Deep learning for motor imagery EEG-based classification: A review

• Published in: Biomedical signal processing and control Vol. 63; p. 102172
• Main Authors: Al-Saegh, Ali, Dawwd, Shefa A., Abdul-Jabbar, Jassim M.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.01.2021
• Subjects: BCI; Deep learning; Deep neural network; EEG; Motor imagery; VEP; DNN; ELM; DL; CPU; WPD; GPU; ELU; Deep learning; 1d-AX; ADAM; DBN; RNN; FFT; ULM; SSVEP; RBM; EMD; PSD; BSS; AE; HGD; EEG; BCI; moVEP; PSO; PCA; AAR; Deep neural network; ERD; SAE; ReLU; FC; CNN; ERP; ERS; STFT; GRU; CWD; BGRU; EOG; FBCSP; GD; CSP; CWT; fNIRS; LSTM; ICA; Motor imagery; SGD; VAE; SELU
• ISSN: 1746-8094; 1746-8108
• DOI: 10.1016/j.bspc.2020.102172

The availability of large and varied Electroencephalogram (EEG) datasets, rapidly advances and inventions in deep learning techniques, and highly powerful and diversified computing systems have all permitted to easily analyzing those datasets and discovering vital information within. However, the classification process of EEG signals and discovering vital information should be robust, automatic, and with high accuracy. Motor Imagery (MI) EEG has attracted us due to its significant applications in daily life. This paper attempts to achieve those goals throughout a systematic review of the state-of-the-art studies within this field of research. The process began by intensely surfing the well-known specialized digital libraries and, as a result, 40 related papers were gathered. The papers were scrutinized upon multiple noteworthy technical issues, among them deep neural network architecture, input formulation, number of MI EEG tasks, and frequency range of interest. Deep neural networks build robust and automated systems for the classification of MI EEG recordings by exploiting the whole input data throughout learning salient features. Specifically, convolutional neural networks (CNN) and hybrid-CNN (h-CNN) are the dominant architectures with high performance in comparison to public datasets with other types of architectures. The MI related datasets, input formulation, frequency ranges, and preprocessing and regularization methods were also reviewed. This review gives the required preliminaries in developing MI EEG-based BCI systems. The review process of the published articles in the last five years aims to help in choosing the appropriate deep neural network architecture and other hyperparameters for developing those systems.