The Single-Trial Estimation Of Visual Evoked Potential

Visual evoked potentials(VEP) is a tufty electricity signal potential of the cerebrum cortex in response to the stimulus.From the point of view of clinical diagnosis, the extraction of VEP has very important significance. The single-trial estimation of VEP has become the research objective of many pepole.Many pepole have been put forward many methods to resolve the problem of VEP extraction. The independent component analysis (ICA) is a new developed statistical method in recent years. This method is based on high order statistics. ICA is to separate the original signals into several independent components by selecting a particular criterion and an optimal algorithm. Though the specific information of the sources and mixing system are unknown, the probability for the source decomposition can be realized by using the principle of statistical independence.In this paper, the basic knowledge of ICA has been first introduced, including the statistics theory and information theory that are necessary to understanding and mastering ICA technique. Then the basic principle of ICA has been introduced.This paper introduced the famous independent component analysis algorithm: two categories of independent component analysis algorithm which based on information theory and statistical kurtosis theory. Another research focus of this paper is FastICA algorithm. According to independent component analysis and mathematical basis of the theory, this paper pointed out the inadequate of Newton's method in the independent component analysis, and raised its solution: Applying simplified Newton method to reduce the amount of computation; Adding additional constraints to ensure the convergence function.Applying the improved algorithm, A simulation experiment was done.The results show that the improved algorithm can reduced the number of iterations,proved the feasibility of improving the algorithm.At the end of this paper, we give conclusions and introduce our future works.