Travel demand and distance analysis for free-floating car sharing based on deep learning method

Autoři: Chen Zhang aff001;  Jie He aff001;  Ziyang Liu aff001;  Lu Xing aff001;  Yinhai Wang aff002
Působiště autorů: School of Transportation, Southeast University, Dongnandaxuelu, Nanjing, P.R. China aff001;  Smart Transportation Applications and Research Laboratory, Department of Civil and Environmental Engineering, University of Washington, Seattle, WA, United States of America aff002
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article
doi: 10.1371/journal.pone.0223973


In order to address the time pattern problems in free-floating car sharing, in this paper, the authors offer a comprehensive time-series method based on deep learning theory. According to car2go booking record data in Seattle area. Firstly, influence of time and location on the free-floating car-sharing usage pattern is analyzed, which reveals an apparent doublet pattern for time and dependence usage amount on population. Then, on the basis of the long-short-term memory recurrent neural network (LSTM-RNN), hourly variation in short-term traffic characteristics including travel demand and travel distance are modeled. The results were also compared with other different statistical models, such as support vector regression (SVR), Autoregressive Integrated Moving Average model (ARIMA), single and second exponential smoothing. It showed that (LSTM-RNN) shows better performance in terms of statistical analysis and tendency precision based on limited data sample.

Klíčová slova:

Deep learning – Forecasting – Fuels – Human mobility – Recurrent neural networks – Statistical data – Statistical methods – Statistical models


1. Henrik B, Francesco C, Kay W. A. Comparing car-sharing schemes in Switzerland: User groups usage patterns. Transportation Research Part A. 2017; 97:17–29.

2. Martin E., Shaheen S. The impacts of car2go on vehicle ownership, modal shift, vehicle miles traveled, and greenhouse gas emissions. (TSRC working paper) University of California, California. 2016.

3. Milos B, Francesco C, Kay W. A. Modeling the impact of parking policy on free-floating carsharing: case study for Zruich, Switzerland. Transportation Research Part C. 2017; 77: 207–205.

4. Michiko N, Hadi D. Vehicle ownership reduction: A comparison of one-way and two-way car-sharing system. Transport Policy. 2018; 64: 38–50.

5. Jorg F. Triangulation of two methods measuring the impacts of a free-floating car sharing systems in Germany. Transportation Research Part A. 2012; 46: 1654–1672.

6. Phiilip S. Chodrow, al-Awwad Zeyad, Shan J, Marta C. G. Demand and congestion in multiplex transportation networks. PLoS ONE. 2016; doi: 10.1371/journal.pone.0161738 27657738

7. Jinjun T, Jian L, Shen Z, Helai H, Fang L. Inferring driving trajectories based on probabilistic model from large scale taxi GPS data. Physica A. 2018; 506(15): 566–577.

8. Jinjun T, Fang L, Yinhai W, Hua W. Uncovering urban human mobility from large scale taxi GPS data. Physica A. 2015; 48(15): 140–153.

9. Jinjun T, Shen Z, Xinqiang C, Fang L, Yajie Z. Taxi Trips distribution modeling based on Entropy-Maximizing theory: A case study in Harbin city-China. Physica A. 2018; 493(1): 430–443.

10. Jinjun T, Han J, Zhibin L, Meng L, Fang L, Yinhai W. A two-layer model for taxi customer searching behaviors using GPS trajectory data. IEEE transactions on intelligent transportation systems. 2016; 17(11): 1–7.

11. Bo C, Harry J. Prediction based on conditional distributions of vine copulas. 2019. Available from:

12. Jinjun T, Shaowei Y, Fang L, Xinqiang C, Helai Huang. A hierarchical prediction model for lane-changes based on combination of fuzzy c-means and adaptive neural network. Expert System with Applications. 2019; doi: 10.1016/j.eswa.2019.04.032

13. Yajie Z, Xinzhi Z, Jinjun T, Xin Y, Lingtan W, Muhammad ljaz, et al. A Coupla-based approach for accommodating the underreporting effect in wildlife-vehicle crash analysis. Sustainability. 2019; 11(2): 418.

