Data-Driven Metro Train Crowding Prediction Based on Real-Time Load Data
The DOI matches its Crossref record; 28 of the 28 references it cites were found in a registry or an index.
Abstract
This paper formulates the car-specific metro train crowding prediction problem based on real-time load data and evaluates the performance of several data-driven prediction methods (lasso, stepwise regression, and boosted tree ensembles). Two variants of the prediction problem are considered: 1) train-centered prediction, focusing on in-vehicle crowding information provision and 2) station-centered prediction focusing on crowding information provision at stations. The methodology is applied to a metro line in Stockholm, Sweden. The prediction accuracy is evaluated with respect to absolute passenger loads and discrete crowding levels. When available, predictions with real-time load data significantly outperform historical averages, with accuracy improvements varying in magnitude across target stations and train cars depending on load variability. The results suggest that the real-time crowding information can be provided sufficiently early to influence travelers’ route, train, and car choices, in order to reduce in-vehicle crowding.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It is shown that real-time load data significantly improve the prediction accuracy (from between 70% and 90% to between 80% and 95%).”
From Sensing Technologies for Crowd Management, Adaptation, and Information Dissemination in Public Transportation Systems: A Review (2023) · cites this paper as [67]
Citations
Cites
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970
The Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Understanding attitudes towards public transport and private car: A qualitative study
Beirão, G., & Sarsfield Cabral, J. A. (2007) · Transport Policy · doi:10.1016/j.tranpol.2007.04.009 · Cited by 1,198 · cited 1×
“Crowding is associated with negative effects on traveler satisfaction and wellbeing, including stress, anxiety, threat to personal safety and security, and loss of productivity due to lack of seating space [1], [2].”
BackgroundShort-term traffic forecasting: where we are and where we’re going
Vlahogianni, E. I., Karlaftis, M. G., & Golias, J. C. (2014) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2014.01.005 · Cited by 1,132 · cited 1×
“series analysis, regression modeling, clustering and pattern recognition algorithms [23].”
MethodTransit capacity and quality of service manual
Hunter-Zaworski, K. (2003) · Cited by 711
Tirachini, A., Hensher, D. A., & Rose, J. M. (2013) · Transportation Research Part A: Policy and Practice · doi:10.1016/j.tra.2013.06.005 · Cited by 385 · cited 1×
“Crowding is associated with negative effects on traveler satisfaction and wellbeing, including stress, anxiety, threat to personal safety and security, and loss of productivity due to lack of seating space [1], [2].”
BackgroundWatkins, K. E., Ferris, B., Borning, A., Rutherford, G. S., & Layton, D. (2011) · Transportation Research Part A: Policy and Practice · doi:10.1016/j.tra.2011.06.010 · Cited by 384
Twenty Years of Rail Crowding Valuation Studies: Evidence and Lessons from British Experience
Wardman, M., & Whelan, G. (2011) · Transport Reviews · doi:10.1080/01441647.2010.519127 · Cited by 292 · cited 1×
“Studies show that travelers’ perceived travel times increase with the level of crowding [3]–[5].”
BackgroundDynamic at-stop real-time information displays for public transport: effects on customers
Dziekan, K., & Kottenhoff, K. (2007) · Transportation Research Part A: Policy and Practice · doi:10.1016/j.tra.2006.11.006 · Cited by 278 · cited 1×
“RTI systems have been shown to have positive effects on perceived waiting times, safety and security, impacts of service disruptions, and general satisfaction [17]–[20].”
BackgroundModeling and simulation of passenger alighting and boarding movement in Beijing metro stations
Zhang, Q., Han, B., & Li, D. (2008) · Transportation Research Part C: Emerging Technologies · doi:10.1016/j.trc.2007.12.001 · Cited by 223 · cited 1×
“Crowding also affects vehicle dwell times at stations as well as passenger waiting times, which increases the variability in headways and reduces reliability [6], [7].”
BackgroundCats, O., & Jenelius, E. (2014) · Networks and Spatial Economics · doi:10.1007/s11067-014-9237-7 · Cited by 187
Self-citationRaveau, S., Guo, Z., Muñoz, J. C., & Wilson, N. H. M. (2014) · Transportation Research Part A: Policy and Practice · doi:10.1016/j.tra.2014.05.010 · Cited by 177
Eboli, L., & Mazzulla, G. (2015) · Public Transport · doi:10.1007/s12469-014-0096-x · Cited by 165 · cited 1×
“RTI systems have been shown to have positive effects on perceived waiting times, safety and security, impacts of service disruptions, and general satisfaction [17]–[20].”
