Dynamic frequency feature selection based approach for classification of motor imageries

Electroencephalography (EEG) is one of the most popular techniques to record the brain activities such as motor imagery, which is of low signal-to-noise ratio and could lead to high classification error. Therefore, selection of the most discriminative features could be crucial to improve the classification performance. However, the traditional feature selection methods employed in brain-computer interface (BCI) field (e.g. Mutual Information-based Best Individual Feature (MIBIF), Mutual Information-based Rough Set Reduction (MIRSR) and cross-validation) mainly focus on the overall performance on all the trials in the training set, and thus may have very poor performance on some specific samples, which is not acceptable. To address this problem, a novel sequential forward feature selection approach called Dynamic Frequency Feature Selection (DFFS) is proposed in this paper. The DFFS method emphasized the importance of the samples that got misclassified while only pursuing high overall classification performance. In the DFFS based classification scheme, the EEG data was first transformed to frequency domain using Wavelet Packet Decomposition (WPD), which is then employed as the candidate set for further discriminatory feature selection. The features are selected one by one in a boosting manner. After one feature being selected, the importance of the correctly classified samples based on the feature will be decreased, which is equivalent to increasing the importance of the misclassified samples. Therefore, a complement feature to the current features could be selected in the next run. The selected features are then fed to a classifier trained by random forest algorithm. Finally, a time series voting-based method is utilized to improve the classification performance. Comparisons between the DFFS-based approach and state-of-art methods on BCI competition IV data set 2b have been conducted, which have shown the superiority of the proposed algorithm.

[1]  Zuren Feng,et al.  Structure constrained semi-nonnegative matrix factorization for EEG-based motor imagery classification , 2015, Comput. Biol. Medicine.

[2]  Ingrid Daubechies,et al.  The wavelet transform, time-frequency localization and signal analysis , 1990, IEEE Trans. Inf. Theory.

[3]  B. Hjorth The physical significance of time domain descriptors in EEG analysis. , 1973, Electroencephalography and clinical neurophysiology.

[4]  Klaus-Robert Müller,et al.  Neurophysiological predictor of SMR-based BCI performance , 2010, NeuroImage.

[5]  Klaus-Robert Müller,et al.  Spatio-spectral filters for improving the classification of single trial EEG , 2005, IEEE Transactions on Biomedical Engineering.

[6]  R. Ilmoniemi,et al.  Magnetoencephalography-theory, instrumentation, and applications to noninvasive studies of the working human brain , 1993 .

[7]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[8]  Christoph Lehmann,et al.  Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG) , 2007, Journal of Neuroscience Methods.

[9]  Y. Kim,et al.  Classification of prefrontal and motor cortex signals for three-class fNIRS–BCI , 2015, Neuroscience Letters.

[10]  Girijesh Prasad,et al.  Bispectrum-based feature extraction technique for devising a practical brain–computer interface , 2011, Journal of neural engineering.

[11]  Klaus-Robert Müller,et al.  Enhanced Performance by a Hybrid Nirs–eeg Brain Computer Interface , 2022 .

[12]  Klaus-Robert Müller,et al.  Combined Optimization of Spatial and Temporal Filters for Improving Brain-Computer Interfacing , 2006, IEEE Transactions on Biomedical Engineering.

[13]  G. Pfurtscheller,et al.  Brain–Computer Communication: Motivation, Aim, and Impact of Exploring a Virtual Apartment , 2007, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

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

[15]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[16]  K. Jellinger Toward Brain-Computer Interfacing , 2009 .

[17]  Na Lu,et al.  Motor imagery classification via combinatory decomposition of ERP and ERSP using sparse nonnegative matrix factorization , 2015, Journal of Neuroscience Methods.

[18]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[19]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[20]  Yan Cui,et al.  An adaptive feature extraction method in BCI-based rehabilitation , 2015, J. Intell. Fuzzy Syst..

[21]  Anton Nijholt,et al.  Turning Shortcomings into Challenges: Brain-Computer Interfaces for Games , 2009, INTETAIN.

[22]  Benjamin Blankertz,et al.  MATHEMATICAL ENGINEERING TECHNICAL REPORTS Spectrally weighted Common Spatial Pattern algorithm for single trial EEG classification , 2006 .

[23]  M. Fox,et al.  Spontaneous fluctuations in brain activity observed with functional magnetic resonance imaging , 2007, Nature Reviews Neuroscience.

