Skip to main content
SpringerLink
Log in

Mixed logit model based on nonlinear random utility functions: a transfer passenger demand prediction method on overnight D-trains

  • Soft computing in decision making and in modeling in economics
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

In recent years, with the development of high-speed railway in China, the operating mileage and passenger transport capacity have increased rapidly in transportation industry. Due to the high density of trains in the daytime, we usually set up skylights at night (0:00–6:00 am) on high-speed railway for comprehensive maintenance. However, this arrangement contradicts with the operation demand of D-series overnight high-speed trains (overnight D-trains for short). In order to adjust the operation plan of overnight D-trains with skylights coordinately, it is necessary to predict the passenger demand of newly added overnight D-trains. Therefore, in this paper, a mixed logit model based on nonlinear random utility functions for different transport modes is proposed, in order to predict transfer passenger demand. According to Maximum Simulated Likelihood Method, the likelihood function of this mixed logit model is proposed to maximize the overall utility value of different passenger groups while Metropolis–Hastings algorithm is adopted to iteratively solve the probabilities of discrete random variables in utility functions. After that, the unknown distributions of parameters are estimated and the optimal solution of this model is provided by traditional algorithms, basic heuristic algorithms and improved heuristic algorithms including improved fireworks-simulated annealing algorithm proposed in this paper, respectively. Finally, a real-world instance with related data of Beijing–Shanghai corridor is implemented to demonstrate the performance and effectiveness of the proposed approaches.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. Utility-maximizing rule Based on the usual mentality of people for making choices, people always choose the option which will give them the highest utility under certain budget.

  2. Detail balance condition When the probability transition matrix of non-periodic Markov chain and the probability of each state satisfy \(\pi (i)\cdot p(j|i)=\pi (j)\cdot p(i|j)\) where j denotes the next state of the current state i, and the final state \(\pi \) is a given, desired stationary distribution of the Markov chain.

References

  • Ahn Y, Kowada T, Tsukaguchi H, Vandebona U (2017) Estimation of passenger flow for planning and management of railway stations. Transp Res Procedia 25:315–330

    Article  Google Scholar 

  • Castro-Neto M, Jeong Y, Jeong MK, Han LD (2009) Aadt prediction using support vector regression with data-dependent parameters. Expert Syst Appl 36(2):2979–2986

    Article  Google Scholar 

  • Castro-Neto M, Jeong YS, Jeong MK, Han LD (2009) Online-svr for short-term traffic flow prediction under typical and atypical traffic conditions. Expert Syst Appl 36(3):6163–6173

    Article  Google Scholar 

  • Chen H, Grant-Muller S (2001) Use of sequential learning for short-term traffic flow forecasting. Transp Res Part C: Emerg Technol 9(5):319–336

    Article  Google Scholar 

  • Cheng H, Yang X (2015) Random parameter nested logit model for combined departure time and route choice. Int J Transp Sci Technol 4(1):93–106

    Article  MathSciNet  Google Scholar 

  • Dia H (2001) An object-oriented neural network approach to short-term traffic forecasting. Eur J Oper Res 131(2):253–261

    Article  MATH  Google Scholar 

  • Dorigo M (1992) Optimization, learning and natural algorithms. PhD thesis, Italy: Department of Electronics, Politecnico di Milano

  • Eleni IV (2007) Prediction of non-recurrent short-term traffic patterns using genetically optimized probabilistic neural networks. Oper Res 7(2):171–184

    Google Scholar 

  • Eleni IV, Karlaftis MG, Golias JC (2010) Spatio-temporal short-term urban traffic volume forecasting using genetically optimized modular networks. Comput-Aid Civil Infrastruct Eng 22(5):317–325

    Google Scholar 

  • Gelhausen MC, Berster P, Wilken D (2018) A new direct demand model of long-term forecasting air passengers and air transport movements at German airports. J Air Transp Manage 71:140–152

    Article  Google Scholar 

  • Geng X, Li Y, Wang L, Zhang L, Yang Q, Ye J, Liu Y (2019) Spatiotemporal multi-graph convolution network for ride-hailing demand forecasting. In: The 33rd AAAI conference on artificial intelligence (AAAI)

  • Glisović N, Milenković M, Bojović N, švadlenka L, Avramović Z, (2016) A hybrid model for forecasting the volume of passenger flows on serbian railways. Oper Res 16(2):271–285

  • Guang Z, Yang J, Jian L (2017) Forecast of short-term passenger flow of urban railway stations based on seasonal arima model. In: International conference on electrical and information technologies for rail transportation

