Feature extraction from EEGs associated with emotions

Abstract

The state of mind of a person is supported by the brain activity, and hence features of the state of mind appear in the scalp potentials, as seen on an electroencephalogram (EEG). The EEG features have been extracted into a set of 135 state variables of cross-correlation coefficients of EEGs collected with ten scalp electrodes in the θ, α, and β frequency bands corresponding toanger, sadness, joy, andrelaxation. An emotion matrix is defined which transforms the set of 135 state variables into a four-element emotion vector of which the components are indexes corresponding to the four elementary emotional states. The maximum time resolution of the emotion analysis is 0.64s and it is done in real time. This new technique has a wide variety of applications in both medical and non-medical areas, and the technology suggests the possibility of direct control of systems by the human emotional state.