Evaluation of Driver's Cognitive Distracted State Considering the Ambient State of a Car

Evaluation of Driver's Cognitive Distracted State Considering the Ambient State of a Car

Hiroaki Koma (Tokyo University of Science, Chiba, Japan), Taku Harada (Tokyo University of Science, Chiba, Japan), Akira Yoshizawa (Denso IT Laboratory, Inc., Tokyo, Japan) and Hirotoshi Iwasaki (Denso IT Laboratory, Inc., Tokyo, Japan)
DOI: 10.4018/IJCINI.2019010102

Abstract

The effectiveness of considering the ambient state of a driving car for evaluating the driver's cognitive distracted state is evaluated. In this article, Support Vector Machines and Random Forest, which are representative machine learning models, are applied. As input data for the machine learning model, in addition to a driver's biometric data and car driving data, an ambient state data of a driving car are used. The ambient state data of a driving car considered in this study are that of the preceding car and the shape of the road. Experiments using a driving simulator are conducted to evaluate the effectiveness of considering the ambient state of a driving car.
Article Preview
Top

Background

There are many studies that have used driver biometric information such as eye movement to evaluate the cognitive distracted state. Eye movement is the primary sign of life in neuropsychology and cognitive science (Wang, 2014).

Yoshizawa, et. al. discussed the influence of nonvisual secondary tasks on driver's pedestrian detection to eye movement (Yoshizawa & Iwasaki, 2015). Miyaji, et al. detected driver cognitive distraction by using the eye movement and head movement data (Miyaji, Kawanaka, & Oguri, 2010). Liu et al. have also detected the distracted state by using the eye movement and head movement data obtained while driving (Liu, Yang, Huang, & Lin, 2015; Liu, Yang, Huang, Yeo, & Lin, 2016; Liu, Yang, Huang, Lin, Klanner, Denk, & Rasshofer, 2015). Mizoguchi et al. extracted complex rules appearing in cognitive distracted state from various driver characteristics such as eye movement, steering angle, and pedal pressure, using inductive logic programming (Mizoguchi, Ohwada, Nishiyama, Yoshizawa, & Iwasaki, 2015). In addition, Mizoguchi, et al. combined the driver rule in the cognitive distracted state generated by inductive logic programming and the classification result of the SVM, and then detected the cognitive distracted state with a higher precision than other existing methods (Mizoguchi, Nishiyama, & Iwasaki, 2014). We evaluated the cognitive distracted state using the eye movement data acquired while driving and the eye movement data acquired from visual experiment tasks on a personal computer display (Harada, Iwasaki, Mori, Yoshizawa, & Mizoguchi, 2014; Harada, Mori, Yoshizawa, & Iwasaki, 2015; Harada, Kawakami, Yoshizawa, Iwasaki, & Mizoguchi, 2015; Koma, Harada, Yoshizawa, & Iwasaki, 2017).

This shows the way eye movement data is used for evaluating the cognitive distracted state. However, the eye movement is affected by the ambient state of the car being driven. Therefore, by evaluating the cognitive distracted state in consideration of the ambient state of the driving car, more accurate results are expected compared with evaluation without considering the ambient state.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 14: 4 Issues (2020): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2019)
Volume 12: 4 Issues (2018)
Volume 11: 4 Issues (2017)
Volume 10: 4 Issues (2016)
Volume 9: 4 Issues (2015)
Volume 8: 4 Issues (2014)
Volume 7: 4 Issues (2013)
Volume 6: 4 Issues (2012)
Volume 5: 4 Issues (2011)
Volume 4: 4 Issues (2010)
Volume 3: 4 Issues (2009)
Volume 2: 4 Issues (2008)
Volume 1: 4 Issues (2007)
View Complete Journal Contents Listing