隨著人口的激增和繁忙的城市生活方式，預測個人出行的能力對於公共交通管理，動態系統操作和個性化出行推薦至關重要。但是，大多數現有方法側重於預測人流或目的地，而我們則側重於個人旅程並且同時解決雙系統(捷運與巴士系統)轉乘。在本文中，我們提出了一種方法，可以預測單個乘客的下一次行程（進站位置o，目的地d和目前出站時間到下一次行程t的持續時間）。為了預測單個乘客的下一次行程，我們將其分解為兩個小問題，即1.預測目的地d以及2.預測下一個o和持續時間t。首先，對於目的地d的預測，我們將單個行程分為常規行程和不規則行程，並提出了要解決的個人和組模塊。其次，預測下次進站點o和持續時間t上，我們提出了一個雙系統模組，該模組可以同時預測捷運和巴士系統的下一次行程。

Individual trip prediction is crucial to the management of public transport and personalized trip recommendation systems; however, most existing methods focus on passenger flow or the destination. In the current study, we focus on two problems pertaining to the prediction of trips for individual users: (1) Predicting the destination of the current trip when it is first initiated; and (2) predicting when and where the next trip will be initiated. We employed smart card data as well as several trip features. In preprocessing, we grouped users by these trip features. To predict the destination of the current trip, we first classify the current trip as regular or irregular. Regular cases are examined using historical data at the individual level, whereas irregular trips are examined using data at the group level. To predict the interval to the next trip and corresponding trip origin, we first predict the transport system the user will employ (BRT or MRT) and then use group-level historical data pertaining to that transport system. Extensive experiments on real datasets demonstrate that in terms of prediction accuracy the proposed scheme outperforms existing state-of-the-art systems.

[1] S. Gambs, M.-O. Killijian, and M. N. del Prado Cortez, “Next place prediction usingmobility markov chains,” inProceedings of the first workshop on measurement, privacy,and mobility, 2012, pp. 1–6.
[2] W. Mathew, R. Raposo, and B. Martins, “Predicting future locations with hiddenmarkov models,” inThe 2012 ACM Conference on Ubiquitous Computing, Ubicomp ’12,Pittsburgh, PA, USA, September 5-8, 2012, A. K. Dey, H. Chu, and G. R. Hayes, Eds.ACM, 2012, pp. 911–918. [Online]. Available: https://doi.org/10.1145/2370216.2370421
[3] A. Noulas, S. Scellato, N. Lathia, and C. Mascolo, “Mining user mobility features fornext place prediction in location-based services,” in12th IEEE International Conferenceon Data Mining, ICDM 2012, Brussels, Belgium, December 10-13, 2012, M. J. Zaki,A. Siebes, J. X. Yu, B. Goethals, G. I. Webb, and X. Wu, Eds. IEEE Computer Society,2012, pp. 1038–1043. [Online]. Available: https://doi.org/10.1109/ICDM.2012.113
[4] B. Hawelka, I. Sitko, P. Kazakopoulos, and E. Beinat, “Collective prediction of individualmobility traces for users with short data history,”PloS one, vol. 12, no. 1, p. e0170907,2017.
[5] F. Alhasoun, M. Alhazzani, F. Aleissa, R. Alnasser, and M. Gonz ́alez, “City scale nextplace prediction from sparse data through similar strangers,” inProceedings of ACM KDDWorkshop, 2017, pp. 191–196.
[6] X. Lu, E. Wetter, N. Bharti, A. J. Tatem, and L. Bengtsson, “Approaching the limit ofpredictability in human mobility,”Scientific reports, vol. 3, no. 1, pp. 1–9, 2013.
