Asynchronous decoding of finger movements from ECoG signals using long-range dependencies conditional random fields.

OBJECTIVE In this work we propose the use of conditional random fields with long-range dependencies for the classification of finger movements from electrocorticographic recordings. APPROACH The proposed method uses long-range dependencies taking into consideration time-lags between the brain activity and the execution of the motor task. In addition, the proposed method models the dynamics of the task executed by the subject and uses information about these dynamics as prior information during the classification stage. MAIN RESULTS The results show that incorporating temporal information about the executed task as well as incorporating long-range dependencies between the brain signals and the labels effectively increases the system's classification performance compared to methods in the state of art. SIGNIFICANCE The method proposed in this work makes use of probabilistic graphical models to incorporate temporal information in the classification of finger movements from electrocorticographic recordings. The proposed method highlights the importance of including prior information about the task that the subjects execute. As the results show, the combination of these two features effectively produce a significant improvement of the system's classification performance.

[1]  E. Niebur,et al.  Neural Correlates of High-Gamma Oscillations (60–200 Hz) in Macaque Local Field Potentials and Their Potential Implications in Electrocorticography , 2008, The Journal of Neuroscience.

[2]  D J Weber,et al.  Human motor cortical activity recorded with Micro-ECoG electrodes, during individual finger movements , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  Müjdat Çetin,et al.  Word-level language modeling for P300 spellers based on discriminative graphical models , 2015, Journal of neural engineering.

[4]  Alain Rakotomamonjy,et al.  Algorithms for Multiple Basis Pursuit Denoising , 2009 .

[5]  Gerwin Schalk,et al.  Rapid Communication with a “P300” Matrix Speller Using Electrocorticographic Signals (ECoG) , 2010, Front. Neurosci..

[6]  G. Schalk,et al.  Brain-Computer Interfaces Using Electrocorticographic Signals , 2011, IEEE Reviews in Biomedical Engineering.

[7]  Gerwin Schalk,et al.  Prior Knowledge Improves Decoding of Finger Flexion from Electrocorticographic Signals , 2011, Front. Neurosci..

[8]  Jason Farquhar,et al.  Graphical models for decoding in BCI visual speller systems , 2009, 2009 4th International IEEE/EMBS Conference on Neural Engineering.

[9]  Christa Neuper,et al.  Hidden Markov models for online classification of single trial EEG data , 2001, Pattern Recognit. Lett..

[10]  Christoph Guger,et al.  An electrocorticographic BCI using code-based VEP for control in video applications: a single-subject study , 2014, Front. Syst. Neurosci..

[11]  Müjdat Çetin,et al.  Hidden conditional random fields for classification of imaginary motor tasks from EEG data , 2011, 2011 19th European Signal Processing Conference.

[12]  Gerwin Schalk,et al.  A brain–computer interface using electrocorticographic signals in humans , 2004, Journal of neural engineering.

[13]  Mujdat Cetin,et al.  Discriminative Methods for Classification of Asynchronous Imaginary Motor Tasks From EEG Data , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[14]  Terrence J. Sejnowski,et al.  Toward Brain-Computer Interfacing (Neural Information Processing) , 2007 .

[15]  Alain Rakotomamonjy,et al.  Decoding Finger Movements from ECoG Signals Using Switching Linear Models , 2011, Front. Neurosci..

[16]  J. Wolpaw,et al.  Decoding two-dimensional movement trajectories using electrocorticographic signals in humans , 2007, Journal of neural engineering.

[17]  Robert Frysch,et al.  Hidden Markov model and support vector machine based decoding of finger movements using electrocorticography , 2013, Journal of neural engineering.

[18]  Panagiotis D. Bamidis,et al.  Comparing Sensorimotor Cortex Activation during Actual and Imaginary Movement , 2010 .

[19]  Guillaume Charvet,et al.  CLINATEC® BCI platform based on the ECoG-recording implant WIMAGINE® and the innovative signal-processing: Preclinical results , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

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

[21]  Ke Liao,et al.  Decoding Individual Finger Movements from One Hand Using Human EEG Signals , 2014, PloS one.

[22]  J. Wolpaw,et al.  Decoding flexion of individual fingers using electrocorticographic signals in humans , 2009, Journal of neural engineering.

[23]  Rajesh P. N. Rao,et al.  Neural correlates of learning in an electrocorticographic motor-imagery brain-computer interface. , 2014, Brain computer interfaces.

[24]  John D. Simeral,et al.  An assistive decision-and-control architecture for force-sensitive hand–arm systems driven by human–machine interfaces , 2015, Int. J. Robotics Res..

[25]  Rajesh P. N. Rao,et al.  Broadband changes in the cortical surface potential track activation of functionally diverse neuronal populations , 2014, NeuroImage.