Automated EEG Artifact Detection Using Independent Component Analysis

In electroencephalogram (EEG) recordings, physiological and non-physiological artifacts pose many problems. Independent Component Analysis (ICA) is a widely used algorithm for removing different artifacts from EEG signals. It separates data in linearly Independent Components (IC). However, the evaluation and classification of the calculated ICs as an EEG or artifact is not currently automated which requires manual intervention to reject ICs with visually detected artifacts after decomposition. In this paper, we propose a new automated approach for artifacts detection using the ICA algorithm. The best result of mean square error was achieved using SOBI-ICA (Second Order Blind Identification) and ADJUST algorithms. Compared with the existing automated solutions, our approach is not limited to electrode configurations, number of EEG channels, or specific types of artifacts. It provides a practical tool, reliable, automatic, and real-time capable, which avoids the need for the time-consuming manual selection of ICs during artifacts rejection.