  • Guo S, Lin Y, Feng N, Song C, Wan H (2019) Attention based spatial-temporal graph convolutional networks for traffic flow forecasting. In: The 33rd AAAI conference on artificial intelligence (AAAI)

  • Han B, Ren S, Bao JJ (2020) Mixed logit model based on improved nonlinear utility functions: a market shares solution method of different railway traffic modes. Sustainability 12(4):1406

    Article  Google Scholar 

  • Han Y, Wang S, Ren Y, Wang C, Gao P, Chen G (2019) Predicting station-level short-term passenger flow in a citywide metro network using spatiotemporal graph convolutional neural networks. IISPRS Int J Geo-Inf 30(8):1–25

    Google Scholar 

  • Hensher D, Greene WH (2003) The mixed logit model: the state of practice. Transportation 30(2):133–176

    Article  Google Scholar 

  • Hess S, Polak JW (2005) Mixed logit modeling of airport choice in multi-airport regions. J Air Transp Manage 11(2):59–68

    Article  Google Scholar 

  • Huang ZJ, Feng S (2014) Grey forecasting model in the application of railway passenger flow prediction research. Technol Econ Areas Commun 16(1):57–60

    Google Scholar 

  • Ivanov V, Osetrov E (2018) Application of artificial neural networks and singular-spectral analysis in forecasting the daily traffic in the moscow metro. In: European physical journal web of conferences

  • Jiang RY (1997) One new probability density function with bimodal shape. J Chang Commun Univ 13(1):1–8

    Google Scholar 

  • Jonas B, Mindaugas M, Vladas I, Skirmantas M (2004) Analysis and forecast of the dynamics of passenger transportation by public land transport. Transport 19(1):3–8

    Article  Google Scholar 

  • Jou RC, Hensher DA, Hsu TL (2011) Airport ground access mode choice behavior after the introduction of a new mode: a case study of Taoyuan international airport in Taiwan. Transp Res Part E: Logist Transp Rev 47(3):371–381

    Article  Google Scholar 

  • Jung SY, Yoo KE (2014) Passenger airline choice behavior for domestic short haul travel in South Korea. J Air Transp Manage 38:43–47

    Article  Google Scholar 

  • Lee JK, Yoo KE, Song KH (2016) A study on travelers‘ transport mode choice behavior using the mixed logit model: a case study of the seoul-jeju route. J Air Transp Manage 56:131–137

    Article  Google Scholar 

  • Lei ZT, Zuo DJ, Wang WX, Xue F (2018) Influence of the train arrival time and on-schedule rate on boarding choice for railway passengers. Theor Policy 40(9):69–74

    Google Scholar 

  • Li CB, Wang KC (2007) A new grey forecasting model based on bp neural network and markov chain. J Cent South Univ Technol 14(5):713–718

    Article  Google Scholar 

  • Li JZ, Tan Y (2018) The bare bones fireworks algorithm: a minimalist global optimizer. Appl Soft Comput 62:454–462

    Article  Google Scholar 

  • Li MT, Ji XF, Zhang J, Ran B (2014) Fa-bp neural network-based forecast for railway passenger volume. Appl Mech Mater 641–642:673–677

    Google Scholar 

  • Lin L, He Z, Peeta S (2018) Predicting station-level hourly demand in a large-scale bike-sharing network: a graph convolutional neural network approach. Appl Mech Mater 97:258–276

    Google Scholar 

  • Lopez AC, Rose M, Michael BP (2011) States in mind: evolution, coalitional psychology, and international politics. Int Secur 36(2):48–83

    Article  Google Scholar 

  • McFadden D, Train KE (2000) Mixed mnl models for discrete response. J Appl Econom 15(5):447–470

    Article  Google Scholar 

  • Metropolis N (1953) Algorithms in unnormalized arithmetic. Numer Math 7(2):104–112

    Article  MathSciNet  MATH  Google Scholar 

  • Oh TH, Lee SH, Cheon CK, Yu BY (2017) Design hourly factor estimation with railway passenger data. J Korea Instit Intell Transp Syst 16(1):64–77

    Article  Google Scholar 

  • Oh TH, Lee SH, Kang HU, Insigne MSL, Lee SJ (2017) Estimating an optimal scale of a railway station with non-passengers. J Korea Instit Intell Transp Syst 16(4):76–91

    Article  Google Scholar 

  • Park Y, Ha HK (2006) Analysis of the impact of high-speed railroad service on air transport demand. Transp Res Part E: Logist Transp Rev 42(2):95–104

    Article  Google Scholar 

  • Roos J, Bonnevay S, Gavin G (2018) Dynamic bayesian networks with gaussian mixture models for short-term passenger flow forecasting. In: International conference on intelligent systems and knowledge engineering