14. Katherine K, Rand M. Free-floating car sharing systems: innovations in membership prediction, mode share, and vehicle allocation optimization methodologies.2012; Available from:

15. Henrik B, Francesco C, Kay W. A. Modeling free-floating car-sharing use in Switzerland: A spatial regression and conditional logit approach. Transportation Research Part C.2017; 81: 286–299.

16. Cindy T, Jinhua Z. Seasonal autoregressive model of Vancouver bicycle traffic using weather variables. I-managers Journal on Civil Engineering. 2011; 1(4). doi: 10.26634/jce.1.4.1694

17. Diana J, Goncalo H. Correia d. A. Carsharing systems demand estimation and defined operations: a literature review. European Journal of Transport and Infrastructure Research Issue. 2013; 13(3), 201–220.

18. Andreas K, Rodrigo M, Jens G, Joan C, Rafael B. Urban cycles and mobility patterns exploring and predicting trends in a bicycle-based public transport system. Pervasive and Mobile Computing. 2010; 6(4): 455–466.

19. Abdul W. B, Aqeel A. B, Khadija Q, Khanji H, Sadia K, Ahmad M. S. Forecasting the consumption of gasoline in transport sector in Pakistan based on ARIMA model. Journal of Environmental Progress & Sustainable Energy. 2017; 36: 1490–1497.

20. Chuan D, Jinxiao D, Yanru Z, Xinkai W, Guizhen Y. Using an ARIMA-GARCH Modeling Approach to Improve Subway Short-Term Ridership Forecasting Accounting for Dynamic Volatility. IEEE Transactions On Intelligent Transportation Systems. 2018; 19(4): 1054–1064.

21. Bahman M, Abolfazl S, Camille N. K, Wei H. Cycle-Length Prediction in Actuated Traffic-Signal Control Using ARIMA Model. Journal of Computing in Civil Engineering. 2018; 32(2): 04017083.

22. Yoshua B, Patrice S, Paolo F. Learning Long-Term Dependencies with Gradient Descent Is Difficult. IEEE Transactions on Neural Networks. 1994; 5(2): 157–166. doi: 10.1109/72.279181 18267787

23. Sepp H, Jurgen S. Long Short-Term Memory. Neural Computation. 1997; 9(8): 1735–1780. 9377276

24. Na S-H, Kim H, Min J, Kim K. Improving LSTM CRFs using character-based composition for Korean named entity recognition. Computer Speech and Language. 2019; 54: 106–121.

25. Ostmeyer J. Machine learning on sequential data using a recurrent weighted average. Neurocomputing. 2019; 331: 281–288. doi: 10.1016/j.neucom.2018.11.066 30799908

26. Lianli G. Hierarchical LSTMs with Adaptive Attention for Visual Captioning. IEEE Transactions on Pattern analysis and machine intelligence. 2019; 14(8): 1–17.

27. Yan T, Kaili Z, Jianyuan L, Xianxuan L, Bailin Y. LSTM-based traffic flow prediction with missing data. Neurocomputing. 2018; 318:297–305.

28. Chengcheng X, Junyi Ji, Pan L. The station-free sharing bike demand forecasting with a deep learning approach and large-scale datasets. Transportation Research Part C. 2018; 95: 47–60.

29. Xiaolei M, Zhimin T, Yinhai W, Haiyang Y, Yunpeng W. Long short-term memory neural network for traffic speed prediction using remote microwave data. Transportation Research Part C. 2015; 54:187–197.

30. Rose Y, Yaguang L, Cyrus S, Ugur D, Yan L. Deep learning: a generic approach for extreme condition traffic forecasting, In Proceedings of the 2017 SIAM international Conference on Data Mining. 2017; 777–785.

31. Wu Y, Tan H. Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework. 2016; Available from:

32. Weihai C, Zheng Z, Jingmeng L, Peter C. Y. C, Xingmeng W. LSTM network: a deep learning approach for short-term traffic forecast. IET intelligent Transport Systems. 2017; 11(2): 68–75.

33. Box G.E.P, Jenkins G.M. Time series analysis: Forecasting and control. Holden-Day, San Francisco. 1970.

34. Barbour William W, Prediction of arrival times of freight traffic on US railroads using support vector regression. M.S. Thesis. 2017; Available from:

Článek vyšel v časopise


2019 Číslo 10