Progress in neural networks for EEG signal recognition in 2021

TL;DR

This paper reviews recent advances in neural network applications for EEG signal recognition, highlighting key achievements, feature extraction techniques, and providing guidelines for reporting research in this domain.

Contribution

It offers a comprehensive summary of recent neural network models for EEG processing and provides recommendations for effectively presenting research results.

Findings

Neural networks have significantly advanced EEG signal processing.

Various models have been applied to extract features from EEG signals.

The paper discusses best practices for reporting EEG neural network research.

Abstract

In recent years, neural networks showed unprecedented growth that ultimately influenced dozens of different industries, including signal processing for the electroencephalography (EEG) process. Electroencephalography, although it appeared in the first half of the 20th century, was not changed the physical principles of work to this day. But signal processing technology made significant progress in this area through the use of neural networks. But many different models of neural networks complicate the process of understanding the real situation in this area. This manuscript summarizes the current state of knowledge on this topic, summarizes and describes the most significant achievements in various fields of application of neural networks for processing EEG signals. We discussed in detail the results presented in recent research papers for various fields in which EEG signals have been involved. We also examined in detail the process of extracting features from EEG signals using neural networks. In conclusion, we have provided recommendations for the correct demonstration of research results in manuscripts on the subject of neural networks and EEG.