MEG Classification Based on Band Power and Statistical Characteristics

With the work of magnetoencephalography (MEG) classification in brain-computer interface (BCI), a feature extraction method of frequency band power and statistical characteristics was proposed. On the basis of spectrum analysis for the two subjects´ experimental MEG data, frequency band powers of 0.5~6Hz for S1 and 10~25Hz for S2 were extracted as features for the two subjects, together with the statistical characteristics of mean for S1/S2 and standard deviation for S1, finally, the features were classified with linear discriminate analysis function directly and secondly, the results showed that the average classification accuracy was 54.38% which was higher than the achievement of BCI competition winner. Therefore, the frequency band power and statistical characteristics are effective features for MEG signals and the research of this paper gives MEG-based BCIs a beneficial complement.