Abstract
The accuracy of vehicle arrival predictions affects every aspect of transit performance including ridership, reliability, and operating costs. Kalman Filter algorithms have been shown to provide more accurate predictions than simple regression. This paper presents a scalable framework to implement Kalman Filters on an entire bus network running live. A novel architecture to cache the data and weight inputs based on current operating conditions is presented. All the necessary features to support Kalman Filter predictions are described and implemented in TheTransitClock, an open-source prediction tool. TheTransitClock was deployed on the Metro Transit bus network in the Minneapolis-St. Paul region for one month. The Kalman Filter algorithm predicted the arrivals of over 900 buses on 167 routes. The accuracy and sensitivity of the method was compared to a schedule-based prediction method used in practice. The Kalman Filter was found to provide more accurate and stable predictions, especially in times and places that are difficult to predict with conventional methods.
This is a preview of subscription content, log in via an institution to check access.
Notes
Although for the implementation, a prediction method based on simple regression was used.
References
Achar A et al (2019) Bus arrival time prediction: a spatial Kalman filter approach. IEEE Trans Intell Transp Syst 21(3):1298–1307
APTA (2018) Factbook. American Public Transportation Association, Washington D.C
Bartholdi III, John J, Eisenstein DD (2012) A self-coördinating bus route to resist bus bunching. Transp Res B Methodol 46(4):481–491
Berrebi SJ, Watkins KE, Laval JA (2015) A real-time bus dispatching policy to minimize passenger wait on a high frequency route. Transp Res B Methodol 81:377–389
Berrebi SJ, Hans E, Chiabaut N, Leclercq L, Laval JA, Watkins K, E. (2018a) Comparing bus holding methods with and without real-time predictions. Transp Res Part C Emerg Technol 87:197–211
Berrebi SJ, Crudden S, Watkins K, E. (2018b) Translating research to practice: implementing real-time control on high-frequency transit routes. Transp Res A Policy Pract 111:213–226
Brakewood C, Macfarlane GS, Watkins K (2015) The impact of real-time information on bus ridership in New York City. Transp Res Part C Emerg Technol 53:59–75
Cathey FW, Dailey DJ (2001) Arrival/departure prediction using the tri-met AVL system. Department of Electrical Engineering, University of Washington
Cathey FW, Dailey DJ (2003) A prescription for transit arrival/departure prediction using automatic vehicle location data. Transp Res Part C Emerg Technol 11(3–4):241–264
Cats O, Jenelius E (2014) Dynamic vulnerability analysis of public transport networks: mitigation effects of real-time information. Netw Spat Econ 14(3–4):435–463
Cats O, Loutos G (2016a) Real-time bus arrival information system: an empirical evaluation. J Intell Transp Syst 20(2):138–151
Cats O, Loutos G (2016b) Evaluating the added-value of online bus arrival prediction schemes. Transp Res A Policy Pract 86:35–55
Cats O, Koutsopoulos HN, Burghout W, Toledo T (2011) Effect of real-time transit information on dynamic path choice of passengers. Transp Res Rec 2217(1):46–54
Chen M, Liu X, Xia J (2005) Dynamic prediction method with schedule recovery impact for bus arrival time. Transp Res Rec 1923(1):208–217
Chien SI-J, Chen M, Liu X (2003) Use of Neural Network/Dynamic Algorithms to Predict Bus Travel Times Under Congested Conditions. No. FHWA-NJ-2003–019. https://trid.trb.org/view/743260
Daganzo CF, Pilachowski J (2011) Reducing bunching with bus-to-bus cooperation. Transp Res B Methodol 45(1):267–277
Dailey DJ, Maclean SD, Cathey FW, Wall ZR (2001) Transit vehicle arrival prediction: algorithm and large-scale implementation. Transp Res Rec 1771(1):46–51
