A Robust System for Detection of Artifacts from EEG Brain Recordings

Abstract

Epilepsy is a chronic disorder and has the propensity of two or more brain. Analysis of EEG is the primary method for the diagnosis of epilepsy. Contamination of eye movement and blink artifacts presence in EEG data becomes more complicated to the doctors during the diagnosis period. Earlier detection of these artifacts gives a significant advantage of refining the Epilepsy identification process. In this regard, a robust subspace detection method is applied to detect the target signal in noise with possible interference-artifacts, then a dimensionality reduction model, with the combination of fast Independent and Robust Principal Component Analysis (FICA and rPCA) is implemented for identification of artifacts from EEG brain recordings. To perform this the proposed detection method uses synthetic data and artifact contaminated data. The extracted target subspace signal is considered as the input for rPCA and FICA. The ROC analysis is developed as a standard methodology to quantify the detectors' ability to correctly distinguish the target of interest (artifacts) from the background noise in the system.