Taxonomy on EEG Artifacts Removal Methods, Issues, and Healthcare Applications

Electroencephalogram (EEG) signals are progressively growing data widely known as biomedical big data, which is applied in biomedical and healthcare research. The measurement and processing of EEG signal result in the probability of signal contamination through artifacts which can obstruct the important features and information quality existing in the signal. To diagnose the human neurological diseases like epilepsy, tumors, and problems associated with trauma, these artifacts must be properly pruned assuring that there is no loss of the main attributes of EEG signals. In this paper, the latest and updated information in terms of important key features are arranged and tabulated extensively by considering the 60 published technical research papers based on EEG artifact removal method. Moreover, the paper is a review vision about the works in the area of EEG applied to healthcare and summarizes the challenges, research gaps, and opportunities to improve the EEG big data artifacts removal more precisely.

Automated summary

EEG signals are considered biomedical big data, but they can be contaminated by artifacts. Proper removal of artifacts is necessary for accurate diagnosis of neurological diseases. This paper reviews 60 technical research papers to summarize important key features in EEG artifact removal.