Artifact Elimination from EEG Signals using Error Normalized algorithms for Brain Computer Interface Systems

Abstract

In this paper some efficient and low computation complex signal conditioning algorithms are proposed in distant health tracking applications, for improvement of the electroencephalogram (EEG) signal. Few artifacts are contaminated also mask small characteristics underlying EEG signal activity in medical environments during extraction of EEG signal. Low computational difficulty filters are appealing especially within distant healthcare surveillance. Therefore, we provided several effective and less computing adaptive noise cancellers (ANCs) in this work to improve EEG signal. Most of these techniques use easy addition as well as shift calculations also attain significant convergence performance compared to other standard techniques. Real EEG signals collected using emotional EEG systems are verified for proposed implementations. Using several performances measures our studies demonstrate that techniques suggested provides best performance than prevailing methods. This methodology is suitable in the analysis of brain computer interface (BCI) applications.