An approach to emotion recognition in single-channel EEG signals using stationarywavelet transform
Fecha
2017-01-01
Autores
Gómez, A.
Quintero, L.
López, N.
Castro, J.
Villa, L.
Título de la revista
ISSN de la revista
Título del volumen
Editor
SPRINGER
Resumen
In this work, we perform an approach to emotion recognition from Electroencephalography (EEG) single channel signals extracted in four (4) mother-child dyads experiment in developmental psychology. Single channel EEG signals are decomposed by several types of wavelets and each subsignal are processed using several window sizes by performing a statistical analysis. Finally, three types of classifiers were used, obtaining accuracy rate between 50% to 87% for the emotional states such as happiness, sadness and neutrality. © Springer Nature Singapore Pte Ltd. 2017.