On the Usage of Linear Regression Models to Reconstruct Limb Kinematics from Low Frequency EEG Signals

Several works have reported on the reconstruction of 2D/3D limb kinematics from low-frequency EEG signals using linear regression models based on positive correlation values between the recorded and the reconstructed trajectories. This paper describes the mathematical properties of the linear model and the correlation evaluation metric that may lead to a misinterpretation of the results of this type of decoders. Firstly, the use of a linear regression model to adjust the two temporal signals (EEG and velocity profiles) implies that the relevant component of the signal used for decoding (EEG) has to be in the same frequency range as the signal to be decoded (velocity profiles). Secondly, the use of a correlation to evaluate the fitting of two trajectories could lead to overly-optimistic results as this metric is invariant to scale. Also, the correlation has a non-linear nature that leads to higher values for sinus/cosinus-like signals at low frequencies. Analysis of these properties on the reconstruction results was carried out through an experiment performed in line with previous studies, where healthy participants executed predefined reaching movements of the hand in 3D space. While the correlations of limb velocity profiles reconstructed from low-frequency EEG were comparable to studies in this domain, a systematic statistical analysis revealed that these results were not above the chance level. The empirical chance level was estimated using random assignments of recorded velocity profiles and EEG signals, as well as combinations of randomly generated synthetic EEG with recorded velocity profiles and recorded EEG with randomly generated synthetic velocity profiles. The analysis shows that the positive correlation results in this experiment cannot be used as an indicator of successful trajectory reconstruction based on a neural correlate. Several directions are herein discussed to address the misinterpretation of results as well as the implications on previous invasive and non-invasive works.

[1]  John G. Proakis,et al.  Digital Signal Processing: Principles, Algorithms, and Applications , 1992 .

[2]  Dawn M. Taylor,et al.  Direct Cortical Control of 3D Neuroprosthetic Devices , 2002, Science.

[3]  Nicholas G. Hatsopoulos,et al.  Brain-machine interface: Instant neural control of a movement signal , 2002, Nature.

[4]  R D Pascual-Marqui,et al.  Standardized low-resolution brain electromagnetic tomography (sLORETA): technical details. , 2002, Methods and findings in experimental and clinical pharmacology.

[5]  J. Colebatch,et al.  Movement-related potentials associated with self-paced, cued and imagined arm movements , 2002, Experimental Brain Research.

[6]  David M. Santucci,et al.  Learning to Control a Brain–Machine Interface for Reaching and Grasping by Primates , 2003, PLoS biology.

[7]  Jonathan R Wolpaw,et al.  Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Lüder Deecke,et al.  High Resolution DC-EEG Analysis of the Bereitschaftspotential and Post Movement Onset Potentials Accompanying Uni- or Bilateral Voluntary Finger Movements , 2004, Brain Topography.

[9]  L. Paninski,et al.  Superlinear Population Encoding of Dynamic Hand Trajectory in Primary Motor Cortex , 2004, The Journal of Neuroscience.

[10]  C. Mehring,et al.  Encoding of Movement Direction in Different Frequency Ranges of Motor Cortical Local Field Potentials , 2005, The Journal of Neuroscience.

[11]  A. Georgopoulos,et al.  Magnetoencephalographic signals predict movement trajectory in space , 2005, Experimental Brain Research.

[12]  Deniz Erdogmus,et al.  Determining Patterns in Neural Activity for Reaching Movements Using Nonnegative Matrix Factorization , 2005, EURASIP J. Adv. Signal Process..

[13]  Mandayam A. Srinivasan,et al.  Continuous shared control for stabilizing reaching and grasping with brain-machine interfaces , 2006, IEEE Transactions on Biomedical Engineering.

[14]  Miguel A. L. Nicolelis,et al.  Brain–machine interfaces: past, present and future , 2006, Trends in Neurosciences.

[15]  J. Colebatch.  Bereitschaftspotential and movement‐related potentials: Origin, significance, and application in disorders of human movement , 2007, Movement disorders : official journal of the Movement Disorder Society.

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

[17]  Richard A Andersen,et al.  Decoding Trajectories from Posterior Parietal Cortex Ensembles , 2008, The Journal of Neuroscience.

[18]  Andreas Schulze-Bonhage,et al.  Prediction of arm movement trajectories from ECoG-recordings in humans , 2008, Journal of Neuroscience Methods.

[19]  C. Braun,et al.  Hand Movement Direction Decoded from MEG and EEG , 2008, The Journal of Neuroscience.

