Blind Signal Processing Methods for Analyzing Multichannel Brain Signals

A great challenge in neurophysiology is to asses non-invasively the physiological changes occurring in different parts of the brain. These activation can be modeled and measured often as neuronal brain source signals that indicate the function or malfunction of various physiological subsystems. To extract the relevant information for diagnosis and therapy, expert knowledge is required not only in medicine and neuroscience but also statistical signal processing. Besides classical signal analysis tools (such as adaptive supervised filtering, parametric or non-parametric spectral estimation, time-frequency analysis, and higher-order statistics), new and emerging blind signal processing (BSP) methods, especially, generalized component analysis (GCA) including fusion (integration) of independent component analysis (ICA), sparse component analysis (SCA), time-frequency component analyzer (TFCA) and nonnegative matrix factorization (NMF) can be used for analyzing brain data, especially for noise reduction and artefacts elimination, enhancement, detection and estimation of neuronal brain source signals. The recent trends in the BSP is to consider problems in the framework of matrix factorization or more general signals decomposition with probabilistic generative and tree structured graphical models and exploit a priori knowledge about true nature and structure of latent (hidden) variables or brain sources such as spatio-temporal decorrelation, statistical independence, sparseness, smoothness or lowest complexity in the sense e.g., of best linear predictability. The goal of BSP can be considered as estimation of sources and parameters of a mixing system or more generally as finding a new reduced or hierarchical and structured representation for the observed brain data that can be interpreted as physically meaningful coding or blind source estimation. The key issue is to find such transformation or coding (linear or nonlinear) which has true neurophysiological and neuroanatomical meaning and interpretation. In this paper, we briefly discuss how some novel blind signal processing techniques such as blind source separation, blind source extraction and various blind source separation and signal decomposition methods can be applied for analysis and processing EEG data. We discuss also a promising application of BSP to early detection of Alzheimer disease (AD) using only EEG recordings.