Enhancement of Target Components in EEG Signals Based on A Probabilistic Generative Model Using Spatial Correlation Prior
真木 勇人 (1351096)
Event-related potentials (ERPs) of electroencephalogram (EEG) are one of the major techniques for analyzing analysis of brain activities. However, as EEG signals easily suffer from various artifacts, ERPs are often collapsed and hard to observe. There are several attempts at using multi-channel EEG signals to enhance EEG signals of interest and make ERPs more clearly observed. For example, a previous work has proposed a blind EEG signal separation method using a multi-channel Wiener filter designed with a probabilistic generative model of observed EEG signals. This method copes with the under-determination of EEG signal separation by assuming sparseness of each EEG component in the time-frequency domain. Although this method blindly separates EEG signals into individual EEG components using time-varying scaled spatial correlation matrices, target EEG components, such as P300 of ERP, are often known in advance in some applications. In this thesis, inspired by this previous work, we propose a probabilistic EEG signal enhancement
method using a multi-channel Wiener filter, newly incorporating prior
information of the spatial correlation matrices related to the target
EEG component in the probabilistic generative model to improve performance of
EEG signal enhancement. An experimental evaluation for P300 enhancement
show that the proposed method significantly reduces artifacts.