Recent Artifacts Handling Algorithms in Electroencephalogram

Abstract

The Electroencephalogram (EEG) is mostly used to measure electrical activity of brain. EEG tells us how the Brain reacts to various stimuli at that instant of time or in various conditions arrived at any instance of time. These are even used for Brain-Computer-Interface (BCI) activities, where the activities of brain are communicated to brain directly. While doing so the Artifacts produced in EEG data by various activities of a human being is a common problem and a research going on in this stream. Therefore, Artifact handling and removal at a very early stage is a prior research going on.

This paper focuses on various artifacts involved and recent algorithms which give higher accuracy EEG signals. Mainly EEG artifacts handling and removals using various algorithms are presented based on their performances. We have studied various EEG Artifacts handling techniques by retrieving methods from past 12 years. These methods are categorized to handle various artifacts including EEG, EOG and EMG. Study found that instead of using one single algorithm; hybrid combination of it gives superior results as compared to single algorithm.

Results found by using Hybrid model of handling artifacts that usage of individual machine learning algorithm had few limitations, whereas combination of algorithms could give better accuracy and sensitivity. Mostly Independent Component Analysis (ICA) and Support Vector Machine (SVM) where found to be used by various authors more times and these gave better performances as compared to other algorithms individually and combinational

Keywords: Electroencephalograms (EEG), Artifacts removal, Machine learning, Hybrid algorithms.