[20]  C. Braun,et al.  A review on directional information in neural signals for brain-machine interfaces , 2009, Journal of Physiology-Paris.

[21]  José Luis Contreras-Vidal,et al.  Decoding center-out hand velocity from MEG signals during visuomotor adaptation , 2009, NeuroImage.

[22]  Yijun Wang,et al.  Predicting Intended Movement Direction Using EEG from Human Posterior Parietal Cortex , 2009, HCI.

[23]  W. A. Sarnacki,et al.  Electroencephalographic (EEG) control of three-dimensional movement , 2010, Journal of neural engineering.

[24]  J. Wolpaw.  Brain–Computer Interface Research Comes of Age: Traditional Assumptions Meet Emerging Realities , 2010, Journal of motor behavior.

[25]  N. Thakor,et al.  Electrocorticographic amplitude predicts finger positions during slow grasping motions of the hand , 2010, Journal of neural engineering.

[26]  Jun Lv,et al.  Decoding hand movement velocities from EEG signals during a continuous drawing task , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[27]  Yali Amit,et al.  Encoding of Coordinated Grasp Trajectories in Primary Motor Cortex , 2010, The Journal of Neuroscience.

[28]  Bin He,et al.  Relationship between speed and EEG activity during imagined and executed hand movements , 2010, Journal of neural engineering.

[29]  Naotaka Fujii,et al.  Long-Term Asynchronous Decoding of Arm Motion Using Electrocorticographic Signals in Monkeys , 2009, Front. Neuroeng..

[30]  Trent J. Bradberry,et al.  Reconstructing Three-Dimensional Hand Movements from Noninvasive Electroencephalographic Signals , 2010, The Journal of Neuroscience.

[31]  John P. Donoghue,et al.  Decoding 3-D Reach and Grasp Kinematics From High-Frequency Local Field Potentials in Primate Primary Motor Cortex , 2010, IEEE Transactions on Biomedical Engineering.

[32]  D. Farina,et al.  Detection of movement intention from single-trial movement-related cortical potentials , 2011, Journal of neural engineering.

[33]  Rodolphe J. Gentili,et al.  Reply to comment on 'Fast attainment of computer cursor control with noninvasively acquired brain signals' , 2011 .

[34]  Trent J. Bradberry,et al.  Fast attainment of computer cursor control with noninvasively acquired brain signals , 2011, Journal of neural engineering.

[35]  Riccardo Poli,et al.  Comment on 'fast attainment of computer cursor control with noninvasively acquired brain signals'. , 2011, Journal of neural engineering.

[36]  Emmanuel Maby,et al.  Inferring hand movement kinematics from MEG, EEG and intracranial EEG: From brain-machine interfaces to motor rehabilitation Décoder la cinématique d'un mouvement de la main à partir d'enregistrements MEG et EEG: des interfaces cerveau-machine à la réhabilitation motrice , 2011 .

[37]  José Luis Contreras-Vidal,et al.  Reconstructing hand kinematics during reach to grasp movements from electroencephalographic signals , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[38]  A. Doud,et al.  Continuous Three-Dimensional Control of a Virtual Helicopter Using a Motor Imagery Based Brain-Computer Interface , 2011, PloS one.

[39]  Towards Decoding 3 D Finger Trajectories from EEG , 2011 .

[40]  David M. Evans,et al.  A Comprehensive Evaluation of Potential Lung Function Associated Genes in the SpiroMeta General Population Sample , 2011, PloS one.

[41]  Ronald N. Goodman,et al.  Neural decoding of treadmill walking from noninvasive electroencephalographic signals. , 2011, Journal of neurophysiology.

[42]  Masa-aki Sato,et al.  Reconstruction of two-dimensional movement trajectories from selected magnetoencephalography cortical currents by combined sparse Bayesian methods , 2011, NeuroImage.

[43]  Nicolas Y. Masse,et al.  Reach and grasp by people with tetraplegia using a neurally controlled robotic arm , 2012, Nature.

[44]  Eduardo Serrano,et al.  Characterization of a clinical olfactory test with an artificial nose , 2011, Front. Neuroeng..

[45]  Gernot R. Müller-Putz,et al.  Decoding of velocities and positions of 3D arm movement from EEG , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[46]  J. Millán,et al.  Detection of self-paced reaching movement intention from EEG signals , 2012, Front. Neuroeng..