An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces

• Published in: Biomedical signal processing and control Vol. 74; p. 103496
• Main Author: Roy, Arunabha M.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2022
• Subjects: Brain-computer interfaces (BCIs); Convolutional neural network (CNN); Electroencephalogram (EEG); Feature extraction; Motor imagery (MI); Signal classification; Motor imagery (MI); Feature extraction; Electroencephalogram (EEG); Convolutional neural network (CNN); Signal classification; Brain-computer interfaces (BCIs)

•An efficient multi-scale CNN(MS-CNN) model has been proposed with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces.•Muti-scale convolution block (MSCB) has been designed which can extract the distinguishable features of several non-overlapping c...