Data Mining on Open Public Transit Data for Transportation Analytics During Pre-COVID-19 Era and COVID-19 Era

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1263)


As the urbanization of the world continues and the population of cities rise, the issue of how to effectively move all these people around the city becomes much more important. In order to use the limited space in a city most efficiently, many cities and their residents are increasingly looking towards public transportation as the solution. In this paper, we focus on the public bus system as the primary form of public transit. In particular, we examine open public transit data for the Canadian city of Winnipeg. We mine and conduct transportation analytics on data prior to the coronavirus disease 2019 (COVID-19) situation and during the COVID-19 situation. By discovering how often and when buses were reported to be too full to take on new passengers at bus stops, analysts can get an insight of which routes and destinations are the busiest. This information would help decision makers make appropriate actions (e.g., add extra bus for those busiest routines). This results in a better and more convenient transit system towards a smart city. Moreover, during the COVID-19 era, it leads to additional benefits of contributing to safer buses services and bus waiting experiences while maintaining social distancing.


Data mining Open data Data analytics Transportation analytics Public transit analytics COVID-19 



This work is partially supported by NSERC (Canada) and University of Manitoba.


  1. 1.
    Statistics Canada: Commuters using sustainable transportation in census metropolitan areas. 2016 census in brief (2017).
  2. 2.
    Consolo, S., Petrillo, U.F.: A framework for the efficient collection of big data from online social networks. In: INCoS 2014, pp. 34–41 (2014)Google Scholar
  3. 3.
    Leung, C.K.: Big data analysis and mining. In: Advanced Methodologies and Technologies in Network Architecture, Mobile Computing, and Data Analytics, pp. 15–27 (2019)Google Scholar
  4. 4.
    Mai, M., Leung, C.K., Choi, J.M.C., Kwan, L.K.R.: Big data analytics of Twitter data and its application for physician assistants: who is talking about your profession in Twitter? In: Data Management and Analysis, pp. 17–32 (2020)Google Scholar
  5. 5.
    Souza, J., Leung, C.K., Cuzzocrea, A.: An innovative big data predictive analytics framework over hybrid big data sources with an application for disease analytics. In: AINA 2020. AISC, vol. 1151, pp. 669–680 (2020)Google Scholar
  6. 6.
    Leung, C.K., Braun, P., Cuzzocrea, A.: AI-based sensor information fusion for supporting deep supervised learning. Sensors 19(6), 1345:1–1345:12 (2019)CrossRefGoogle Scholar
  7. 7.
    Lin, J., Liao, S., Leu, F.: A novel bounded-error piecewise linear approximation algorithm for streaming sensor data in edge computing. In: INCoS 2019. AISC, vol. 1035, pp. 123–132 (2019)Google Scholar
  8. 8.
    Amato, F., Cozzolino, G., Moscato, F., Xhafa, F.: Semantic analysis of social data streams. In: INCoS 2018. LNDECT, vol. 23, pp. 59–70 (2018)Google Scholar
  9. 9.
    Leung, C.K., Tanbeer, S.K., Cameron, J.J.: Interactive discovery of influential friends from social networks. Soc. Network Anal. Min. 4(1), 154:1–154:13 (2014)Google Scholar
  10. 10.
    Tanbeer, S.K., Leung, C.K., Cameron, J.J.: Interactive mining of strong friends from social networks and its applications in e-commerce. JOCEC 24(2–3), 157–173 (2014)Google Scholar
  11. 11.
    Audu, A.A., Cuzzocrea, A., Leung, C.K., MacLeod, K.A., Ohin, N.I., Pulgar-Vidal, N.C.: An intelligent predictive analytics system for transportation analytics on open data towards the development of a smart city. In: CISIS 2019. AISC, vol. 993, pp. 224–236 (2019)Google Scholar
  12. 12.
    Leung, C.K., Braun, P., Hoi, C.S.H., Souza, J., Cuzzocrea, A.: Urban analytics of big transportation data for supporting smart cities. In: DaWaK 2019. LNCS, vol. 11708, pp. 24–33 (2019)Google Scholar
  13. 13.
    Kolici, V., Xhafa, F., Barolli, L., Lala, A.: Scalability, memory issues and challenges in mining large data sets. In: INCoS 2014, pp. 268–273 (2014)Google Scholar
  14. 14.
    Lakshmanan, L.V.S., Leung, C.K., Ng, R.T.: The segment support map: scalable mining of frequent itemsets. ACM SIGKDD Explor. 2(2), 21–27 (2000)CrossRefGoogle Scholar
  15. 15.
    Leung, C.K.: Frequent itemset mining with constraints. In: Encyclopedia of Database Systems, 2nd edn., pp. 1531–1536 (2018)Google Scholar
  16. 16.
    Perner, P.: The study of the internal mitochondrial movement of the cells by data mining with prototype-based classification. In: INCoS 2014, pp. 262–267 (2014)Google Scholar
  17. 17.
    Zhang, J., Li, J.: Retail commodity sale forecast model based on data mining. In: INCoS 2016, pp. 307–310 (2016)Google Scholar
  18. 18.
    Fujihara, A.: Proposing a blockchain-based open data platform and its decentralized oracle. In: INCoS 2019. AISC, vol. 1035, pp. 190–201 (2019)Google Scholar
  19. 19.
    Zhao, K., Khryashchev, D., Vo, H.: Predicting taxi and Uber demand in cities: approaching the limit of predictability. IEEE TKDE (2019). Scholar
  20. 20.
    Yamaguchi, T., Mansur, A.S., Mine, T.: Prediction of bus delay over intervals on various kinds of routes using bus probe data. In: IEEE/ACM BDCAT 2018, pp. 97–106 (2018)Google Scholar
  21. 21.
    Liu, T., Ma, J., Guan, W., Song, Y., Niu, H.: Bus arrival time prediction based on the k-nearest neighbor method. In: CSO 2012, pp. 480–483 (2012)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.University of ManitobaWinnipegCanada

Personalised recommendations