Improving The Accuracy Of Brain Computer Interface By Eliminating Eye Blink Artifacts From Eeg Data Using ICA

The accuracy of brain computer interfaces (BCI) depends upon the quality of electroencephalographic (EEG) signals from the subject. Artifacts in EEG present serious problems for EEG interpretation and analysis which also reduces the accuracy of BCI. Many methods have been proposed to remove artifacts from EEG recordings, especially those arising from eye movements and blinks. Because EEG and ocular activity mix bi-directionally, regressing out eye artifacts inevitably involves subtracting relevant EEG signals from each record as well. Regression methods become even more problematic when a good regressing channel is not available for each artifact source. Use of principal component analysis (PCA) has been proposed to remove eye artifacts from multichannel EEG However, PCA cannot completely separate eye artifacts from brain signals, especially when they have comparable amplitudes. Here, a new and generally applicable method for removing a wide variety of artifacts from EEG records based on blind source separation by independent component analysis (ICA) is used.