Feature Extraction Of Visual Evoked Potentials Using Independent Component Analysis

Electroencephalogram (EEG) is the spontaneous electrical activity recordings of brain cells from scalp, which is the outer-representation of all electrical activities in human's brain and contains ample information useful for physical, psychological and pathological analysis. It's very important to analyze and process the brain signals, not only for diagnosis and therapy of brain diseases but also for the research in cognitive science field.There are many kinds of artifacts in the raw brain signals from scalp, such as eyes blinks, Electrocardiograph (ECG), electromyography (EMG) and other mechanical noises, which could degenerate the real evoked potentials. How to extract the underlying evoked potentials from noisy acquired data has became an important and urgent problem to be resolved.With the development of Independent Component Analysis technology in signal processing field, it's also gradually applied to biomedical signals process. Compared with the traditional average or time-frequency methods, ICA has been proved to be more effective in EEG artifacts reduction and EP...