Research Article
Chessboard EEG Images Classification for BCI Systems Using Deep Neural Network
@INPROCEEDINGS{10.1007/978-3-030-57115-3_8, author={Ward Fadel and Moutz Wahdow and Csaba Kollod and Gergely Marton and Istvan Ulbert}, title={Chessboard EEG Images Classification for BCI Systems Using Deep Neural Network}, proceedings={Bio-inspired Information and Communication Technologies. 12th EAI International Conference, BICT 2020, Shanghai, China, July 7-8, 2020, Proceedings}, proceedings_a={BICT}, year={2020}, month={8}, keywords={Brain Computer Interface (BCI) Electroencephalography (EEG) Classification Motor imagery Convolutional Neural Networks (CNN) Long Short Term Memory (LSTM)}, doi={10.1007/978-3-030-57115-3_8} }- Ward Fadel
Moutz Wahdow
Csaba Kollod
Gergely Marton
Istvan Ulbert
Year: 2020
Chessboard EEG Images Classification for BCI Systems Using Deep Neural Network
BICT
Springer
DOI: 10.1007/978-3-030-57115-3_8
Abstract
Classification of electroencephalography (EEG) signals is a fundamental issue of Brain Computer Interface (BCI) systems, and deep learning techniques are still under investigation although they are dominant in other fields like computer vision and natural language processing. In this paper, we introduce the chessboard image transformation method in which the motor imagery EEG signals were transformed into images in order to be classified using a hybrid deep learning model. The EEG motor movement/imagery Physionet dataset was used and the Motor Imagery (MI) signals for two frequency bands (Mu [8–13 Hz] and Beta [13–30 Hz]) were transformed into 2-channel images (one channel for each band). The network model consists of Deep Convolutional Neural Network (DCNN) to extract the spatial and frequency features followed by Long Short Term Memory (LSTM) to extract temporal features and then finally to be classified into 5 different classes (4 motor imagery tasks and one rest). The results were promising with 68.72% classification accuracy for the chessboard approach compared to 68.13% for the azimuthal projection with Clough-Tocher interpolation (2-bands scenario) and to 64.64% average accuracy for a baseline method, i.e., Support Vector Machine (SVM).
