Time frequency analysis and spatial filtering in the evaluation of beta ERS after finger movement

Abstract

Different methods are compared for the evaluation of the event related synchronization (ERS) in the beta rhythm corresponding to finger movements. In addition to the standard procedure usually employed, the realistic Surface Laplacian (SL) is here introduced to improve the spatial localization of the phenomenon, while a Wavelet Packet (WP) decomposition approach is intended to better detect the time dependent characteristics. The parameters of interest (ERS amplitude and latency) were statistically analyzed through Analysis of Variance (ANOVA) and Scheffe's test. The WP filtering results are well comparable with the traditional filtering procedure. On the other hand, the realistic SL considerably improves the spatial localization and the consistency of the estimation (decreased variance) of the ERS amplitude.