Bayesian filtering of myoelectric signals.

Surface electromyography is used in research, to estimate the activity of muscle, in prosthetic design, to provide a control signal, and in biofeedback, to provide subjects with a visual or auditory indication of muscle contraction. Unfortunately, successful applications are limited by the variability in the signal and the consequent poor quality of estimates. I propose to use a nonlinear recursive filter based on Bayesian estimation. The desired filtered signal is modeled as a combined diffusion and jump process and the measured electromyographic (EMG) signal is modeled as a random process with a density in the exponential family and rate given by the desired signal. The rate is estimated on-line by calculating the full conditional density given all past measurements from a single electrode. The Bayesian estimate gives the filtered signal that best describes the observed EMG signal. This estimate yields results with very low short-time variability but also with the capability of very rapid response to change. The estimate approximates isometric joint torque with lower error and higher signal-to-noise ratio than current linear methods. Use of the nonlinear filter significantly reduces noise compared with current algorithms, and it may therefore permit more effective use of the EMG signal for prosthetic control, biofeedback, and neurophysiology research.

[1]  S.G. Meek,et al.  Fatigue compensation of the electromyographic signal for prosthetic control and force estimation , 1993, IEEE Transactions on Biomedical Engineering.

[2]  S Conforto,et al.  Extraction of the envelope from surface EMG signals. , 2001, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[3]  KarlikBekir,et al.  A fuzzy clustering neural network architecture for classification of ECG arrhythmias , 2006 .

[4]  G. Hefftner,et al.  The electromyogram (EMG) as a control signal for functional neuromuscular stimulation. II. Practical demonstration of the EMG signature discrimination system , 1988, IEEE Transactions on Biomedical Engineering.

[5]  Euljoon Park,et al.  Adaptive filtering of the electromyographic signal for prosthetic control and force estimation , 1995, IEEE Transactions on Biomedical Engineering.

[6]  S. Harkema,et al.  A Bayesian change-point analysis of electromyographic data: detecting muscle activation patterns and associated applications. , 2003, Biostatistics.

[7]  J Bagger,et al.  Effect of functional bracing, quadriceps and hamstrings on anterior tibial translation in anterior cruciate ligament insufficiency: a preliminary study. , 1992, Journal of rehabilitation research and development.

[8]  N. Hogan,et al.  Customized interactive robotic treatment for stroke: EMG-triggered therapy , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Serge H. Roy,et al.  Modeling of surface myoelectric signals. II. Model-based signal interpretation , 1999, IEEE Transactions on Biomedical Engineering.

[10]  M. Osman Tokhi,et al.  A fuzzy clustering neural network architecture for multifunction upper-limb prosthesis , 2003, IEEE Transactions on Biomedical Engineering.

[11]  C M Light,et al.  Development of a lightweight and adaptable multiple-axis hand prosthesis. , 2000, Medical engineering & physics.

[12]  S. Meek,et al.  Comparison of signal-to-noise ratio of myoelectric filters for prosthesis control. , 1992, Journal of rehabilitation research and development.

[13]  Vaclav Edvard Benes,et al.  Recursive nonlinear estimation of a diffusion acting as the rate of an observed Poisson process , 1980, IEEE Trans. Inf. Theory.

[14]  H Al-Nashash,et al.  Surface myoelectric signal classification for prostheses control , 2005, Journal of medical engineering & technology.

[15]  Roger W. Brockett,et al.  Trajectory estimation from place cell data , 2001, Neural Networks.

[16]  R E Kass,et al.  Recursive bayesian decoding of motor cortical signals by particle filtering. , 2004, Journal of neurophysiology.

[17]  G. Hefftner,et al.  The electromyogram (EMG) as a control signal for functional neuromuscular stimulation. I. Autoregressive modeling as a means of EMG signature discrimination , 1988, IEEE Transactions on Biomedical Engineering.

[18]  Adrian D. C. Chan,et al.  Continuous myoelectric control for powered prostheses using hidden Markov models , 2005, IEEE Transactions on Biomedical Engineering.

[19]  E. Clancy,et al.  Influence of advanced electromyogram (EMG) amplitude processors on EMG-to-torque estimation during constant-posture, force-varying contractions. , 2006, Journal of biomechanics.

[20]  Edward A. Clancy,et al.  Adaptive whitening of the electromyogram to improve amplitude estimation , 2000, IEEE Transactions on Biomedical Engineering.