BackgroundA study of crowding effects at the Hong Kong light rail transit stations
Lam, W. H. K., Cheung, C.-Y., & Lam, C. F. (1999) · Transportation Research Part A: Policy and Practice · doi:10.1016/s0965-8564(98)00050-0 · Cited by 158 · cited 1×
“Crowding also affects vehicle dwell times at stations as well as passenger waiting times, which increases the variability in headways and reduces reliability [6], [7].”
BackgroundA real-time passenger flow estimation and prediction method for urban bus transit systems
Zhang, J., Shen, D., Tu, L., Zhang, F., Xu, C., Wang, Y., Tian, C., Li, X., Huang, B., & Li, Z. (2017) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2686877 · Cited by 130 · cited 1×
“Another approach proposes a combination of historical pattern recognition and Kalman filtering for short-term prediction of bus loads based on real-time AFC and AVL data [27].”
BackgroundDoes crowding affect the path choice of metro passengers?
Kim, K. M., Hong, S., Ko, S.-J., & Kim, D. (2015) · Transportation Research Part A Policy and Practice · doi:10.1016/j.tra.2015.04.023 · Cited by 122 · cited 1×
“Studies show that travelers’ perceived travel times increase with the level of crowding [3]–[5].”
BackgroundAn Integrated Framework to Predict Bus Travel Time and Its Variability Using Traffic Flow Data
Mazloumi, E., Rose, G., Currie, G., & Sarvi, M. (2011) · Journal of Intelligent Transportation Systems · doi:10.1080/15472450.2011.570109 · Cited by 74 · cited 1×
“Several methods for short-term arrival time prediction based on various assumptions about data availability have been proposed, e.g., [14]–[16].”
Why do passengers choose a specific car of a metro train during the morning peak hours?
Kim, H.-M., Kwon, S., Wu, S. K., & Sohn, K. (2014) · Transportation Research Part A Policy and Practice · doi:10.1016/j.tra.2014.02.015 · Cited by 62
A mesoscopic transit assignment model including real-time predictive information on crowding
Nuzzolo, A., Crisalli, U., Comi, A., & Rosati, L. (2016) · Journal of Intelligent Transportation Systems · doi:10.1080/15472450.2016.1164047 · Cited by 55 · cited 2×
“…the positive results on train car load balancing from earlier pilot studies with less timely information [22] and simulation experiments [24], [25], the results suggest that real-time crowding information can be an effective means to reduce in-vehicle crowding and passengers’ discomfort,…”
ResultImpact of real-time crowding information: a Stockholm metro pilot study
Zhang, Y., Jenelius, E., & Kottenhoff, K. (2017) · Public Transport · doi:10.1007/s12469-016-0150-y · Cited by 52 · cited 2×
“Considering the positive results on train car load balancing from earlier pilot studies with less timely information [22] and simulation experiments [24], [25], the results suggest that real-time crowding information can be an effective means to reduce in-vehicle crowding and passengers’…”
BackgroundResultSelf-citationWiFi Sensing-Based Real-Time Bus Tracking and Arrival Time Prediction in Urban Environments
Zhang, R., Liu, W., Jia, Y., Jiang, G., Xing, J. H., Jiang, H., & Liu, J. (2018) · IEEE Sensors Journal · doi:10.1109/jsen.2018.2813983 · Cited by 38 · cited 1×
“Several methods for short-term arrival time prediction based on various assumptions about data availability have been proposed, e.g., [14]–[16].”
Transit Data Analytics for Planning, Monitoring, Control, and Information
Koutsopoulos, H. N., Ma, Z., Noursalehi, P., & Zhu, Y. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-812970-8.00010-5 · Cited by 38 · cited 1×
“A recent study utilizes real-time AFC and AVL data from trains combined with mesoscopic simulation to predict demand patterns and in-vehicle crowding, focusing on the risk of denied boarding [26].”
MethodAlleviating a subway bottleneck through a platform gate
Muñoz, J. C., Soza‐Parra, J., Didier, A., & Silva, C. (2018) · Transportation Research Part A Policy and Practice · doi:10.1016/j.tra.2018.07.004 · Cited by 37 · cited 1×
“…loads, including varying the stop positions of trains at stations considering passenger flows and locations of station entrances [12], and the installation of one-way gates on platforms to control passenger flows and influence car boarding choices [13], but real-time crowding management is uncommon.”