  • Shi F, Deng LB, Huo L (2007) Boarding choice behavior and its utility of railway passengers. China Railway Sci 28(6):117–121

    Google Scholar 

  • Stella F, Vigano V, Bogni D, Benzoni M (2006) An integrated forecasting and regulation framework for light rail transit systems. J Intell Transp Syst 10(2):59–73

    Article  Google Scholar 

  • Tan Y, Zhu YC (2010) Fireworks algorithm for optimization. Int Conf Swarm Intell 6145:355–364

    Google Scholar 

  • Tian QF, Zhao SZ, Cao Y (2011) Prediction of station passenger flow volume based on fractal theory. Appl Mech Mater 99–100:203–206

    Article  Google Scholar 

  • Train KE (2003) Properties of discrete choice models. Discrete choice methods with simulation. Cambridge University Press, Cambridge, England

    Book  MATH  Google Scholar 

  • Wang C, Qian J, Jun LI, Zhao J (2012) Application of trend extrapolation model based on time series in passenger flow prediction of urban transit station. Railway Comput Appl 21(5):50–55

    Google Scholar 

  • Wang M, Lai B, Gong X, Hua X, Huang J (2019) Dynamic spatial-temporal graph convolutional neural networks for traffic forecasting. In: The 33rd AAAI conference on artificial intelligence (AAAI)

  • Wang Q, Sun H (2017) Urban traffic modal splitting based on improved md forecast model. J Xian Univ Archit Technol 49(3):340–345

    Google Scholar 

  • Wardman M (1998) The value of travel time a review of British evidence. J Transp Econ policy 32(3):285–316

    Google Scholar 

  • Wardman M (2006) Demand for rail travel and the effects of external factors. Transp Res Part E: Logist Transp Rev 42(3):129–148

    Article  Google Scholar 

  • Wei Y, Chen M (2012) Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transportation Research Part C: Emerging Technologies 21(1):148–162

  • Yin J, Yang L, Tang T, Gao Z, Ran B (2017) Dynamic passenger demand oriented metro train scheduling with energy-efficiency and waiting time minimization: mixed-integer linear programming approaches. Transp Res Part B: Methodol 97:182–213

  • Yu B, Yin H, Zhu Z (2018a) Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: The twenty-seventh international joint conference on artificial intelligence (IJCAI)

  • Yu W, Li J, He N (2018) Application of nested-logit model in urban rail transit integration of prediction. J Dalian Jiaotong Univ 39(3):27–30

    Google Scholar 

  • Zhao L, Song Y, Zhang C, Liu Y, Wang P, Lin T, Deng M, Li H (2019) T-gcn: a temporal graph convolutional network for traffic prediction. IEEE Trans Intell Transp Syst 21(9):3848–3858

    Article  Google Scholar 

Download references

Acknowledgements

This research is supported by two foundation items including Fundamental Research Funds for the Central Universities (No. 2021YJS039) and National Natural Science Foundation of China (No. 62072025).

Author information

Authors and Affiliations

  1. School of Computer and Information Technology, Beijing Jiaotong University, 100044, Beijing, China

    Bing Han & Shuang Ren

Authors
  1. Bing Han
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shuang Ren
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shuang Ren.

Ethics declarations

Conflict of interest

Author Bing Han and author Shuang Ren declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants performed by any of the authors.

Informed consent

Informed consent is obtained from all individual participants included in the study.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

A. Parameter settings in numerical experiment

A. Parameter settings in numerical experiment

As shown in Fig. 10, we set Beijing municipal government as origin and Shanghai municipal government as destination, and then, the total expenses and time of different transport modes in Beijing–Shanghai corridor are shown in Table 6. Among them, the data of travel expenses and travel time for different transport modes are from Qunar.com and 12306.com, and the data of transfer expenses and time for different transfer modes are from Baidu Map. Due to the large number of certain transport modes, the range of airplane arrival time is from 10:00 AM to 6:00 PM, the range of G-train arrival time is from 10:00 AM to 6:00 PM, and the range of D-train arrival time is from 7:00 AM to 10:00 PM the next day.

And then total travel expenses and total travel time of different combination results, and proposal probabilities (i.e., prior probabilities subjectively based on Sect. 2.1) of different (low-, medium- and high-) income passenger groups are shown in Table 7.

Table 7 Total expenses, total time and proposal probabilities of different combination results
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, B., Ren, S. Mixed logit model based on nonlinear random utility functions: a transfer passenger demand prediction method on overnight D-trains. Soft Comput 26, 3411–3434 (2022). https://doi.org/10.1007/s00500-021-06621-4

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-021-06621-4

Keywords

Search

Navigation