Dhivyabharathi B, Anil Kumar B, Vanajakshi L (2016) Real time bus arrival time prediction system under Indian traffic condition. 2016 IEEE International Conference on Intelligent Transportation Engineering (ICITE). IEEE
Ding Y (2000) The Development and Application of Dynamic Models for Predicting Transit Arrival Times. No. AAT 9959684 (UMI order#)
Dueker K, Kimpel TJ, Strathman JG (2001) Development of a statistical algorithm for the real-time prediction of transit vehicle arrival times under adverse conditions, Portland State University, Center for urban Studies. https://pdxscholar.library.pdx.edu/cgi/viewcontent.cgi?article=1075&context=cus_pubs
Fan W, Gurmu Z (2015) Dynamic travel time prediction models for buses using only GPS data. Int J Transp Sci Technol 4(4):353–366
Ferris B, Watkins K, Borning A (2010) OneBusAway: results from providing real-time arrival information for public transit. Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. ACM
Kalman RE (1960) A new approach to linear filtering and prediction problems. J Basic Eng 82(1):35–45
Kerr D (2018) Retrieved on May 6, 2021, from https://www.metrotransit.org/rail-lines-set-records-as-metro-transit-ridership-tops-819-million-in-2017
Kumar BA, Jairam R, Arkatkar SS, Vanajakshi L (2019) Real time bus travel time prediction using k-NN classifier. Transp Lett 11(7):362–372
Padmanaban RPS, Divakar K, Vanajakshi L, Subramanian SC (2010) Development of a real-time bus arrival prediction system for Indian traffic conditions. IET Intell Transp Syst 4(3):189–200
Reinhoudt EM, Velastin SA (1997) A dynamic predicting algorithm for estimating bus arrival time. IFAC Proceedings Volumes 30(8):1225–1228
Shalaby A, Farhan A (2004) Prediction model of bus arrival and departure times using AVL and APC data. J Public Transp 7(1):3
Shalaik B (2012) Software for the control and analysis of public transport systems. Diss. National University of Ireland Maynooth
Tang L, Thakuriah PV (2012) Ridership effects of real-time bus information system: a case study in the City of Chicago. Transp Res Part C Emerg Technol 22:146–161
Verbich D, Diab E, El-Geneidy A (2016) Have they bunched yet? An exploratory study of the impacts of bus bunching on dwell and running times. Public Transport 8(2):225–242
Vu NH (2007) Bus real-time arrival prediction using statistical pattern recognition technique. Diss. Carleton University
Watkins KE et al (2011) Where is my bus? Impact of mobile real-time information on the perceived and actual wait time of transit riders. Transp Res A Policy Pract 45(8):839–848
Yu B, Yang Z-Z, Chen K, Yu B (2010) Hybrid model for prediction of bus arrival times at next station. J Adv Transp 44(3):193–204
Zaki M et al (2013) Online bus arrival time prediction using hybrid neural network and Kalman filter techniques. Int J Modern Eng Res 3(4):2035–2041
Zhang L, Li J-Q, Zhou K, Gupta SD, Li M, Zhang W-B, Miller MA, Misener JA (2011) Traveler information tool with integrated real-time transit information and multimodal trip planning: design and implementation. Transp Res Rec 2215(1):1–10
Acknowledgments
The authors wish to thank Metro Transit for funding this project and supporting the development of TheTransitClock. We are particularly grateful to Laura Matson, Joey Reid, Ben Rajkowski, and Eric Lind for helping navigate the data and understand how service is delivered. We also thank Raphael Barcham, Sheldon Brown, and Lenny Caraballo who participated in the implementation of TheTransitClock. Finally, the authors wish to thank the University of Arkansas at Little Rock and especially the late Yupo Chan who led the Chan Wui Rising Star Workshop.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Crudden, S.Ó., Berrebi, S. An Open-Source Framework to Implement Kalman Filter Bus Arrival Predictions. Netw Spat Econ 23, 429–443 (2023). https://doi.org/10.1007/s11067-021-09541-w
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11067-021-09541-w