Abstract
Public transit is one of the first things that come to mind when someone talks about “smart cities.” As a result, many technologies, applications, and infrastructure have already been deployed to bring the promise of the smart city to public transportation. Most of these have focused on answering the question, “When will my bus arrive?”; little has been done to answer the question, “How full will my next bus be?” which also dramatically affects commuters’ quality of life. In this article, we consider the bus fullness problem. In particular, we propose two different formulations of the problem, develop multiple predictive models, and evaluate their accuracy using data from the Pittsburgh region. Our predictive models consistently outperform the baselines (by up to 8 times).
- Vito Albino, Umberto Berardi, and Rosa Maria Dangelico. 2015. Smart cities: Definitions, dimensions, performance, and initiatives. J. Urb. Technol. 22, 1 (2015), 3--21.Google Scholar
Cross Ref
- Kittelson 8 Associates, Federal Transit Administration, Transit Cooperative Research Program, and Transit Development Corporation. 2003. Transit Capacity and Quality of Service Manual. Number 100. Transportation Research Board.Google Scholar
- Marco Balduini, Marco Brambilla, Emanuele Della Valle, Christian Marazzi, Tahereh Arabghalizi, Behnam Rahdari, and Michele Vescovi. 2018. Models and practices in urban data science at scale. Big Data Res. (Aug. 2018). DOI:https://doi.org/10.1016/j.bdr.2018.04.003Google Scholar
- Anthony G. Barnston. 1992. Correspondence among the correlation, RMSE, and Heidke forecast verification measures; refinement of the Heidke score. Weath. Forecast. 7, 4 (1992), 699--709.Google Scholar
Cross Ref
- Yu Bin, William H. K. Lam, and Mei Lam Tam. 2011. Bus arrival time prediction at bus stop with multiple route. Transport. Res. Part C: Emerg. Technol. 19, 6 (Dec. 2011), 1157--1170.Google Scholar
- Yu Bin, Yang Zhongzhen, and Yao Baozhen. 2006. Bus arrival time prediction using support vector machines. J. Intell. Transport. Syst. 10, 4 (Dec. 2006), 151--158.Google Scholar
- J. Martin Bland and Douglas G. Altman. 1996. Statistics notes: Measurement error. BMJ 312, 7047 (1996), 1654.Google Scholar
- Leo Breiman. 2001. Random forests. Mach. Learn. 45, 1 (Oct. 2001), 5--32.Google Scholar
Digital Library
- Colin A. Cameron and Pravin K. Trivedi. 2001. Essentials of count data regression. Compan. Theoret. Economet. 331 (2001).Google Scholar
- National Operational Hydrologic Remote Sensing Center. 2019. National Weather Service Climate of Pittsburgh. Retrieved from https://www.nohrsc.noaa.gov/interactive/.Google Scholar
- Steven I-Jy Chien, Yuqing Ding, and Chienhung Wei. 2002. Dynamic bus arrival time prediction with artificial neural networks. J. Transport. Eng. 128, 5 (Sept. 2002), 429--438.Google Scholar
- Hafedh Chourabi, Taewoo Nam, Shawn Walker, J. Ramon Gil-Garcia, Sehl Mellouli, Karine Nahon, Theresa A. Pardo, and Hans Jochen Scholl. 2012. Understanding smart cities: An integrative framework. In Proceedings of the 45th Hawaii International Conference on System Sciences. IEEE, 2289--2297.Google Scholar
- Pennsylvania State Climatologist. 2018--2019. PASC IDA Data. Retrieved from http://climate.psu.edu/data/ida/.Google Scholar
- Kate Crawford. 2013. The Hidden Biases in Big Data. Retrieved from https://hbr.org/2013/04/the-hidden-biases-in-big-data.Google Scholar
- Google Developers. 2016. General Transit Feed Specification (Static Overview). Retrieved from https://developers.google.com/transit/gtfs/.Google Scholar
