Predicting traffic congestion using driver behavior

Toshio Ito, Ryohei Kaneyasu

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Traffic congestion is one of the largest traffic problems and one solution is a prediction of its generation. Traffic congestion comes from three phases order: the free travel phase, the meta-stability phase, and the traffic congestion phase. Therefore, it can be considered that if the meta-stability phase can be detected, forecasting traffic congestion becomes possible. This paper proposes a driver model that forecasts traffic congestion based on changes in driving behavior and that does not rely on traffic flow monitoring infrastructure. As a result of evaluation in driving simulators, it was understood that the distribution of steering, throttle and speed input frequency changes based on changes in the travel phase. It is possible to distinguish these changes using support vector machines as shown in Figure 1, and it is possible to make this into a driver model that predicts traffic congestion. This method is the first propose that uses only CAN (Controller Area Network) data and needs no additional sensors to detect driving environments or any infrastructures.

Original languageEnglish
Pages (from-to)1288-1297
Number of pages10
JournalProcedia Computer Science
Volume112
DOIs
Publication statusPublished - 2017 Jan 1

Fingerprint

Traffic congestion
Phase stability
Support vector machines
Simulators
Controllers
Monitoring
Sensors

Keywords

  • congestion prediction
  • driver behavior
  • meta-stability phase

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Predicting traffic congestion using driver behavior. / Ito, Toshio; Kaneyasu, Ryohei.

In: Procedia Computer Science, Vol. 112, 01.01.2017, p. 1288-1297.

Research output: Contribution to journalArticle

Ito, Toshio ; Kaneyasu, Ryohei. / Predicting traffic congestion using driver behavior. In: Procedia Computer Science. 2017 ; Vol. 112. pp. 1288-1297.
@article{c68211bdced04115b60ba1c3c82b6a52,
title = "Predicting traffic congestion using driver behavior",
abstract = "Traffic congestion is one of the largest traffic problems and one solution is a prediction of its generation. Traffic congestion comes from three phases order: the free travel phase, the meta-stability phase, and the traffic congestion phase. Therefore, it can be considered that if the meta-stability phase can be detected, forecasting traffic congestion becomes possible. This paper proposes a driver model that forecasts traffic congestion based on changes in driving behavior and that does not rely on traffic flow monitoring infrastructure. As a result of evaluation in driving simulators, it was understood that the distribution of steering, throttle and speed input frequency changes based on changes in the travel phase. It is possible to distinguish these changes using support vector machines as shown in Figure 1, and it is possible to make this into a driver model that predicts traffic congestion. This method is the first propose that uses only CAN (Controller Area Network) data and needs no additional sensors to detect driving environments or any infrastructures.",
keywords = "congestion prediction, driver behavior, meta-stability phase",
author = "Toshio Ito and Ryohei Kaneyasu",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.procs.2017.08.090",
language = "English",
volume = "112",
pages = "1288--1297",
journal = "Procedia Computer Science",
issn = "1877-0509",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Predicting traffic congestion using driver behavior

AU - Ito, Toshio

AU - Kaneyasu, Ryohei

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Traffic congestion is one of the largest traffic problems and one solution is a prediction of its generation. Traffic congestion comes from three phases order: the free travel phase, the meta-stability phase, and the traffic congestion phase. Therefore, it can be considered that if the meta-stability phase can be detected, forecasting traffic congestion becomes possible. This paper proposes a driver model that forecasts traffic congestion based on changes in driving behavior and that does not rely on traffic flow monitoring infrastructure. As a result of evaluation in driving simulators, it was understood that the distribution of steering, throttle and speed input frequency changes based on changes in the travel phase. It is possible to distinguish these changes using support vector machines as shown in Figure 1, and it is possible to make this into a driver model that predicts traffic congestion. This method is the first propose that uses only CAN (Controller Area Network) data and needs no additional sensors to detect driving environments or any infrastructures.

AB - Traffic congestion is one of the largest traffic problems and one solution is a prediction of its generation. Traffic congestion comes from three phases order: the free travel phase, the meta-stability phase, and the traffic congestion phase. Therefore, it can be considered that if the meta-stability phase can be detected, forecasting traffic congestion becomes possible. This paper proposes a driver model that forecasts traffic congestion based on changes in driving behavior and that does not rely on traffic flow monitoring infrastructure. As a result of evaluation in driving simulators, it was understood that the distribution of steering, throttle and speed input frequency changes based on changes in the travel phase. It is possible to distinguish these changes using support vector machines as shown in Figure 1, and it is possible to make this into a driver model that predicts traffic congestion. This method is the first propose that uses only CAN (Controller Area Network) data and needs no additional sensors to detect driving environments or any infrastructures.

KW - congestion prediction

KW - driver behavior

KW - meta-stability phase

UR - http://www.scopus.com/inward/record.url?scp=85032365724&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032365724&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2017.08.090

DO - 10.1016/j.procs.2017.08.090

M3 - Article

VL - 112

SP - 1288

EP - 1297

JO - Procedia Computer Science

JF - Procedia Computer Science

SN - 1877-0509

ER -