Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data

Tsubasa Yamaguchi, Mansur As, Tsunenori Mine

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.

Original languageEnglish
Title of host publicationProceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018
EditorsJosef Spillner, Alan Sill
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages97-106
Number of pages10
ISBN (Electronic)9781538655023
DOIs
Publication statusPublished - Jan 9 2019
Event5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018 - Zurich, Switzerland
Duration: Dec 17 2018Dec 20 2018

Publication series

NameProceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018

Conference

Conference5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018
CountrySwitzerland
CityZurich
Period12/17/1812/20/18

Fingerprint

Learning systems
Travel time
Decision trees
travel
learning
regression
linear model
neural network
Bus
Prediction
Linear regression
time
Time delay
Neural networks
performance
Learning model
Machine learning
Gradient
Decision tree
Boosting

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Information Systems
  • Artificial Intelligence
  • Decision Sciences (miscellaneous)
  • Information Systems and Management
  • Communication

Cite this

Yamaguchi, T., As, M., & Mine, T. (2019). Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data. In J. Spillner, & A. Sill (Eds.), Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018 (pp. 97-106). [8606640] (Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BDCAT.2018.00020

Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data. / Yamaguchi, Tsubasa; As, Mansur; Mine, Tsunenori.

Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018. ed. / Josef Spillner; Alan Sill. Institute of Electrical and Electronics Engineers Inc., 2019. p. 97-106 8606640 (Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamaguchi, T, As, M & Mine, T 2019, Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data. in J Spillner & A Sill (eds), Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018., 8606640, Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018, Institute of Electrical and Electronics Engineers Inc., pp. 97-106, 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018, Zurich, Switzerland, 12/17/18. https://doi.org/10.1109/BDCAT.2018.00020
Yamaguchi T, As M, Mine T. Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data. In Spillner J, Sill A, editors, Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 97-106. 8606640. (Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018). https://doi.org/10.1109/BDCAT.2018.00020
Yamaguchi, Tsubasa ; As, Mansur ; Mine, Tsunenori. / Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data. Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018. editor / Josef Spillner ; Alan Sill. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 97-106 (Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018).
@inproceedings{3e45eed47e8d4e98962912c8f2f9f4d3,
title = "Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data",
abstract = "Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.",
author = "Tsubasa Yamaguchi and Mansur As and Tsunenori Mine",
year = "2019",
month = "1",
day = "9",
doi = "10.1109/BDCAT.2018.00020",
language = "English",
series = "Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "97--106",
editor = "Josef Spillner and Alan Sill",
booktitle = "Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018",
address = "United States",

}

TY - GEN

T1 - Prediction of Bus Delay over Intervals on Various Kinds of Routes Using Bus Probe Data

AU - Yamaguchi, Tsubasa

AU - As, Mansur

AU - Mine, Tsunenori

PY - 2019/1/9

Y1 - 2019/1/9

N2 - Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.

AB - Prediction of bus travel time and/or delay time is a useful tool for passengers who want to plan their journey, e.g., when they should leave from the origin bus stop, what they will do after arriving at the destination bus stop, and so on. Many studies have tackled this task using probe data and/or the real time data provided by automatic vehicle location (AVL) systems. Most of them only targeted a small number of routes, short time periods, e.g. less than one week, and used few machine learning models to evaluate their methods. However, different routes generally show different characteristics. In fact, there are big differences between urban routes and rural routes. Furthermore, the performance of machine learning models also varies according to the data dealt with by the models. In this paper, we propose prediction models for bus delay over all intervals between pairs of adjacent bus stops. To build the models, we use one month of bus probe data, which includes more than 80 routes, and apply several machine learning models: linear regression (LR), artificial neural network (ANN), support vector regression (SVR), random forest (RF), and gradient boosting decision tree (GBDT). Experimental results demonstrate the superiority of the GBDT-based prediction model and the effects of considering travel time over prior intervals.

UR - http://www.scopus.com/inward/record.url?scp=85061786597&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85061786597&partnerID=8YFLogxK

U2 - 10.1109/BDCAT.2018.00020

DO - 10.1109/BDCAT.2018.00020

M3 - Conference contribution

AN - SCOPUS:85061786597

T3 - Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018

SP - 97

EP - 106

BT - Proceedings - 5th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, BDCAT 2018

A2 - Spillner, Josef

A2 - Sill, Alan

PB - Institute of Electrical and Electronics Engineers Inc.

ER -