- Google Developers. 2020. Keras. Retrieved from https://www.tensorflow.org/guide/keras.Google Scholar
- Donald Erdman, Laura Jackson, and Arthur Sinko. 2008. Zero-inflated Poisson and zero-inflated negative binomial models using the COUNTREG procedure. In Proceedings of the SAS Global Forum, Vol. 2008. 322--2008.Google Scholar
- François Chollet. 2017. Deep Learning with Python (1st ed.). Manning Publications Co., USA.Google Scholar
Digital Library
- Vikash V. Gayah, Zhengyao Yu, Jonathan S. Wood, Mineta National Transit Research Consortium, et al. 2016. Estimating uncertainty of bus arrival times and passenger occupancies. Technical Report. Mineta National Transit Research Consortium.Google Scholar
- Irving John Good. 1952. Rational decisions. J. Roy. Stat. Soc. Series B (Methodol.) 14, 1 (1952), 107--114.Google Scholar
Cross Ref
- Taylah Hasaballah. 2019. Grab a seat and be on time with new transit updates on Google Maps. Retrieved from https://www.blog.google/products/maps/grab-seat-and-be-time-new-transit-updates-google-maps/.Google Scholar
- Taylah Hasaballah. 2019. Transit crowdedness trends from around the world, according to Google Maps. Retrieved from https://www.blog.google/products/maps/transit-crowdedness-trends-around/.Google Scholar
- Jeff Heaton. 2008. Introduction to Neural Networks with Java. Heaton Research, Inc.Google Scholar
Digital Library
- Avi Herbon and Yuval Hadas. 2015. Determining optimal frequency and vehicle capacity for public transit routes: A generalized newsvendor model. Transport. Res. Part B: Methodol. 71 (2015), 85--99.Google Scholar
- Moovit Inc. 2012. MoovIT. Retrieved from https://moovitapp.com.Google Scholar
- Scikit learn Developers. 2007--2018. Scikit-learn models. Retrieved from https://scikit-learn.org/.Google Scholar
- Zheng Li and David A. Hensher. 2013. Crowding in public transport: A review of objective and subjective measures. J. Pub. Transport. 16, 2 (2013), 6.Google Scholar
Cross Ref
- Yanchi Liu, Chuanren Liu, Nicholas Jing Yuan, Lian Duan, Yanjie Fu, Hui Xiong, Songhua Xu, and Junjie Wu. 2014. Exploiting heterogeneous human mobility patterns for intelligent bus routing. In Proceedings of the IEEE International Conference on Data Mining. IEEE, 360--369.Google Scholar
- Yanchi Liu, Chuanren Liu, Nicholas Jing Yuan, Lian Duan, Yanjie Fu, Hui Xiong, Songhua Xu, and Junjie Wu. 2017. Intelligent bus routing with heterogeneous human mobility patterns. Knowl. Inf. Syst. 50, 2 (2017), 383--415.Google Scholar
Digital Library
- Yan Lyu, Chi-Yin Chow, Victor C. S. Lee, Joseph K. Y. Ng, Yanhua Li, and Jia Zeng. 2019. CB-planner: A bus line planning framework for customized bus systems. Transport. Res. Part C: Emerg. Technol. 101 (2019), 233--253.Google Scholar
Cross Ref
- Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schutze. 2008. Introduction to Information Retrieval. Cambridge University Press.Google Scholar
Digital Library
- Port Authority of Allegheny County. 2018. Port Authority of Allegheny County Annual Service Report 2018.Google Scholar
- University of Pittsburgh. 2016. Pitt Smart Living Project.Retrieved from https://pittsmartliving.org/.Google Scholar
- Pittsburgh Weather Forecast Office. 2018--2019. Interactive Snow Information. Retrieved from https://w2.weather.gov/climate/xmacis.php?wfo=pbz.Google Scholar
- R. H. Oldfield and P. H. Bly. 1988. An analytic investigation of optimal bus size. Transport. Res. Part B: Methodol. 22, 5 (1988), 319--337.Google Scholar
- Joseph N. Prashker. 1979. Direct analysis of the perceived importance of attributes of reliability of travel modes in urban travel. Transportation 8, 4 (Dec. 1979), 329--346.Google Scholar
