Stress identification from electrodermal activity by support vector machines
-
Autores: Roberto Sánchez, Arturo Martínez Rodrigo
, Antonio Fernández Caballero
- Localización: Understanding the Brain Function and Emotions: 8th International Work-Conference on the Interplay Between Natural and Artificial Computation, IWINAC 2019 Almería, Spain, June 3–7, 2019 Proceedings, Part I / José Manuel Ferrández Vicente (dir. congr.) , José Ramón Álvarez Sánchez (dir. congr.) , Félix de la Paz López (dir. congr.) , Francisco Javier Toledo Moreo (dir. congr.), Hojjat Adeli (dir. congr.), 2019, ISBN 978-3-030-19591-5, págs. 202-211
- Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
Continuous atmosphere of competitiveness, job pressure,economic status and social judgment in modern societies leads many people to a frenetic life rhythm, thus favoring the appearance of stress. Consequently, early detection of calm and negative stress is useful to prevent long-term mental illness as depression or anxiety. This paper describes the acquisition of electrodermal activity (EDA) signals from a commercial wearable, and their storage and processing. Several time-domain,frequency-domain and morphological features are extracted over the skin conductance response component of the EDA signals. Afterwards, classification is undergone by using several support vector machines (SVMs).The International Affective Pictures System has been used to evoke calmness and distress to validate the classification results. The best results obtained during training and validation for each of the SVMs report around 87.7% accuracy for Gaussian and cubic kernels.
