, data from the Beijing Xizhimen subway station are used for validation, and results show that the PSO-DeepAR model has high prediction accuracy, with a 90% confidence interval coverage of up to 93.6%.

References:

[1] Adler T, Ben-Akiva M. A theoretical and empirical model of trip chaining behavior[J]. Transportation Research Part B: Methodological, 1979, 13(3): 243-257. DOI:10.1016/0191-2615(79)90016-X.
[2] Kondo K, Kitamura R. Time-space constraints and the formation of trip chains[J].Regional Science and Urban Economics, 1987, 17(1): 49-65. DOI:10.1016/0166-0462(87)90068-8.
[3] Tan J M, Xu R H. Analysis of multi-factors influencing trip chain buildup [J]. Journal of Tongji University(Natural Science), 2009, 37(10): 1340-1344. DOI:10. 3969/j. issn. 0253-374x. 2009. 10. 012. (in Chinese)
[4] Qi C, Zhu Z J, Guo X C, et al. Examining interrelationships between tourist travel mode and trip chain choices using the nested logit model[J]. Sustainability, 2020, 12(18): 7535. DOI:10.3390/su12187535.
[5] Wang C Y, Hu S R, Chu C P. A combined activity nodes choice and trip-chain based user equilibrium traffic assignment model[J]. Transportation Research Procedia, 2017, 25: 2461-2472. DOI:10.1016/j.trpro.2017.05.271.
[6] Wang J C, Chen S K, He Y Q, et al. Simulation of transfer organization of urban public transportation hubs[J].Journal of Transportation Systems Engineering and Information Technology, 2006, 6(6): 96-102. DOI:10.1016/S1570-6672(07)60004-X.
[7] Wang Z W, Chen T, Song M Q. Coordinated optimization of operation routes and schedules for responsive feeder transit under simultaneous pick-up and delivery mode[J]. Journal of Traffic and Transportation Engineering, 2019, 19(5): 139-149. DOI:10.19818/j.cnki.1671-1637.2019.05.014. (in Chinese)
[8] Zhang X J. The study on the transfer between urban rail transportation and conventional public transit [D]. Chengdu: Southwest Jiaotong University, 2004.(in Chinese)
[9] Xiong J, Guan W, Sun Y X. Metro transfer passenger forecasting based on Kalman filter[J]. Journal of Beijing Jiaotong University, 2013, 37(3): 112-116, 121. DOI:10. 3969/j. issn. 1673-0291. 2013. 03. 021. (in Chinese)
[10] Zhang G P. Time series forecasting using a hybrid ARIMA and neural network model[J].Neurocomputing, 2003, 50: 159-175. DOI:10.1016/S0925-2312(01)00702-0.
[11] Liu G J, Yin Z Z, Jia Y J, et al. Passenger flow estimation based on convolutional neural network in public transportation system[J]. Knowledge-Based Systems, 2017, 123: 102-115. DOI:10.1016/j.knosys.2017.02.016.
[12] Hu Y R, Wu C, Liu H J. Prediction of passenger flow on the highway based on the least square support vector machine[J]. Transport, 2011, 26(2): 197-203.
[13] Zhao J D, Gao Y, Bai Z M, et al. Traffic speed prediction under non-recurrent congestion: Based on LSTM method and BeiDou navigation satellite system data[J]. IEEE Intelligent Transportation Systems Magazine, 2019, 11(2): 70-81. DOI:10.1109/MITS.2019.2903431.
[14] Zhang X H. Short-term traffic flow interval forecasting based on grey system theory[D]. Zhenjiang: Jiangsu University, 2011.(in Chinese)
[15] Zhu S L, Cheng L, Chu Z M. Bayesian network model for traffic flow estimation using prior link flows[J].Journal of Southeast University(English Edition), 2013, 29(3): 322-327. DOI:10.3969/j.issn.1003-7985.2013.03.017.
[16] Tong L, Guan Z. Fuzzy granulation prediction of traffic flow based on improved whale optimization support vector machine[J]. Journal of Computer Applications, 2021(10): 2919-2927. DOI:10. 11772/j. issn. 1001-9081. 2020122048. (in Chinese)
[17] Salinas D, Flunkert V, Gasthaus J, et al. DeepAR: Probabilistic forecasting with autoregressive recurrent networks[J]. International Journal of Forecasting, 2020, 36(3): 1181-1191. DOI:10.1016/j.ijforecast.2019.07.001.
[18] Yan L C, Li Y, Song H, et al. Web traffic prediction based on prophet-DeepAR[J]. Journal of Guangxi Normal University(Natural Science Edition), 2022(3): 172-184. DOI:10. 16088/j. issn. 1001-6600. 2021071505. (in Chinese)
[19] Zhu G, Li W, Du S G, et al. Time series prediction based on deep learning model DeepAR and application examples[J]. E-Business Journal, 2020, 39(7): 83-86. DOI:10. 14011/j. cnki. dzsw. 2020. 07. 039. (in Chinese)
[20] Li H, Wang Z J, Li Z, et al. Prediction of remaining useful life of aero-engine based on stacked Autoencoder and DeepAR [J]. Journal of Propulsion Technology, 2022: 1-10.
[21] Wang Z J, Zhan Z H, Kwong S, et al. Adaptive granularity learning distributed particle swarm optimization for large-scale optimization[J]. IEEE Transactions on Cybernetics, 2021, 51(3): 1175-1188. DOI:10.1109/TCYB.2020.2977956.
[22] Seaborn C W. Application of Smart Card fare payment data to bus network planning in London, UK [D]. Massachusetts: Massachusetts Institute of Technology, 2008.
[23] Wang Y Y. Research on methods of extraction commuting trip characteristic based on public transportation multi-source data [D]. Beijing: Beijing University of Technology, 2014.(in Chinese)
[24] �D6;zakta瘙塂 H, K�131;rkavak N, Alpay A N. A paradox of the average waiting time for the case of a single bottleneck on the commuters’ route[J]. Modelling and Simulation in Engineering, 2021, 2021: 1-9. DOI:10.1155/2021/2315987.
[25] Yan W P. Evaluation of public transportation index in metropolis[D]. Beijing: Beijing University of Technology, 2012.(in Chinese)
[26] Zhao Y Y, Xia L, Jiang X G. Short-term subway passenger flow prediction model based on empirical modal decomposition and long-term memory neural networks [J]. Journal of Traffic and Transportation Engineering, 2020, 20(4): 194-204.

Memo

Memo:
Biographies: Shen Jin(1997—), female, Ph.D. graduate; Zhao Jiandong(corresponding author), male, doctor, professor, zhaojd@bjtu.edu.cn.
Foundation items: The National Key Research and Development Program of China(No. 2019YFB160-0200), the National Natural Science Foundation of China(No. 71871011, 71890972/71890970).
Citation: Shen Jin, Zhao Jiandong, Gao Yuan, et al. Probabilistic interval prediction of metro-to-bus transfer passenger flow in the trip chain[J].Journal of Southeast University(English Edition), 2022, 38(4):408-417.DOI:10.3969/j.issn.1003-7985.2022.04.010.
Last Update: 2022-12-20