[7] A. Asahara, K. Maruyama, A. Sato, and K. Seto, “Pedestrian-movement predictionbased on mixed markov-chain model,” in19th ACM SIGSPATIAL InternationalSymposium on Advances in Geographic Information Systems, ACM-GIS 2011, November1-4,2011,Chicago,IL, USA, Proceedings, I. F. Cruz, D. Agrawal, C. S.Jensen, E. Ofek, and E. Tanin, Eds.ACM, 2011, pp. 25–33. [Online]. Available:https://doi.org/10.1145/2093973.209397934
[8] H. Hsieh, C. Li, and X. Gao, “T-gram: A time-aware language model to predict humanmobility,” inProceedings of the Ninth International Conference on Web and SocialMedia, ICWSM 2015, University of Oxford, Oxford, UK, May 26-29, 2015, M. Cha,C. Mascolo, and C. Sandvig, Eds. AAAI Press, 2015, pp. 614–617. [Online]. Available:http://www.aaai.org/ocs/index.php/ICWSM/ICWSM15/paper/view/10559
[9] G. Gid ́ofalvi and F. Dong, “When and where next: individual mobility prediction,”inProceedings of the First ACM SIGSPATIAL International Workshop on MobileGeographic Information Systems, MobiGIS 2012, Redondo Beach, CA, USA, November6, 2012, C. Chow and S. Shekhar, Eds.ACM, 2012, pp. 57–64. [Online]. Available:https://doi.org/10.1145/2442810.2442821
[10] M. Dou, T. He, H. Yin, X. Zhou, Z. Chen, and B. Luo, “Predicting passengers inpublic transportation using smart card data,” inDatabases Theory and Applications -26th Australasian Database Conference, ADC 2015, Melbourne, VIC, Australia, June4-7, 2015. Proceedings, ser. Lecture Notes in Computer Science, M. A. Sharaf, M. A.Cheema, and J. Qi, Eds., vol. 9093.Springer, 2015, pp. 28–40. [Online]. Available:https://doi.org/10.1007/978-3-319-19548-33
[11] S. Foell, S. Phithakkitnukoon, G. Kortuem, M. Veloso, and C. Bento, “Catchme if you can:Predicting mobility patterns of public transport users,” in17thInternational IEEE Conference on Intelligent Transportation Systems, ITSC 2014,Qingdao, China, October 8-11, 2014. IEEE, 2014, pp. 1995–2002. [Online]. Available:https://doi.org/10.1109/ITSC.2014.6957997
[12] Z. Zhao, H. N. Koutsopoulos, and J. Zhao, “Individual mobility prediction using transitsmart card data,”Transportation research part C: emerging technologies, vol. 89, pp. 19–34,2018.
[13] N. Lathia, C. Smith-Clarke, J. Froehlich, and L. Capra, “Individuals among commuters:Building personalised transport information services from fare collection systems,”Pervasive Mob. Comput., vol. 9, no. 5, pp. 643–664, 2013. [Online]. Available:https://doi.org/10.1016/j.pmcj.2012.10.007
[14] P. Midgley, “Bicycle-sharing schemes: enhancing sustainable mobility in urban areas,”United Nations, Department of Economic and Social Affairs, vol. 8, pp. 1–12, 2011.
[15] P. DeMaio, “Bike-sharing: History, impacts, models of provision, and future,”Journal ofpublic transportation, vol. 12, no. 4, p. 3, 2009.
[16] L. Zhang, J. Zhang, Z.-y. Duan, and D. Bryde, “Sustainable bike-sharing systems: charac-teristics and commonalities across cases in urban china,”Journal of Cleaner Production,vol. 97, pp. 124–133, 2015.
[17] E. C^ome and L. Oukhellou, “Model-based count series clustering for bike sharingsystem usage mining: A case study with the v ́elib’ system of paris,”ACM Trans.Intell. Syst. Technol., vol. 5, no. 3, pp. 39:1–39:21, 2014. [Online]. Available:https://doi.org/10.1145/2560188
[18] P. Vogel and D. C. Mattfeld, “Strategic and operational planning of bike-sharing systemsby data mining - A case study,” inComputational Logistics - Second InternationalConference, ICCL 2011, Hamburg, Germany, September 19-22, 2011. Proceedings, ser.Lecture Notes in Computer Science, J. B ̈ose, H. Hu, C. Jahn, X. Shi, R. Stahlbock,and S. Voß, Eds., vol. 6971.Springer, 2011, pp. 127–141. [Online]. Available:https://doi.org/10.1007/978-3-642-24264-910
[19] P. Midgley, “The role of smart bike-sharing systems in urban mobility,”Journeys, vol. 2,no. 1, pp. 23–31, 2009.
