An Automatic Identification Method for the Blink Artifacts in the Magnetoencephalography with Machine Learning

Magnetoencephalography (MEG) detects very weak magnetic fields originating from the neurons so as to study human brain functions. The original detected MEG data always include interference generated by blinks, which can be called blink artifacts. Blink artifacts could cover signal we are interested in, and therefore need removed. Commonly used artifact cleaning algorithms space projection (SSP) independent component analysis (ICA). These locate artifacts, is typically done with identification of signals in electrooculogram (EOG). EOG needs measured electrodes placed near eye. In this work, a new algorithm proposed for automatic on-the-fly based on machine learning; specifically, artificial neural network (ANN). Seven hundred one contained eight sets harnessed verify effect algorithm. results show that method recognize data, providing feasible data-processing approach potentially implemented automatically simultaneously measurement.