SmartCar: detecting driver stress

By Jennifer A. Healey, Rosalind W. Picard. Proceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2000

301 citations recorded by the source corpus.

Smart physiological sensors embedded in an automobile afford a novel opportunity to capture naturally occurring episodes of driver stress. In a series of ten ninety minute drives on public roads and highways, ECG, EMG, respiration and skin conductance sensors were used to measure the autonomic nervous system activation. The signals were digitized in real time and stored on the SmartCar's Pentium class computer. Each drive followed a pre-specified route through fifteen different events, from which four stress level categories were created according to the results of the subjects self report questionnaires. In total, 545 one minute segments were classified. A linear discriminant function was used to rank each feature individually based on the recognition performance, and a sequential forward floating selection algorithm was used to find an optimal set of features for recognizing patterns of driver stress. Using multiple features improved performance significantly over the best single feature performance.

Subfields: Biomedical Engineering, Cardiology and Cardiovascular Medicine, Cognitive Neuroscience

View Paper: https://www.semanticscholar.org/paper/9d68d09e449d554afae2ff50a65b6c90bb31ecec

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Cardiology and Cardiovascular Medicine

In Cognitive Neuroscience

Citations in the corpus

Adaptive interfaces and agents (2002, background): “Since it is possible to recognize these characteristics reasonably well on the basis of speech, a system might adopt a voice or dialog”
Affective Learning — A Manifesto (2004, background): “Additionally, the Media Lab has attained from 89—96% classification accuracy of three levels of cognitive-emotional stress [ 70 ], although the latter data was from drivers in Boston and not from children in learning situations, where stress would also be interesting to study.”
Emotion recognition from physiological signals using wireless sensors for presence technologies (2004, background): “Healey and Picard conducted a study [18] in which physiological signals (electrocardiogram, electromyogram, respiration, and skin conductance) of the drivers were measured in order to detect their stress level.”
Probabilistic assessment of user's emotions in educational games (2002, methodology): “This has been achieved either by focusing on recognizing a specific emotion in a fairly constraining interaction ( Healy and Picard, 2000; Hudlicka and McNeese, 2002) or by assessing only lower level dimensions of emotional reaction, such as its intensity and vale nce1 (Ball and Breeze, 2000).”
Estimating cognitive load using remote eye tracking in a driving simulator (2010, background): “However, physiological measures depend on many factors, including other aspects of the user’s cognitive state (such as stress [Healey and Picard 2000] and arousal), the user’s physical activity and environmental variables (such as temperature).”
Real-time system for monitoring driver vigilance (2004, background): “A representative project in this line is MIT Smart Car [3], where several sensors (electrocardiogram, electromyogram, respiration and skin conductance) embedded in a car and visual information for sensors confirmation are used.”
Overfitting in Making Comparisons Between Variable Selection Methods (2003, methodology): “…et al., 1994, Jain and Zongker, 1997, Kudo and Sklansky, 2000) make many users of variable selection techniques (see e.g., Vyzas and Picard, 1999, Healey and Picard, 2000, Wiltschi et al., 2000) believe that they should not use the simple algorithms, although according to the results shown in…”