MI-EEGNET: A novel convolutional neural network for motor imagery classification

BACKGROUND Brain-Computer Interfaces (BCI) permits humans to interact with machines by decoding brainwaves to command for a variety of purposes. Convolutional Neural Networks (ConvNet) have improved the state-of-the-art of Motor Imagery decoding in an end-to-end approach. However, shallow ConvNets usually perform better than their deep counterparts. Thus, we aim to design a novel ConvNet that is deeper than the existing models, with an increase in terms of performances, and with optimal complexity. NEW METHOD We develop a ConvNet based on Inception and Xception architectures that uses convolutional layers to extract temporal and spatial features. We adopt separable convolutions and depthwise convolutions to enable faster and efficient ConvNet. Then, we introduce a new block that is inspired by Inception to learn more rich features to improve the classification performances. RESULTS The obtained results are comparable with other state-of-the-art techniques. Also, the weights of the convolutional layers give us some insights onto the learned features and reveal the most relevant ones. COMPARISON WITH EXISTING METHOD(S) We show that our model significantly outperforms Filter Bank Common Spatial Pattern (FBCSP), Riemannian Geometry (RG) approaches, and ShallowConvNet (p<0.05). CONCLUSIONS The obtained results prove that Motor Imagery decoding is possible without handcrafted features.

[1]  Panagiotis K. Artemiadis,et al.  EEG feature descriptors and discriminant analysis under Riemannian Manifold perspective , 2018, Neurocomputing.

[2]  Yann LeCun,et al.  Comparing SVM and convolutional networks for epileptic seizure prediction from intracranial EEG , 2008, 2008 IEEE Workshop on Machine Learning for Signal Processing.

[3]  J. Pratt.  Remarks on Zeros and Ties in the Wilcoxon Signed Rank Procedures , 1959 .

[4]  Brent Lance,et al.  EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces , 2016, Journal of neural engineering.

[5]  Sidney Fels,et al.  Deep Learning the EEG Manifold for Phonological Categorization from Active Thoughts , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[6]  Sofia Ben Jebara,et al.  An Investigation of a Feature-Level Fusion for Noisy Speech Emotion Recognition , 2019, Comput..

[7]  R. Srikant,et al.  Why Deep Neural Networks for Function Approximation? , 2016, ICLR.

[8]  Sadasivan Puthusserypady,et al.  An Efficient Multi-Class MI Based BCI Scheme Using Statistical Fusion Techniques of Classifiers , 2019, TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON).

[9]  Jing Luo,et al.  Class discrepancy-guided sub-band filter-based common spatial pattern for motor imagery classification , 2019, Journal of Neuroscience Methods.

[10]  Toshihisa Tanaka,et al.  Fully Data-driven Convolutional Filters with Deep Learning Models for Epileptic Spike Detection , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[11]  Rabab K Ward,et al.  User-customized brain computer interfaces using Bayesian optimization , 2016, Journal of neural engineering.

[12]  Abdellah Adib,et al.  Performance evaluation of feature extraction techniques in MR-Brain image classification system , 2018 .

[13]  Abdellah Adib,et al.  Cross-Subject EEG Signal Classification with Deep Neural Networks Applied to Motor Imagery , 2019, MSPN.

[14]  Yang Li,et al.  A Channel-Projection Mixed-Scale Convolutional Neural Network for Motor Imagery EEG Decoding , 2019, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[15]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

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

[17]  Shuicheng Yan,et al.  Parallel convolutional-linear neural network for motor imagery classification , 2015, 2015 23rd European Signal Processing Conference (EUSIPCO).

[18]  Jaime Gómez Gil,et al.  Brain Computer Interfaces, a Review , 2012, Sensors.

[19]  Huiping Jiang,et al.  Classification of EEG Signal by STFT-CNN Framework: Identification of Right-/left-hand Motor Imagination in BCI Systems , 2017 .

[20]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[22]  Ad Aertsen,et al.  Review of the BCI Competition IV , 2012, Front. Neurosci..

[23]  Sadasivan Puthusserypady,et al.  An end-to-end deep learning approach to MI-EEG signal classification for BCIs , 2018, Expert Syst. Appl..

[24]  Min Wang,et al.  Augmenting The Size of EEG datasets Using Generative Adversarial Networks , 2018, 2018 International Joint Conference on Neural Networks (IJCNN).

[25]  Pheng-Ann Heng,et al.  Multiclass support matrix machine for single trial EEG classification , 2018, Neurocomputing.

[26]  Tiago H. Falk,et al.  Improved motor imagery brain-computer interface performance via adaptive modulation filtering and two-stage classification , 2020, Biomed. Signal Process. Control..

[27]  Lei Cao,et al.  Short time Fourier transformation and deep neural networks for motor imagery brain computer interface recognition , 2018, Concurr. Comput. Pract. Exp..

[28]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[29]  Clemens Brunner,et al.  Mu rhythm (de)synchronization and EEG single-trial classification of different motor imagery tasks , 2006, NeuroImage.

[30]  Wolfram Burgard,et al.  Deep learning with convolutional neural networks for EEG decoding and visualization , 2017, Human brain mapping.

[31]  Hubert Cecotti,et al.  Convolutional Neural Networks for P300 Detection with Application to Brain-Computer Interfaces , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[33]  Razvan Pascanu,et al.  On the difficulty of training recurrent neural networks , 2012, ICML.

[34]  Ayman Atia,et al.  Brain computer interfacing: Applications and challenges , 2015 .

[35]  Christian Jutten,et al.  Multiclass Brain–Computer Interface Classification by Riemannian Geometry , 2012, IEEE Transactions on Biomedical Engineering.

[36]  Athanasios V. Vasilakos,et al.  Brain computer interface: control signals review , 2017, Neurocomputing.

[37]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

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

[39]  Nandini Jog,et al.  Classification of Artefacts in EEG Signal Recordings and Overview of Removing Techniques , 2015 .

[40]  Christa Neuper,et al.  Movement and ERD/ERS , 2003 .

[41]  Li Wang,et al.  Temporal-spatial-frequency depth extraction of brain-computer interface based on mental tasks , 2020, Biomed. Signal Process. Control..

[42]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[43]  Hui Wang,et al.  A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry , 2018, Expert Syst. Appl..

[44]  François Chollet,et al.  Xception: Deep Learning with Depthwise Separable Convolutions , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[45]  Fengzhen Tang,et al.  Learning joint space-time-frequency features for EEG decoding on small labeled data , 2019, Neural Networks.

[46]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .