Estimation of Travel Time Variability Using Bus Probe Data

Mansur As, Tsunenori Mine, Hiroyuki Nakamura

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively improve the prediction accuracy of travel times over intervals by focusing on the three unstable classes and calculating travel times for each interval at each of 8 time-periods in a day.

元の言語英語
ホスト出版物のタイトル6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings
出版者Institute of Electrical and Electronics Engineers Inc.
ページ199-204
ページ数6
ISBN(電子版)9781538616239
DOI
出版物ステータス出版済み - 11 26 2018
イベント6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Bali, インドネシア
継続期間: 7 24 20177 27 2017

出版物シリーズ

名前6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings

その他

その他6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017
インドネシア
Bali
期間7/24/177/27/17

Fingerprint

Travel Time
Travel time
Probe
travel
Interval
Unstable
Predict
Prediction
Arrival Time
time
Bus
Period of time
Waiting Time
Japan
Neural Network Model
Artificial Neural Network
Divides
Time series
Adjacent
Classify

All Science Journal Classification (ASJC) codes

  • Management Science and Operations Research
  • Automotive Engineering
  • Control and Optimization
  • Transportation

これを引用

As, M., Mine, T., & Nakamura, H. (2018). Estimation of Travel Time Variability Using Bus Probe Data. : 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings (pp. 199-204). [8547006] (6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICAdLT.2017.8547006

Estimation of Travel Time Variability Using Bus Probe Data. / As, Mansur; Mine, Tsunenori; Nakamura, Hiroyuki.

6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. p. 199-204 8547006 (6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings).

研究成果: 著書/レポートタイプへの貢献会議での発言

As, M, Mine, T & Nakamura, H 2018, Estimation of Travel Time Variability Using Bus Probe Data. : 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings., 8547006, 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 199-204, 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017, Bali, インドネシア, 7/24/17. https://doi.org/10.1109/ICAdLT.2017.8547006
As M, Mine T, Nakamura H. Estimation of Travel Time Variability Using Bus Probe Data. : 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2018. p. 199-204. 8547006. (6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings). https://doi.org/10.1109/ICAdLT.2017.8547006
As, Mansur ; Mine, Tsunenori ; Nakamura, Hiroyuki. / Estimation of Travel Time Variability Using Bus Probe Data. 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 199-204 (6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings).
@inproceedings{2447c55676c540c08142e13c3c63769f,
title = "Estimation of Travel Time Variability Using Bus Probe Data",
abstract = "Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively improve the prediction accuracy of travel times over intervals by focusing on the three unstable classes and calculating travel times for each interval at each of 8 time-periods in a day.",
author = "Mansur As and Tsunenori Mine and Hiroyuki Nakamura",
year = "2018",
month = "11",
day = "26",
doi = "10.1109/ICAdLT.2017.8547006",
language = "English",
series = "6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "199--204",
booktitle = "6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings",
address = "United States",

}

TY - GEN

T1 - Estimation of Travel Time Variability Using Bus Probe Data

AU - As, Mansur

AU - Mine, Tsunenori

AU - Nakamura, Hiroyuki

PY - 2018/11/26

Y1 - 2018/11/26

N2 - Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively improve the prediction accuracy of travel times over intervals by focusing on the three unstable classes and calculating travel times for each interval at each of 8 time-periods in a day.

AB - Prediction of bus travel times is of crucial importance for passengers in letting them know their departure time from an origin and arrival time at a destination and allowing them to make decisions (e.g., postpone departure time at certain hours) and to reduce their waiting time at bus stops. To predict bus travel times, it is important to know whether the target routes are stable or not. In this paper, we propose a time series approach to predict the travel time over an interval between two adjacent bus stops. We build Artificial Neural Network (ANN) models to predict the travel time over the interval. To make accurate predictions, we divide a day into 8 time-periods in calculating travel time over the interval and classify unstable intervals into three types: weak, medium and strong unstable. We use bus probe data collected from November 21st to December 20th 2013 and provided by Nishitetsu Bus Company, Fukuoka, Japan. Experimental results show that our models can effectively improve the prediction accuracy of travel times over intervals by focusing on the three unstable classes and calculating travel times for each interval at each of 8 time-periods in a day.

UR - http://www.scopus.com/inward/record.url?scp=85059984620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059984620&partnerID=8YFLogxK

U2 - 10.1109/ICAdLT.2017.8547006

DO - 10.1109/ICAdLT.2017.8547006

M3 - Conference contribution

T3 - 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings

SP - 199

EP - 204

BT - 6th IEEE International Conference on Advanced Logistics and Transport, ICALT 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -