A novel decoding method for motor imagery tasks with 4D data representation and 3D convolutional neural networks

• Published in: Journal of neural engineering Vol. 18; no. 4; pp. 46029 - 46048
• Main Authors: Li, Ming-ai, Ruan, Zi-wei
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 01.08.2021
• Subjects: 4D dipole feature matrix; convolutional neural network; data representation; EEG source imaging; motor imagery EEG; time of interest; motor imagery EEG; data representation; EEG source imaging; 4D dipole feature matrix; convolutional neural network; time of interest

Objective . Motor imagery electroencephalography (MI-EEG) produces one of the most commonly used biosignals in intelligent rehabilitation systems. The newly developed 3D convolutional neural network (3DCNN) is gaining increasing attention for its ability to recognize MI tasks. The key to successful...