- Amer Shalaby and Ali Farhan. 2004. Prediction model of bus arrival and departure times using AVL and APC data. J. Pub. Transport. 7, 1 (2004), 3.Google Scholar
Cross Ref
- Aaron Steinfeld, John Zimmerman, Anthony Tomasic, Daisy Yoo, and Rafae Dar Aziz. 2011. Mobile transit information from universal design and crowdsourcing. Transport. Res. Rec. 2217, 1 (2011), 95--102.Google Scholar
- Transit. 2012. TransitApp. Retrieved from https://transitapp.com.Google Scholar
- Yu Wei and Mu-Chen Chen. 2012. Forecasting the short-term metro passenger flow with empirical mode decomposition and neural networks. Transport. Res. Part C: Emerg. Technol. 21, 1 (2012), 148--162.Google Scholar
Cross Ref
- Wen xia Sun, Ti Song, and Hai Zhong. 2009. Study on bus passenger capacity forecast based on regression analysis including time series. In Proceedings of the International Conference on Measuring Technology and Mechatronics Automation, Vol. 2. IEEE, 381--384.Google Scholar
- Zhang Xiong, Hao Sheng, WenGe Rong, and Dave E. Cooper. 2012. Intelligent transportation systems for smart cities: A progress review. Sci. China Inf. Sci. 55, 12 (2012), 2908--2914.Google Scholar
Cross Ref
- Menno Yap, Oded Cats, and Bart van Arem. 2018. Crowding valuation in urban tram and bus transportation based on smart card data. Transportmet. A: Transport Sci. (2018), 1--20.Google Scholar
- Dell Zhang, Jun Wang, and Xiaoxue Zhao. 2015. Estimating the uncertainty of average F1 scores. In Proceedings of the 2015 International Conference on The Theory of Information Retrieval. 317--320.Google Scholar
Digital Library
- Jun Zhang, Dayong Shen, Lai Tu, Fan Zhang, Chengzhong Xu, Yi Wang, Chen Tian, Xiangyang Li, Benxiong Huang, and Zhengxi Li. 2017. A real-time passenger flow estimation and prediction method for urban bus transit systems. IEEE Trans. Intell. Transport. Syst. 18, 11 (2017), 3168--3178.Google Scholar
Digital Library
- Wenfeng Zhang, Zhongke Shi, and Zhiyong Luo. 2008. Prediction of urban passenger transport based-on wavelet SVM with quantum-inspired evolutionary algorithm. In Proceedings of the IEEE International Joint Conference on Neural Networks and the IEEE World Congress on Computational Intelligence. IEEE, 1509--1514.Google Scholar
Index Terms
Data-driven Bus Crowding Prediction Models Using Context-specific Features
Recommendations
A Smart City System Architecture based on City-level Data Exchange Platform
With the development of information technology and urban planning, there is a higher demand for the life quality of city people. In order to meet the demand for urban facilitation and intelligence, the research on smart city system has been widely ...
Data Driven Maturity Model for Assessing Smart Cities
ICSDE'18: Proceedings of the 2nd International Conference on Smart Digital EnvironmentSmart cities provide the ability to improve the quality of the citizen's life. Transformation into a smart city consists of defining the way ICT (Information and Communication Technologies) can be used to improve the weaker aspects of the city and ...
Gaussian process-based predictive modeling for bus ridership
UbiComp '13 Adjunct: Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publicationThe dynamics of a city are characterized, among others, by the traveling patterns of its dwellers. Accurate knowledge of human mobility patterns would have applications, e.g., in urban design, in the optimization of public transportation operating costs,...






Comments