Improving the separability of multiple EEG features for a BCI by neural-time-series-prediction-preprocessing

Abstract A recently proposed method for EEG preprocessing is extended and analyzed in this work via a range of different tests in combination with various other BCI components. Neural-time-series-prediction-processing (NTSPP) is a predictive approach to EEG preprocessing where prediction models (PMs) are trained to perform one-step-ahead prediction of the EEG times-series which reflect motor imagery induced alterations in neuronal activity. Due to the specialization of distinct PMs, the predicted signals (Ys) and error signals (Es) are distinctly different from the original (Os) signals. The PMs map the Os signals to a higher dimension which, in the majority of cases, produces features that are more separable than those produced by the Os signals. Four feature extraction procedures, ranging in complexity and in terms of the information which is extracted i.e., time domain, frequency domain and time–frequency ( t – f ) domain, are used to determine the separability enhancements which are verified by comparative statistical tests and brain–computer interface (BCI) tests on six subjects. It is shown that, in the majority of the tests, features extracted from the NTSPP signals are more separable than those extracted from the Os signals, in terms of increased Euclidean distance between class means, reduced inter-class correlations and intra-class variance, and higher classification accuracy (CA), information transfer (IT) rate and mutual information (MI).

[1]  G. R. Muller,et al.  Brain oscillations control hand orthosis in a tetraplegic , 2000, Neuroscience Letters.

[2]  Karla Felix Navarro,et al.  A Comprehensive Survey of Brain Interface Technology Designs , 2007, Annals of Biomedical Engineering.

[3]  G. Williams.  Chaos theory tamed , 1997 .

[4]  B. Everitt,et al.  Applied Multivariate Data Analysis. , 1993 .

[5]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[6]  G. Pfurtscheller,et al.  Conversion of EEG activity into cursor movement by a brain-computer interface (BCI) , 2004, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  G Pfurtscheller,et al.  Estimating the Mutual Information of an EEG-based Brain-Computer Interface , 2002, Biomedizinische Technik. Biomedical engineering.

[8]  G Pfurtscheller,et al.  Real-time EEG analysis with subject-specific spatial patterns for a brain-computer interface (BCI). , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[9]  G Pfurtscheller,et al.  Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters. , 1998, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[10]  T.M. McGinnity,et al.  A time-series prediction approach for feature extraction in a brain-computer interface , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[11]  T. Martin McGinnity,et al.  A Time-Frequency Approach to Feature Extraction for a Brain-Computer Interface with a Comparative Analysis of Performance Measures , 2005, EURASIP J. Adv. Signal Process..

[12]  Xin Yao,et al.  Simultaneous training of negatively correlated neural networks in an ensemble , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[13]  Girijesh Prasad,et al.  Improving signal separability and inter-session stability of a motor imagery-based brain-computer interface by neural-time-series-prediction-preprocessing , 2005 .

[14]  T. Martin McGinnity,et al.  Faster Self-Organizing Fuzzy Neural Network Training and a Hyperparameter Analysis for a Brain–Computer Interface , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  N. Birbaumer,et al.  The thought translation device: a neurophysiological approach to communication in total motor paralysis , 1999, Experimental Brain Research.

[16]  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.

[17]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[18]  T. Martin McGinnity,et al.  A multi-class brain-computer interface with SOFNN-based prediction preprocessing , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[19]  Rabab K Ward,et al.  A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals , 2007, Journal of neural engineering.

[20]  Christa Neuper,et al.  An asynchronously controlled EEG-based virtual keyboard: improvement of the spelling rate , 2004, IEEE Transactions on Biomedical Engineering.

[21]  Steven Lemm,et al.  BCI competition 2003-data set III: probabilistic modeling of sensorimotor /spl mu/ rhythms for classification of imaginary hand movements , 2004, IEEE Transactions on Biomedical Engineering.

[22]  G. Pfurtscheller,et al.  Rapid prototyping of an EEG-based brain-computer interface (BCI) , 2001, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[23]  D.J. McFarland,et al.  Sensorimotor rhythm-based brain-computer interface (BCI): feature selection by regression improves performance , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[24]  Leon D. Iasemidis,et al.  Epileptic seizure prediction and control , 2003, IEEE Transactions on Biomedical Engineering.

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

[26]  N. Birbaumer,et al.  Self-initiation of EEG-based communication in paralyzed patients , 2001, Clinical Neurophysiology.

[27]  Xin Yao,et al.  Making use of population information in evolutionary artificial neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part B.

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

[29]  G Pfurtscheller,et al.  Adaptive Autoregressive Modeling used for Single-trial EEG Classification - Verwendung eines Adaptiven Autoregressiven Modells für die Klassifikation von Einzeltrial-EEG-Daten , 1997, Biomedizinische Technik. Biomedical engineering.

[30]  Jonathan R Wolpaw,et al.  Guest Editorial The Third International Meeting on Brain-Computer Interface Technology: Making a Difference , 2006, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[31]  Girijesh Prasad,et al.  Using motor imagery based brain-computer interface for post-stroke rehabilitation , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[32]  Bruce J. Fisch,et al.  Fisch and Spehlmann's Eeg Primer: Basic Principles of Digital and Analog Eeg , 1999 .

[33]  G Pfurtscheller,et al.  EEG-based communication: improved accuracy by response verification. , 1998, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[34]  Charles Markham,et al.  A Concept for Extending the Applicability of Constraint-Induced Movement Therapy through Motor Cortex Activity Feedback Using a Neural Prosthesis , 2007, Comput. Intell. Neurosci..

[35]  Girijesh Prasad,et al.  Estimating the Predictability of EEG Recorded Over the Motor Cortex using Information Theoretical Functionals , 2004 .