On-road experimental study on driving anger identification model based on physiological features by ROC curve analysis

On-road experimental study on driving anger identification model based on physiological features by ROC curve analysis

For access to this article, please select a purchase option:

Buy eFirst article PDF
(plus tax if applicable)
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
— Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Road rage is a serious psychological issue affecting traffic safety, which has attracted increasing concern regarding driving anger intervention. This study proposed a method for driving anger identification based on physiological features. First, 30 drivers were recruited to perform on-road experiments on a busy route in Wuhan, China. The drivers’ anger could be inducted on the study route by elicitation events, e.g. vehicles weaving/cutting in line, jaywalking, traffic congestion and waiting at red light if they want to finish the experiments ahead of basic time for extra pay. Subsequently, significance analysis was used to determine that five physiological features including heart rate, skin conductance, respiration rate, the relative energy spectrum of θ and β bands of electroencephalogram were effective for driving anger identification. Finally, a linear discriminant model was proposed to identify driving anger based on the optimal thresholds of the five features which were determined by receiver operating characteristic (ROC) curve analysis. The results show that the proposed model achieves an accuracy of 85.84% which is 7.95 and 5.71% higher than the models using back propagation neural network and support vector machine, respectively. The results can provide theoretical foundation for developing driving anger detection devices based on physiological features.

Related content

This is a required field
Please enter a valid email address