An approach to emotion recognition in single-channel EEG signals using stationarywavelet transform
Share this
Date
2017Author
Gómez A.
Quintero L.
López N.
Castro J.
Villa L.
Mejía G.
Mathematical Modeling Research Group, GRIMMAT, Universidad EAFIT, Medellín, Colombia
Medical Technology Laboratory, GATEME, Universidad Nacional de San Juan, San Juan, Argentina
Psychology, Education and Culture Research Group, Institución Universitaria Politécnico Grancolombiano, Bogotá, Colombia
System Engineering Research Group, ARKADIUS, Universidad de Medellín, Medellín, Colombia
Functional Analysis and Aplications Research Group, Universidad EAFIT, Medellín, Colombia
Citación
Metadata
Show full item recordAbstract
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.
Collections
- Indexados Scopus [1632]