BackgroundPeftitsi, S., Jenelius, E., & Cats, O. (2020) · Transportmetrica A Transport Science · doi:10.1080/23249935.2020.1720040 · Cited by 30
Self-citationChristoforou, Z., Collet, P.-A., Kabalan, B., Leurent, F. M., de Feraudy, A., Ali, A., Freeden, T. J. A.-V., & Li, Y. (2017) · Transportation Research Record Journal of the Transportation Research Board · doi:10.3141/2648-14 · Cited by 25 · cited 1×
“…on the platform and boarding different cars depends on a number of factors, including the distance between the platform entrance and the waiting position, the capacity of each waiting position, the crowding distribution between train cars and the exit location at the destination station [9]–[11].”
BackgroundSohn, K. (2013) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2252166 · Cited by 20 · cited 1×
“…of passenger loads, including varying the stop positions of trains at stations considering passenger flows and locations of station entrances [12], and the installation of one-way gates on platforms to control passenger flows and influence car boarding choices [13], but real-time crowding…”
BackgroundSimulating the effects of real-time crowding information in public transport networks
Drabicki, A., Kucharski, R., Cats, O., & Fonzone, A. (2017) · 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS) · doi:10.1109/mtits.2017.8005598 · Cited by 20 · cited 2×
“Considering the positive results on train car load balancing from earlier pilot studies with less timely information [22] and simulation experiments [24], [25], the results suggest that real-time crowding information can be an effective means to reduce in-vehicle crowding and passengers’…”
ResultPrediction algorithms for train arrival time in urban rail transit
Liu, Y., Tang, T., & Xun, J. (2017) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2017.8317609 · Cited by 11
Research works printed but not linked: 1
- 2018, Factsheet Passenger Load Information System Piloted on Downtown Line for Smoother Boarding
Cited by
Aboualola, M., Abualsaud, K., Khattab, T. M., Zorba, N., & Hassanein, H. S. (2023) · IEEE Access · doi:10.1109/access.2023.3293035 · Cited by 164
“For these reasons, research in [16] tackles the issue of crowding in train carts and analyzes the efficacy of numerous data-driven prediction algorithms.”
BackgroundDarsena, D., Gelli, G., Iudice, I., & Verde, F. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3223297 · Cited by 71
“Besides some approaches showing the benefits of RTCI dissemination to the passengers [17, 59, 60, 75], operator-based crowd control in PT systems is still at an early stage of development.”
BackgroundMethodModelling the effects of real-time crowding information in urban public transport systems
Drabicki, A., Kucharski, R., Cats, O., & Szarata, A. (2020) · Transportmetrica A Transport Science · doi:10.1080/23249935.2020.1809547 · Cited by 57
“empirical prediction algorithms Jenelius (2018); Jenelius (2020) Framework for car-specific metro train crowding prediction, based on real-world load (APC) data – Stockholm (Sweden).”
BackgroundMethodInfluentialRoncoli, C., Chandakas, E., & Kaparias, I. (2022) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2022.103963 · Cited by 61
“A notable exception to this has been the work of Jenelius (2019), who, extending their previous work (Jenelius, 2020), used their developed lasso regression approach to predict real-time on-board crowding on buses in Stockholm, taking into account the fact that only 20 % of the vehicles were…”
Machine Learning for public transportation demand prediction: A Systematic Literature Review
di Torrepadula, F. R., Napolitano, E. V., Martino, S. D., & Mazzocca, N. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109166 · Cited by 62
Metadata
- Authors
- Jenelius, E.
- Affiliations
- KTH Royal Institute of Technology (SE)
- Corresponding author
- Jenelius, Erik
- ORCID
- Jenelius, Erik
- Venue
- IEEE Transactions on Intelligent Transportation Systems
- Published
- 2020-06
- Volume
- 21
- Issue
- 6
- Pages
- 2254-2265
- ISSN
- 1524-9050 (ISSN-L)
- 1558-0016
- OpenAlex
- W2946518783
- Cited by
- 60
- References
- 28
- Citations by year
- 2026: 7 · 2025: 5 · 2024: 10 · 2023: 11 · 2022: 8 · 2021: 8 · 2020: 11
- FWCI
- 7.57
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Intelligent Transportation Systems (publishedVersion)
- Funders
- Transport Research Environment with Novel Perspectives (TRENoP) Strategic Research Area
- Topics
- Social Sciences › Transportation › Transportation Planning and Optimization
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Social Sciences › Transportation › Railway Systems and Energy Efficiency
- Keywords
- LASSO, stepwise regression, Stockholm metro
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.