[24]  P. Comon,et al.  Ica: a potential tool for bci systems , 2008, IEEE Signal Processing Magazine.

[25]  Keum-Shik Hong,et al.  Decoding Answers to Four-Choice Questions Using Functional near Infrared Spectroscopy , 2015 .

[26]  Seungjin Choi,et al.  A hybrid NIRS-EEG system for self-paced brain computer interface with online motor imagery , 2015, Journal of Neuroscience Methods.

[27]  B. Hjorth EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[28]  Keum-Shik Hong,et al.  Passive BCI based on drowsiness detection: an fNIRS study. , 2015, Biomedical optics express.

[29]  M. Hallett,et al.  Classifying EEG signals preceding right hand, left hand, tongue, and right foot movements and motor imageries , 2008, Clinical Neurophysiology.

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

[31]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[32]  G. Pfurtscheller,et al.  An SSVEP BCI to Control a Hand Orthosis for Persons With Tetraplegia , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[33]  Mark Hallett,et al.  Left parietal activation related to planning, executing and suppressing praxis hand movements , 2009, Clinical Neurophysiology.

[34]  F. L. D. Silva,et al.  Event-related EEG/MEG synchronization and desynchronization: basic principles , 1999, Clinical Neurophysiology.

[35]  Yan Guozheng,et al.  EEG feature extraction based on wavelet packet decomposition for brain computer interface , 2008 .

[36]  Yijun Wang,et al.  Common Spatial Pattern Method for Channel Selelction in Motor Imagery Based Brain-computer Interface , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[37]  Siamac Fazli,et al.  Subject-dependent classification for robust idle state detection using multi-modal neuroimaging and data-fusion techniques in BCI , 2015, Pattern Recognit..

[38]  Niels Birbaumer,et al.  Brain–computer-interface research: Coming of age , 2006, Clinical Neurophysiology.

[39]  Gary E. Birch,et al.  A wavelet-based approach for the extraction of event related potentials from EEG , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[40]  Natheer Khasawneh,et al.  Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier , 2012, Comput. Methods Programs Biomed..

[41]  Anton Nijholt,et al.  Turning Shortcomings into Challenges: Brain-Computer Interfaces for Games , 2009, INTETAIN.

[42]  R. Leeb,et al.  BCI Competition 2008 { Graz data set B , 2008 .

[43]  Keum-Shik Hong,et al.  fNIRS-based brain-computer interfaces: a review , 2015, Front. Hum. Neurosci..

[44]  Ernst Fernando Lopes Da Silva Niedermeyer,et al.  Electroencephalography, basic principles, clinical applications, and related fields , 1982 .

[45]  Sifis Micheloyannis,et al.  Use of ANN and Hjorth parameters in mental-task discrimination , 2000 .

[46]  Keum-Shik Hong,et al.  Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain–computer interface , 2013, Neuroscience Letters.

[47]  Fernando Lopes da Silva,et al.  Comprar Niedermeyer's Electroencephalography, 6/e (Basic Principles, Clinical Applications, and Related Fields ) | Fernando Lopes Da Silva | 9780781789424 | Lippincott Williams & Wilkins , 2010 .

[48]  P. E. Tikkanen,et al.  Nonlinear wavelet and wavelet packet denoising of electrocardiogram signal , 1999, Biological Cybernetics.

[49]  Jun Zhang,et al.  A Target Guided Subband Filter for Acoustic Event Detection in Noisy Environments Using Wavelet Packets , 2015, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[50]  T. Martin McGinnity,et al.  Quantum Neural Network-Based EEG Filtering for a Brain–Computer Interface , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[51]  Müjdat Çetin,et al.  A latent discriminative model-based approach for classification of imaginary motor tasks from EEG data , 2012, Journal of neural engineering.

[52]  V. Gallese,et al.  Time course and specificity of sensory-motor alpha modulation during the observation of hand motor acts and gestures: a high density EEG study , 2010, Experimental Brain Research.

[53]  K.-R. Muller,et al.  Optimizing Spatial filters for Robust EEG Single-Trial Analysis , 2008, IEEE Signal Processing Magazine.

[54]  Keum-Shik Hong,et al.  Decoding of four movement directions using hybrid NIRS-EEG brain-computer interface , 2014, Front. Hum. Neurosci..