Spectral subtraction based emotion recognition using EEG
HCII'11 Proceedings of the 14th international conference on Human-computer interaction: towards mobile and intelligent interaction environments - Volume Part III
Hi-index | 0.00 |
Artifacts such as eye blinks cause interference signals within electroencephalogram (EEG) measurements. There- fore, we propose a method for artifact removal based on certain power spectrum features of independent compo- nents extracted from the EEGs by fusing ensemble aver- age and cross-corrasion parameter. First, each independent component which was assumed to be a source was searched by applying cross-corrasion parameter to EEG which in- volved artifacts relevant to the eye blinks of a normal per- son. Next, the signal which was assumed to be blink arti- facts can be removed using high-pass filtering. The removal results of the eye blink artifacts are fed into the interpreta- tion system.