A Comparison of Unimodal and Multimodal Measurements of Driver Stress in Real-World Driving Conditions

Abstract

Objectively measuring drivers’ emotions in real-world conditions is a challenging endeavour. This study investigated whether drivers’ emotional responses were captured more meaningfully by unimodal measurements or by a multimodal machine-learning approach. Ten participants drove a 23-mile route around Sunnyvale, California, while their heart rate, breathing rate and facial expressions were recorded. At regular intervals, participants indicated how they were feeling. After the study, independent observers reviewed a sample of the videotaped sessions, classifying the participants as experiencing high or low levels of stress according to their behaviour. The degree to which drivers’ self-report scores, single physiological data streams and facial behaviour - as judged by a facial recognition machine classifier - reflected their actual stress levels was compared to the multimodal algorithmic estimates which combined physiological and facial data outputs. The results showed that, compared to the other single data modes, the multimodal approach captured how the participants were feeling in a way which most meaningfully corresponded with their observed behaviour. The findings re-affirm the need for multimodal emotion-recognition systems for capturing driver stress. The limitations of the study are also discussed.

Silent, unsafe… and underestimated? Exploring the relationships between life stress and safety issues among Spanish drivers

“…This has been hypothesised to be a negative consequence of many factors, such as overconfidence, repeated practice, lack of information and insufficient risk perception among drivers, a set of facts that could be worsening their road safety outcomes (Alonso et al 2020a;Spencer et al 2020). In this context, environmental, social and life-related stressors could be considered as relatively frequent, even though underreporting of their rates remains very high among many sectors of the population (Gustavson et al 2018, Weiten et al 2014.…”

Untitled

“…This has been hypothesised to be a negative consequence of many factors, such as overconfidence, repeated practice, lack of information and insufficient risk perception among drivers, a set of facts that could be worsening their road safety outcomes (Alonso et al 2020a;Spencer et al 2020).…”

“…Reducing the cognitive resources destined for certain daily activities is not especially problematic; however, there are some tasks that can be adversely affected. In this sense, some recent evidence has systematically shown how stress (approached from different theoretical models and conceptions) and driving performance are closely related, as safe driving requires balancing external and personal demands and resources, but demands often overcome the latter (Epel et al 2018, Rowden et al 2011, Spencer et al 2020, Useche et al 2021a). Also, there exists a growing body of scientific evidence endorsing the hypothesis of a relationship between stress and traffic crash rates among drivers (Legree et al 2003).…”