[21]  L. Ince,et al.  EMG biofeedback with upper extremity musculature for relaxation training: a critical review of the literature. , 1985, Journal of behavior therapy and experimental psychiatry.

[22]  E N Brown,et al.  An analysis of neural receptive field plasticity by point process adaptive filtering , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[23]  Robert W. Mann,et al.  Myoelectric Signal Processing: Optimal Estimation Applied to Electromyography - Part I: Derivation of the Optimal Myoprocessor , 1980, IEEE Transactions on Biomedical Engineering.

[24]  Adrian D. C. Chan,et al.  A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses , 2005, IEEE Transactions on Biomedical Engineering.

[25]  R. Merletti,et al.  Modeling of surface myoelectric signals--Part II: Model-based signal interpretation. , 1999, IEEE transactions on bio-medical engineering.

[26]  C. D. De Luca,et al.  Myoelectric signal versus force relationship in different human muscles. , 1983, Journal of applied physiology: respiratory, environmental and exercise physiology.

[27]  Kevin B. Englehart,et al.  A wavelet-based continuous classification scheme for multifunction myoelectric control , 2001, IEEE Transactions on Biomedical Engineering.

[28]  D. Richard Brown,et al.  Adaptive whitening in electromyogram amplitude estimation for epoch-based applications , 2005, IEEE Transactions on Biomedical Engineering.

[29]  L. Ince,et al.  Experimental foundations of EMG biofeedback with the upper extremity: A review of the literature , 1984, Biofeedback and Self-Regulation.

[30]  C M Light,et al.  Intelligent multifunction myoelectric control of hand prostheses , 2002, Journal of medical engineering & technology.

[31]  E. Clancy,et al.  Influence of smoothing window length on electromyogram amplitude estimates , 1998, IEEE Transactions on Biomedical Engineering.

[32]  N. Hogan,et al.  Multiple site electromyograph amplitude estimation , 1995, IEEE Transactions on Biomedical Engineering.

[33]  N Hogan,et al.  A review of the methods of processing EMG for use as a proportional control signal. , 1976, Biomedical engineering.

[34]  Vladimir Medved,et al.  Standards for Reporting EMG Data , 2000, Journal of Electromyography and Kinesiology.

[35]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

[36]  B. Hudgins,et al.  Hidden Markov model classification of myoelectric signals in speech , 2001, 2001 Conference Proceedings of the 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[37]  N. Hogan,et al.  Single site electromyograph amplitude estimation , 1994, IEEE Transactions on Biomedical Engineering.

[38]  Ping Zhou,et al.  Factors governing the form of the relation between muscle force and the EMG: a simulation study. , 2004, Journal of neurophysiology.

[39]  Neville Hogan,et al.  Myoelectric Signal Processing: Optimal Estimation Applied to Electromyography - Part II: Experimental Demonstration of Optimal Myoprocessor Performance , 1980, IEEE Transactions on Biomedical Engineering.

[40]  Emery N. Brown,et al.  Estimating a State-space Model from Point Process Observations Emery N. Brown , 2022 .

[41]  E L Morin,et al.  Sampling, noise-reduction and amplitude estimation issues in surface electromyography. , 2002, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[42]  I. Kingma,et al.  Towards optimal multi-channel EMG electrode configurations in muscle force estimation: a high density EMG study. , 2005, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[43]  N. Hogan,et al.  Probability density of the surface electromyogram and its relation to amplitude detectors , 1999, IEEE Transactions on Biomedical Engineering.

[44]  N. Hogan,et al.  Relating agonist-antagonist electromyograms to joint torque during isometric, quasi-isotonic, nonfatiguing contractions , 1997, IEEE Transactions on Biomedical Engineering.

[45]  Philip A. Parker,et al.  Signal Processing for Proportional Myoelectric Control , 1984, IEEE Transactions on Biomedical Engineering.

[46]  Subhash Challa,et al.  Nonlinear filter design using Fokker-Planck-Kolmogorov probability density evolutions , 2000, IEEE Trans. Aerosp. Electron. Syst..

[47]  E A Clancy,et al.  Estimation and application of EMG amplitude during dynamic contractions. , 2001, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[48]  Andreas Daffertshofer,et al.  Improving EMG-based muscle force estimation by using a high-density EMG grid and principal component analysis , 2006, IEEE Transactions on Biomedical Engineering.