A recognition model of driving risk based on Belief Rule-Base methodology

Chaozhong Wu; Chuan Sun; Duanfeng Chu; Zhenji Lu; Barys Shyrokau; Riender Happee

A recognition model of driving risk based on Belief Rule-Base methodology

Chaozhong Wu, Chuan Sun, Duanfeng Chu, Zhenji Lu, Barys Shyrokau, Riender Happee

Intelligent Vehicles

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modelling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of the proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS.

Original language	English
Title of host publication	Proceedings of the 96th Annual Meeting of the Transportation Research Board
Place of Publication	Washington, DC, USA
Publisher	Transportation Research Board (TRB)
Number of pages	22
Publication status	Published - 2017
Event	96th Annual Meeting of the Transportation Research Board (TRB): Transportation Innovation: Leading the Way in an Era of Rapid Change - Walter E. Washington Convention Center, Washington, United States Duration: 8 Jan 2017 → 12 Jan 2017 http://www.trb.org/AnnualMeeting/AnnualMeeting.aspx

Conference

Conference	96th Annual Meeting of the Transportation Research Board (TRB)
Abbreviated title	TRB 2017
Country/Territory	United States
City	Washington
Period	8/01/17 → 12/01/17
Other	The meeting program will cover all transportation modes, with more than 5,000 presentations in over 800 sessions and workshops, addressing topics of interest to policy makers, administrators, practitioners, researchers, and representatives of government, industry, and academic institutions
Internet address	http://www.trb.org/AnnualMeeting/AnnualMeeting.aspx

Keywords

Highways
Safety and Human Factors

Access to Document

https://trid.trb.org/view.aspx?id=1438569

Cite this

@inproceedings{eaafc080946941bf8d55e958323255b7,

title = "A recognition model of driving risk based on Belief Rule-Base methodology",

abstract = "This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modelling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of the proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS.",

keywords = "Highways, Safety and Human Factors",

author = "Chaozhong Wu and Chuan Sun and Duanfeng Chu and Zhenji Lu and Barys Shyrokau and Riender Happee",

year = "2017",

language = "English",

booktitle = "Proceedings of the 96th Annual Meeting of the Transportation Research Board",

publisher = "Transportation Research Board (TRB)",

note = "96th Annual Meeting of the Transportation Research Board (TRB) : Transportation Innovation: Leading the Way in an Era of Rapid Change, TRB 2017 ; Conference date: 08-01-2017 Through 12-01-2017",

url = "http://www.trb.org/AnnualMeeting/AnnualMeeting.aspx",

}

Wu, C, Sun, C, Chu, D, Lu, Z, Shyrokau, B & Happee, R 2017, A recognition model of driving risk based on Belief Rule-Base methodology. in Proceedings of the 96th Annual Meeting of the Transportation Research Board., 17-03960, Transportation Research Board (TRB), Washington, DC, USA, 96th Annual Meeting of the Transportation Research Board (TRB), Washington, United States, 8/01/17. <https://trid.trb.org/view.aspx?id=1438569>

A recognition model of driving risk based on Belief Rule-Base methodology. / Wu, Chaozhong; Sun, Chuan; Chu, Duanfeng et al.
Proceedings of the 96th Annual Meeting of the Transportation Research Board. Washington, DC, USA: Transportation Research Board (TRB), 2017. 17-03960.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - A recognition model of driving risk based on Belief Rule-Base methodology

AU - Wu, Chaozhong

AU - Sun, Chuan

AU - Chu, Duanfeng

AU - Lu, Zhenji

AU - Shyrokau, Barys

AU - Happee, Riender

PY - 2017

Y1 - 2017

N2 - This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modelling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of the proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS.

AB - This paper aims to recognize driving risks in individual vehicles online based on a data-driven methodology. Existing advanced driver assistance systems (ADAS) have difficulties in effectively processing multi-source heterogeneous driving data. Furthermore, parameters adopted for evaluating the driving risk are limited in these systems. The approach of data-driven modelling is investigated in this study for utilizing the accumulation of on-road driving data. A recognition model of driving risk based on belief rule-base (BRB) methodology is built predicting driving safety as a function of driver characteristics, vehicle state and road environment conditions. The BRB model was calibrated and validated using on-road data from 30 drivers. The test results show that the recognition accuracy of the proposed model can reach about 90% in all situations with three levels (none, medium, large) of driving risks. Furthermore, the proposed simplified model, which provides real-time operation, is implemented in a vehicle driving simulator as a reference for future ADAS.

KW - Highways

KW - Safety and Human Factors

M3 - Conference contribution

BT - Proceedings of the 96th Annual Meeting of the Transportation Research Board

PB - Transportation Research Board (TRB)

CY - Washington, DC, USA

T2 - 96th Annual Meeting of the Transportation Research Board (TRB)

Y2 - 8 January 2017 through 12 January 2017

ER -

A recognition model of driving risk based on Belief Rule-Base methodology

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this