IEEE Transactions on Affective Computing | 2021

Biofeedback Arrests Sympathetic and Behavioral Effects in Distracted Driving

 
 
 
 
 
 
 

Abstract


Operating machinery while distracted is a dangerous behavior, often habitual, which is the source of accidents. Distracted driving in particular has assumed the form of an epidemic, fueled by the ubiquity of smartphone usage and the tendency to slip into absent-mindedness in tedious commutes. Here we show that a method capable of detecting and communicating overarousal trends associated with the onset of distractions, can pull the driver out of a downward psychophysiological spiral. The method is reliable, unobtrusive, and subtle in its intervention—all important characteristics for real-time corrections on human handling of critical machinery. Arousal estimation is performed by a conservative statistical filter acting upon the driver’s perinasal perspiration signal, as this is continuously extracted from a thermal imaging feed. Overarousal notices are communicated via a visual indicator placed in the driver’s peripheral vision. Using this method, we conducted a parallel group experiment, where a control <inline-formula><tex-math notation= LaTeX >$CL$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>C</mml:mi><mml:mi>L</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href= pavlidis-ieq1-2883950.gif /></alternatives></inline-formula> (<inline-formula><tex-math notation= LaTeX >$n=23$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>n</mml:mi><mml:mo>=</mml:mo><mml:mn>23</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href= pavlidis-ieq2-2883950.gif /></alternatives></inline-formula>) and a biofeedback <inline-formula><tex-math notation= LaTeX >$BF$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>B</mml:mi><mml:mi>F</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href= pavlidis-ieq3-2883950.gif /></alternatives></inline-formula> (<inline-formula><tex-math notation= LaTeX >$n=24$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>n</mml:mi><mml:mo>=</mml:mo><mml:mn>24</mml:mn></mml:mrow></mml:math><inline-graphic xlink:href= pavlidis-ieq4-2883950.gif /></alternatives></inline-formula>) cohort were distracted mentally and physically while driving, with only the biofeedback group receiving the benefit of overarousal notification. Results show that heeding biofeedback notices, cuts dramatically the time <inline-formula><tex-math notation= LaTeX >$BF$</tex-math><alternatives><mml:math><mml:mrow><mml:mi>B</mml:mi><mml:mi>F</mml:mi></mml:mrow></mml:math><inline-graphic xlink:href= pavlidis-ieq5-2883950.gif /></alternatives></inline-formula> subjects are engaged in distractions with respect to the control group, significantly reducing their arousal levels and improving their driving behaviors in the context of a typical commute.

Volume 12
Pages 453-465
DOI 10.1109/TAFFC.2018.2883950
Language English
Journal IEEE Transactions on Affective Computing

Full Text