Higher order spectral regression discriminant analysis (HOSRDA): A tensor feature reduction method for ERP detection

Abstract Tensors are valuable tools to represent Electroencephalogram (EEG) data. Tucker decomposition is the most used tensor decomposition in multidimensional discriminant analysis and tensor extension of Linear Discriminant Analysis (LDA), called Higher Order Discriminant Analysis (HODA), is a popular tensor discriminant method used for analyzing Event Related Potentials (ERP). In this paper, we introduce a new tensor-based feature reduction technique, named Higher Order Spectral Regression Discriminant Analysis (HOSRDA), for use in a classification framework for ERP detection. The proposed method (HOSRDA) is a tensor extension of Spectral Regression Discriminant Analysis (SRDA) and casts the eigenproblem of HODA to a regression problem. The formulation of HOSRDA can open a new framework for adding different regularization constraints in higher order feature reduction problem. Additionally, when the dimension and number of samples is very large, the regression problem can be solved via efficient iterative algorithms. We applied HOSRDA on data of a P300 speller from BCI competition III and reached average character detection accuracy of 96.5% for the two subjects. HOSRDA outperforms almost all of other reported methods on this dataset. Additionally, the results of our method are fairly comparable with those of other methods when 5 and 10 repetitions are used in the P300 speller paradigm.

[1]  Andrzej Cichocki,et al.  Nonnegative Matrix and Tensor Factorizations : An algorithmic perspective , 2014, IEEE Signal Processing Magazine.

[2]  Lars Kai Hansen,et al.  Shift-invariant multilinear decomposition of neuroimaging data , 2008, NeuroImage.

[3]  Heikki Lyytinen,et al.  Benefits of Multi-Domain Feature of mismatch Negativity Extracted by Non-Negative Tensor Factorization from EEG Collected by Low-Density Array , 2012, Int. J. Neural Syst..

[4]  S. Huffel,et al.  Neonatal seizure localization using PARAFAC decomposition , 2009, Clinical Neurophysiology.

[5]  Joachim Möcks,et al.  Decomposing event-related potentials: A new topographic components model , 1988, Biological Psychology.

[6]  Xingyu Wang,et al.  Multiway Canonical Correlation Analysis for Frequency Components Recognition in SSVEP-Based BCIs , 2011, ICONIP.

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

[8]  Xingyu Wang,et al.  Frequency Recognition in SSVEP-Based BCI using Multiset Canonical Correlation Analysis , 2013, Int. J. Neural Syst..

[9]  Francisco Sepulveda,et al.  Wavelets and ensemble of FLDs for P300 classification , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[10]  Arthur Tenenhaus,et al.  Discriminant Analysis for Multiway Data , 2014 .

[11]  Xingyu Wang,et al.  Sparse Bayesian multiway canonical correlation analysis for EEG pattern recognition , 2017, Neurocomputing.

[12]  G. Pfurtscheller,et al.  The BCI competition III: validating alternative approaches to actual BCI problems , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[13]  Andrzej Cichocki,et al.  L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[14]  Andrzej Cichocki,et al.  Linked Component Analysis From Matrices to High-Order Tensors: Applications to Biomedical Data , 2015, Proceedings of the IEEE.

[15]  Jian Yang,et al.  Sparse tensor discriminant analysis , 2013, IEEE Transactions on Image Processing.

[16]  Rasmus Bro,et al.  Multiway analysis of epilepsy tensors , 2007, ISMB/ECCB.

[17]  L. Trefethen,et al.  Numerical linear algebra , 1997 .

[18]  Xiaoou Tang,et al.  Tensor linear Laplacian discrimination (TLLD) for feature extraction , 2009, Pattern Recognit..

[19]  Tamara G. Kolda,et al.  Categories and Subject Descriptors: G.4 [Mathematics of Computing]: Mathematical Software— , 2022 .

[20]  E. W. Sellers,et al.  Toward enhanced P300 speller performance , 2008, Journal of Neuroscience Methods.

[21]  Daniel Graupe,et al.  Topographic component (Parallel Factor) analysis of multichannel evoked potentials: Practical issues in trilinear spatiotemporal decomposition , 2005, Brain Topography.

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

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

[24]  L. Manuelidis,et al.  Bevelled Dual-Channel Microelectrodes , 1974 .

