An end-to-end deep learning approach to MI-EEG signal classification for BCIs

作者：

Highlights：

• End-to-end neural network model for classifying motor imagery EEG signals.

• Using 1-D CNN layers to learn temporal and spatial filters for feature extraction.

• Application of transfer learning to calibrate the model for individual subjects.

• Analysis of the temporal and spatial filters learned by the model.

摘要

•End-to-end neural network model for classifying motor imagery EEG signals.•Using 1-D CNN layers to learn temporal and spatial filters for feature extraction.•Application of transfer learning to calibrate the model for individual subjects.•Analysis of the temporal and spatial filters learned by the model.

论文关键词：Deep learning (DL),Electroencephalogram (EEG),Motor imagery (MI),Convolutional neural networks (CNNs),Brain computer interface (BCI),Stroke rehabilitation

论文评审过程：Received 4 June 2018, Revised 31 July 2018, Accepted 14 August 2018, Available online 21 August 2018, Version of Record 2 September 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.08.031