This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Estimation of Driver's Arousal State Using Multi-Dimensional Physiological Indices (2nd Report)
Published October 12, 2011 by Society of Automotive Engineers of Japan in Japan
We proposed new criteria for assessment of driver's arousal states defined by the combination of "arousal level" and the presence of "effort" to wake up. Scores on both axes were obtained by rating facial expressions. Support vector machine (SVM) was introduced to discriminate "high" versus "low" arousal and "with" versus "without" effort. Multi-dimensional physiological indices such as blink categories, skin conductance, EEG alpha wave, respiration, heart rate variability which change depending on the arousal states were selected and utilized to train SVM. Training data were randomly extracted from 3 of 4 participants. The remaining data of them and all data of the other participant were used as test data. SVM for arousal level showed passable performances for the trained data and the generalization capability to non-trained data. Detection of effort was relatively difficult.