On the use of lateralization for lightweight and accurate methodology for EEG real time emotion estimation using Gaussian-process classifier
-
Mikel Val-Calvo ; José Ramón Alvarez-Sánchez ; Alejandro Díaz-Morcillo [1] ; José Manuel Ferrández Vicente [1] ; Eduardo Fernández-Jover
-
[1] Universidad Politécnica de Cartagena
Universidad Politécnica de Cartagena
Cartagena, España
-
- 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. 191-201
- Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
Emotional estimation systems based on electroencephalography (EEG) signals are gaining special attention in recent years due tothe possibilities they offer. The field of human-robot interactions (HRI) will benefit from a broadened understanding of brain emotional encoding and thus, improve the capabilities of robots to fully engage with the user’s emotional reactions. In this paper, a methodology for real-time emotion estimation aimed for its use in the field of HRI is proposed. The proposed methodology takes advantage of the lateralization produced in brain oscillations during emotional stimuli and the use of meaningful features related to intrinsic EEG patterns. In the validation procedure, both DEAP and SEED databases have been used. A mean performance of 88.34% was obtained using four categories of the valence-arousal space, and 97.1% using three discrete categories; both of them obtained with a Gaussian-Process classifier. This lightweight method could run on inexpensive, portable devices such as the openBCI system.