[25]  Xuelong Li,et al.  Discriminant Locally Linear Embedding With High-Order Tensor Data , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[26]  Liqing Zhang,et al.  Noninvasive BCIs: Multiway Signal-Processing Array Decompositions , 2008, Computer.

[27]  Michael A. Saunders,et al.  LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares , 1982, TOMS.

[28]  A. Cichocki,et al.  Tensor decompositions for feature extraction and classification of high dimensional datasets , 2010 .

[29]  Lars Kai Hansen,et al.  ERPWAVELAB A toolbox for multi-channel analysis of time–frequency transformed event related potentials , 2007, Journal of Neuroscience Methods.

[30]  Sepideh Hajipour Sardouie,et al.  Canonical Polyadic decomposition of complex-valued multi-way arrays based on Simultaneous Schur Decomposition , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[31]  Xiaofeng Gong,et al.  Tensor decomposition of EEG signals: A brief review , 2015, Journal of Neuroscience Methods.

[32]  Dong Xu,et al.  Discriminant analysis with tensor representation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[33]  E. Donchin,et al.  Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. , 1988, Electroencephalography and clinical neurophysiology.

[34]  Tapani Ristaniemi,et al.  Multi-Domain Feature Extraction for Small Event-Related potentials through Nonnegative Multi-Way Array Decomposition from Low Dense Array EEG , 2013, Int. J. Neural Syst..

[35]  Pierre Comon,et al.  Blind source separation of underdetermined mixtures of event-related sources , 2014, Signal Process..

[36]  Dan Schonfeld,et al.  Multilinear Discriminant Analysis for Higher-Order Tensor Data Classification , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Haiping Lu,et al.  A survey of multilinear subspace learning for tensor data , 2011, Pattern Recognit..

[38]  E. Donchin,et al.  The mental prosthesis: Assessing the speed of a brain-computer interface , 1998 .

[39]  Alain Rakotomamonjy,et al.  BCI Competition III: Dataset II- Ensemble of SVMs for BCI P300 Speller , 2008, IEEE Transactions on Biomedical Engineering.

[40]  Feiping Nie,et al.  Extracting the optimal dimensionality for local tensor discriminant analysis , 2009, Pattern Recognit..

[41]  J. Mocks,et al.  Topographic components model for event-related potentials and some biophysical considerations , 1988, IEEE Transactions on Biomedical Engineering.

[42]  Xingyu Wang,et al.  Fast nonnegative tensor factorization based on accelerated proximal gradient and low-rank approximation , 2016, Neurocomputing.

[43]  Patrick Dupont,et al.  Canonical decomposition of ictal scalp EEG reliably detects the seizure onset zone , 2007, NeuroImage.

[44]  Tapani Ristaniemi,et al.  Feature Extraction by Nonnegative Tucker Decomposition from EEG Data Including Testing and Training Observations , 2012, ICONIP.

[45]  Andrzej Cichocki,et al.  Nonnegative Tensor Factorization for Continuous EEG Classification , 2007, Int. J. Neural Syst..

[46]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[47]  Johan Wagemans,et al.  Single trial ERP reading based on parallel factor analysis. , 2013, Psychophysiology.

[48]  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.

[49]  Wim Van Paesschen,et al.  Block term decomposition for modelling epileptic seizures , 2014, EURASIP J. Adv. Signal Process..

[50]  Andrzej Cichocki,et al.  Group Component Analysis for Multiblock Data: Common and Individual Feature Extraction , 2012, IEEE Transactions on Neural Networks and Learning Systems.

[51]  Andrzej Cichocki,et al.  Tensor Decompositions for Signal Processing Applications: From two-way to multiway component analysis , 2014, IEEE Signal Processing Magazine.

[52]  Jie Li,et al.  A Prior Neurophysiologic Knowledge Free Tensor-Based Scheme for Single Trial EEG Classification , 2009, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

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

[54]  Evangelia Pippa,et al.  EEG-based Classification of Epileptic and Non-Epileptic Events using Multi-Array Decomposition , 2016, Int. J. Monit. Surveillance Technol. Res..

[55]  Andrzej Cichocki,et al.  Tensor classification for P300-based brain computer interface , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[56]  Jiawei Han,et al.  SRDA: An Efficient Algorithm for Large-Scale Discriminant Analysis , 2008, IEEE Transactions on Knowledge and Data Engineering.