Classification of Mental Task Based on EEG Processing Using Self Organising Feature Map

AN electroencephalograph (EEG) based computer interface system, also known as brain-computer interface (BCI), offers a new means of computer interaction for those with paralysis or severe neuromuscular disorders. This paper illustrates a novel method using Self Organizing Feature Map (SOFM) to classify left-hand movement imagination, right-hand movement imagination, and word generation from EEG. Welch's periodogram, a power spectrum density (PSD) estimation which is very powerful preprocessing method capable of handling both the noisy and non-stationary natures of EEG signals is used for feature extraction. Further, we classify the PSD feature using SOFM. SOFM is arranged deliberately in a specific fashion and trained with variable learning rate to classify various mental tasks under consideration. A classification accuracy obtained using SOFM is compared with other existing techniques.