Proceedings of the 6th International Conference on Body Area Networks
PRICAI'12 Proceedings of the 12th Pacific Rim international conference on Trends in Artificial Intelligence
Evaluating experience sampling of stress in a single-subject research design
Personal and Ubiquitous Computing
| Hi-index | 0.00 |
This article describes an approach to detecting mental stress using unobtrusive wearable sensors. The approach relies on estimating the state of the autonomic nervous system from an analysis of heart rate variability. Namely, we use a non-linear system identification technique known as principal dynamic modes (PDM) to predict the activation level of the two autonomic branches: sympathetic (i.e. stress-inducing) and parasympathetic (i.e. relaxation-related). We validate the method on a discrimination problem with two psychophysiological conditions, one associated with mental tasks and one induced by relaxation exercises. Our results indicate that PDM features are more stable and less subject-dependent than spectral features, though the latter provide higher classification performance within subjects. When PDM and spectral features are combined, our system discriminates stressful events with a success rate of 83% within subjects (69% between subjects).