Current Trends, Challenges, and Future Research Directions of Hybrid and Deep Learning Techniques for Motor Imagery Brain–Computer Interface

Abstract

The field of brain–computer interface (BCI) enables us to establish a pathway between the human brain and computers, with applications in the medical and nonmedical field. Brain computer interfaces can have a significant impact on the way humans interact with machines. In recent years, the surge in computational power has enabled deep learning algorithms to act as a robust avenue for leveraging BCIs. This paper provides an up-to-date review of deep and hybrid deep learning techniques utilized in the field of BCI through motor imagery. It delves into the adoption of deep learning techniques, including convolutional neural networks (CNNs), autoencoders (AEs), and recurrent structures such as long short-term memory (LSTM) networks. Moreover, hybrid approaches, such as combining CNNs with LSTMs or AEs and other techniques, are reviewed for their potential to enhance classification performance. Finally, we address challenges within motor imagery BCIs and highlight further research directions in this emerging field.

Enhancing Classification Accuracy with Integrated Contextual Gate Network: Deep Learning Approach for Functional Near-Infrared Spectroscopy Brain–Computer Interface Application

“…In the ICGN cell, three gates and an internal cell state similar to those in LSTM are introduced. Input, forget, and output gates are sigmoid activation functions of the current input values, previous hidden state, previous cell state, and biased values presented in Equations ( 8)- (10), respectively. The internal cell state is a hyperbolic tangent activation function of the current input values, previous hidden state, and previous cell state presented in Equation (11).…”

“…Until now, to record the motor activity of humans, modalities such as electroencephalography (EEG) [4][5][6][7][8], functional magnetic resonance imaging (fMRI) [9,10], positron emission tomography (PET), and functional near-infrared spectroscopy (fNIRS) [10][11][12][13] have been introduced, along with their decoding algorithms. EEG is designed to acquire a complex set of signals from the brain based on the potential difference created by neuronal signal conduction in the brain.…”