[A robust approach to independent component analysis and its application in the analysis of magnetoencephalographic data].

Independent component analysis (ICA) is a new method of signal statistical processing and widely used in many fields. We face several problems such as the different nature of source signals (e.g. both super-Gaussian and sub-Gaussian sources exist), unknown number of sources and contamination of the sensor signals with a high level of additive noise in the analysis of signal. A robust approach was proposed to solve these problems in this paper. Firstly, observations (noisy data) possessing high dimensionality were preprocessed and decomposed into a source signal subspace and a noise subspace. Then the number of sources was got through the cross-validation method, and this solved the problem that ICA could not confirm the number of sources. At last the transformed low-dimensional source signals were further separated with the fast and stable ICA algorithm. Through the analysis of artificially synthesized data and the real-world Magnetoencephalographic data, the efficacy of this robust approach was illustrated.