Application Of Ica For Separation Of Artifacts In Meg/Eeg Signals By Blind Source Separation Using Improved Particle Swarm Optimizer
A. Naresh Kumar, Gautham Jayakrishnan · Procedia Engineering · 2012
Magneto encephalography (MEG) is a technique by which the activity of the cortical neurons can be measured with very good temporal and moderate spatial resolution. When using a MEG record, as a research or clinical tool, the investigator may face a problem of extracting the essential features of the neuromagnetic signals in the presence of artifacts. The amplitude of the disturbances may be higher than that of the brain signals, and the artifacts may resemble pathological signals in shape. Our proposed method is used to separate brain activity from artifacts by Blind source separation using ICA and PSO for learning rate adjustment. Our approach is found to be more efficient and exhibited rapid convergence and it is stable when compared to other related approaches.