Artifact Elimination of Eeg Signals Based on Deep Learning: Survey

Abstract

Electroencephalogram (EEG) plays an important role in measuring human status and activities. EEG signals come from weak currents and are very vulnerable to artifact pollution, which affects the performance of many EEG tasks. It is crucial to develop methods that can effectively identify and remove artifacts. In the past, researchers have proposed a variety of methods to eliminate artifacts, but there is still no method to achieve the best effect. With the rapid development of deep learning, the new method has made excellent progress in eliminating artifacts. Compared with traditional methods, it is fast and can be automatically processed. This paper explores a new method to eliminate artifacts using deep learning technology. First, it discusses the characteristics and types of artifacts of EEG data, reviews the traditional elimination methods, then introduces the application of new and new methods of deep learning, and introduces the relevant data sets. In the future research, the method of artifact elimination relying on data automation has great potential.