A study on noise reduction using ICA for Magnetoencephalography

In the biomagnetic measurement, the biomagnetic signal is extremely weak compared with environmental magnetic noise. Therefore, it is important to reduce the noise component. There are many noise-reduction studies for MEG using Independent Component Analysis (ICA). The ICA method is expectable to extract and remove noise components from the brain magnetic field measurement data. However, in these researches, each obtained independent components are artificially distinguished to the noise and the signal. We propose a method of distinguishing to the noise and the signal automatically by using the signal subspace method for vector brain magnetic field. By applying this method to a phantom data and Auditory Evoked Field data, it is shown improvement of the signal to noise ratio and estimated accuracy.