Tensor Discriminant Analysis for MI-EEG Signal Classification Using Convolutional Neural Network

Motor Imagery (MI) is a typical paradigm for Brain-Computer Interface (BCI) system. In this paper, we propose a new framework by introducing a tensor-based feature representation of the data and also utilizing a convolutional neural network (CNN) architecture for performing classification of MI-EEG signal. The tensor-based representation that includes the structural information in multi-channel time-varying EEG spectrum is generated from tensor discriminant analysis (TDA), and CNN is designed and optimized accordingly for this representation. Compared with CSP+SVM (the conventional framework which is the most successful in MI-based BCI) in the applications to the BCI competition III-IVa dataset, the proposed framework has the following advantages: (1) the most discriminant patterns can be obtained by applying optimum selection of spatial-spectral-temporal subspace for each subject; (2) the corresponding CNN can take full advantage of tensor-based representation and identify discriminative characteristics robustly. The results demonstrate that our framework can further improve classification performance and has great potential for the practical application of BCI.

[1]  Shuicheng Yan,et al.  Learning Temporal Information for Brain-Computer Interface Using Convolutional Neural Networks , 2018, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Ugur Halici,et al.  A novel deep learning approach for classification of EEG motor imagery signals , 2017, Journal of neural engineering.

[3]  Klaus-Robert Müller,et al.  The non-invasive Berlin Brain–Computer Interface: Fast acquisition of effective performance in untrained subjects , 2007, NeuroImage.

[4]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[5]  Fumikazu Miwakeichi,et al.  Decomposing EEG data into space–time–frequency components using Parallel Factor Analysis , 2004, NeuroImage.

[6]  G. Pfurtscheller,et al.  Motor imagery activates primary sensorimotor area in humans , 1997, Neuroscience Letters.

[7]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorization T , 2007 .

[8]  William Z Rymer,et al.  Guest Editorial Brain–Computer Interface Technology: A Review of the Second International Meeting , 2001 .

[9]  J. Q. Gan,et al.  Multiresolution analysis over simple graphs for brain computer interfaces , 2013, Journal of neural engineering.

[10]  Liqing Zhang,et al.  Regularized tensor discriminant analysis for single trial EEG classification in BCI , 2010, Pattern Recognit. Lett..

[11]  Xuelong Li,et al.  General Tensor Discriminant Analysis and Gabor Features for Gait Recognition , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Miguel P. Eckstein,et al.  Single-Trial Classification of Event-Related Potentials in Rapid Serial Visual Presentation Tasks Using Supervised Spatial Filtering , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Xingyu Wang,et al.  Spatial-Temporal Discriminant Analysis for ERP-Based Brain-Computer Interface , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[14]  Howida A. Shedeed,et al.  A CSP\AM-BA-SVM Approach for Motor Imagery BCI System , 2018, IEEE Access.

[15]  Z J Koles,et al.  The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. , 1991, Electroencephalography and clinical neurophysiology.

[16]  Cuntai Guan,et al.  Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b , 2012, Front. Neurosci..

[17]  Gert Pfurtscheller,et al.  Motor imagery and direct brain-computer communication , 2001, Proc. IEEE.