[20] Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, and T. Li, “Forecastingfine-grained air quality based on big data,” inProceedings of the 21th ACM SIGKDDInternational Conference on Knowledge Discovery and Data Mining, Sydney, NSW,Australia, August 10-13, 2015, L. Cao, C. Zhang, T. Joachims, G. I. Webb, D. D.Margineantu, and G. Williams, Eds. ACM, 2015, pp. 2267–2276. [Online]. Available:https://doi.org/10.1145/2783258.2788573
[21] Y. Li, Y. Zheng, H. Zhang, and L. Chen, “Traffic prediction in a bike-sharing system,” inProceedings of the 23rd SIGSPATIAL International Conference on Advances in GeographicInformation Systems, Bellevue, WA, USA, November 3-6, 2015, J. Bao, C. Sengstock,M. E. Ali, Y. Huang, M. Gertz, M. Renz, and J. Sankaranarayanan, Eds. ACM, 2015,pp. 33:1–33:10. [Online]. Available: https://doi.org/10.1145/2820783.2820837
[22] B. Pan, Y. Zheng, D. Wilkie, and C. Shahabi, “Crowd sensing of traffic anomaliesbased on human mobility and social media,” in21st SIGSPATIAL InternationalConference on Advances in Geographic Information Systems, SIGSPATIAL 2013,Orlando, FL, USA, November 5-8, 2013, C. A. Knoblock, M. Schneider, P. Kr ̈oger,J. Krumm, and P. Widmayer, Eds.ACM, 2013, pp. 334–343. [Online]. Available:https://doi.org/10.1145/2525314.2525343
[23] J. Lin, T. Yang, and Y. Chang, “A hub location inventory model for bicycle sharingsystem design: Formulation and solution,”Comput. Ind. Eng., vol. 65, no. 1, pp. 77–86,2013. [Online]. Available: https://doi.org/10.1016/j.cie.2011.12.006
[24] H. Durrant-Whyte, N. Roy, and P. Abbeel, “Load balancing for mobility-on-demand sys-tems,” 2012.
[25] Y. Liu, X. Yan, Y. Wang, Z. Yang, and J. Wu, “Grid mapping for spatial pattern analysesof recurrent urban traffic congestion based on taxi gps sensing data,”Sustainability, vol. 9,no. 4, p. 533, 2017.
[26] X. Tian and B. Zheng, “Using smart card data to model commuters’ responsesupon unexpected train delays,” inIEEE International Conference on Big Data, BigData 2018, Seattle, WA, USA, December 10-13, 2018, N. Abe, H. Liu, C. Pu,X. Hu, N. K. Ahmed, M. Qiao, Y. Song, D. Kossmann, B. Liu, K. Lee, J. Tang,J. He, and J. S. Saltz, Eds.IEEE, 2018, pp. 831–840. [Online]. Available:https://doi.org/10.1109/BigData.2018.8622233
[27] J. Zhang, X. Pan, M. Li, and P. S. Yu, “Bicycle-sharing system analysis and tripprediction,” inIEEE 17th International Conference on Mobile Data Management,MDM 2016, Porto, Portugal, June 13-16, 2016, C. Chow, P. P. Jayaraman, andW. Wu, Eds.IEEE Computer Society, 2016, pp. 174–179. [Online]. Available:https://doi.org/10.1109/MDM.2016.35
[28] Z. Zhao, H. N. Koutsopoulos, and J. Zhao, “Discovering latent activity patterns fromtransit smart card data: A spatiotemporal topic model,”Transportation Research Part C:Emerging Technologies, vol. 116, p. 102627, 2020.
[29] M. Mishra and M. Srivastava, “A view of artificial neural network,” in2014 InternationalConference on Advances in Engineering & Technology Research (ICAETR-2014). IEEE,2014, pp. 1–3.
[30] S. Hochreiter and J. Schmidhuber, “Long short-term memory,”Neural Comput., vol. 9,no. 8, pp. 1735–1780, 1997. [Online]. Available: https://doi.org/10.1162/neco.1997.9.8.1735
[31] M. A. Hearst, “Trends & controversies: Support vector machines,”IEEE Intell. Syst.,vol. 13, no. 4, pp. 18–28, 1998. [Online]. Available: https://doi.org/10.1109/5254.708428
[32] L. Breiman, “Random forests,”Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001. [Online].Available: https://doi.org/10.1023/A:101093340432438