Learning to decode human emotions with Echo State Networks

• Published in: Neural networks Vol. 78; pp. 112 - 119
• Main Authors: Bozhkov, Lachezar, Koprinkova-Hristova, Petia, Georgieva, Petia
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2016
• Subjects: Affective computing; Brain; Brain - physiology; Echo State Networks; Electroencephalography - methods; Emotions; Emotions - physiology; Event Related Potentials; Evoked Potentials - physiology; Feature extraction; Feature selection; Human; Humans; Machine Learning; Mathematical analysis; Mathematical models; Networks; Neural Networks (Computer); Reservoir computing; Reservoirs; Affective computing; Feature selection; Event Related Potentials; Echo State Networks; Reservoir computing

The aim of this paper is to identify the common neural signatures based on which the positive and negative valence of human emotions across multiple subjects can be reliably discriminated. The brain activity is observed via Event Related Potentials (ERPs). ERPs are transient components in the Electr...