Estimation of Electrically-Evoked Knee Torque from Mechanomyography Using Support Vector Regression

The difficulty of real-time muscle force or joint torque estimation during neuromuscular electrical stimulation (NMES) in physical therapy and exercise science has motivated recent research interest in torque estimation from other muscle characteristics. This study investigated the accuracy of a computational intelligence technique for estimating NMES-evoked knee extension torque based on the Mechanomyographic signals (MMG) of contracting muscles that were recorded from eight healthy males. Simulation of the knee torque was modelled via Support Vector Regression (SVR) due to its good generalization ability in related fields. Inputs to the proposed model were MMG amplitude characteristics, the level of electrical stimulation or contraction intensity, and knee angle. Gaussian kernel function, as well as its optimal parameters were identified with the best performance measure and were applied as the SVR kernel function to build an effective knee torque estimation model. To train and test the model, the data were partitioned into training (70%) and testing (30%) subsets, respectively. The SVR estimation accuracy, based on the coefficient of determination (R2) between the actual and the estimated torque values was up to 94% and 89% during the training and testing cases, with root mean square errors (RMSE) of 9.48 and 12.95, respectively. The knee torque estimations obtained using SVR modelling agreed well with the experimental data from an isokinetic dynamometer. These findings support the realization of a closed-loop NMES system for functional tasks using MMG as the feedback signal source and an SVR algorithm for joint torque estimation.

[1]  Y. Ballay,et al.  Activation of human quadriceps femoris during isometric, concentric, and eccentric contractions. , 2001, Journal of applied physiology.

[2]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[3]  G. P. Braz,et al.  Functional Electrical Stimulation Control of Standing and Stepping After Spinal Cord Injury: A Review of Technical Characteristics , 2009, Neuromodulation : journal of the International Neuromodulation Society.

[4]  C. S. Bickel,et al.  Variable-frequency-train stimulation of skeletal muscle after spinal cord injury. , 2004, Journal of rehabilitation research and development.

[5]  Shih-Wei Lin,et al.  Particle swarm optimization for parameter determination and feature selection of support vector machines , 2008, Expert Syst. Appl..

[6]  GülerNihal Fatma,et al.  Use of Support Vector Machines and Neural Network in Diagnosis of Neuromuscular Disorders , 2005 .

[7]  Dejan B Popović,et al.  Advances in functional electrical stimulation (FES). , 2014, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[8]  G. Matheson,et al.  Vibromyography as a quantitative measure of muscle force production. , 1997, Scandinavian journal of rehabilitation medicine.

[9]  Nur Azah Hamzaid,et al.  Mechanomyographic Parameter Extraction Methods: An Appraisal for Clinical Applications , 2014, Sensors.

[10]  Carlo Menon,et al.  Comparison of regression models for estimation of isometric wrist joint torques using surface electromyography , 2011, Journal of NeuroEngineering and Rehabilitation.

[11]  Claudio Orizio,et al.  Surface mechanomyogram reflects the changes in the mechanical properties of muscle at fatigue , 1999, European Journal of Applied Physiology and Occupational Physiology.

[12]  Hong-Bo Xie,et al.  Classification of the mechanomyogram signal using a wavelet packet transform and singular value decomposition for multifunction prosthesis control , 2009, Physiological measurement.

[13]  Stephen Kwek,et al.  Applying Support Vector Machines to Imbalanced Datasets , 2004, ECML.

[14]  Muin J. Khoury,et al.  Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetes , 2010, BMC Medical Informatics Decis. Mak..

[15]  Michael R. Lyu,et al.  Localized support vector regression for time series prediction , 2009, Neurocomputing.

[16]  Kyung-shik Shin,et al.  An application of support vector machines in bankruptcy prediction model , 2005, Expert Syst. Appl..

[17]  Nicolas Babault,et al.  Electrostimulation training effects on the physical performance of ice hockey players. , 2005, Medicine and science in sports and exercise.

[18]  Hong-Bo Xie,et al.  Estimation of wrist angle from sonomyography using support vector machine and artificial neural network models. , 2009, Medical engineering & physics.

[19]  Ali Selamat,et al.  Modeling permeability and PVT properties of oil and gas reservoir using hybrid model based on type-2 fuzzy logic systems , 2015, Neurocomputing.

[20]  D. Farina,et al.  Motor unit acceleration maps and interference mechanomyographic distribution. , 2008, Journal of biomechanics.

[21]  Sabri Koçer,et al.  Use of Support Vector Machines and Neural Network in Diagnosis of Neuromuscular Disorders , 2005, Journal of Medical Systems.

[22]  Surendra M. Gupta,et al.  Support Vector Machines based Modelling of Concrete Strength , 2008 .

[23]  Chris M Gregory,et al.  Recruitment patterns in human skeletal muscle during electrical stimulation. , 2005, Physical therapy.

[24]  M. J. Hartman,et al.  Time and frequency domain responses of the mechanomyogram and electromyogram during isometric ramp contractions: a comparison of the short-time Fourier and continuous wavelet transforms. , 2008, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[25]  Shahaboddin Shamshirband,et al.  Support vector regression methodology for wind turbine reaction torque prediction with power-split hydrostatic continuous variable transmission , 2014 .

[26]  Wonkeun Youn,et al.  Feasibility of using an artificial neural network model to estimate the elbow flexion force from mechanomyography , 2011, Journal of Neuroscience Methods.

[27]  A. Joseph Threlkeld,et al.  Quantifying thigh muscle co-activation during isometric knee extension contractions: within- and between-session reliability. , 2014, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[28]  Nur Azah Hamzaid,et al.  Mechanomyography and muscle function assessment: a review of current state and prospects. , 2014, Clinical biomechanics.

[29]  Joseph P. Weir,et al.  ASEP PROCEDURES RECOMMENDATION I: ACCURATE ASSESSMENT OF MUSCULAR STRENGTH AND POWER , 2001 .

[30]  C. Orizio Muscle sound: bases for the introduction of a mechanomyographic signal in muscle studies. , 1993, Critical reviews in biomedical engineering.

[31]  Sunday Olusanya Olatunji,et al.  Estimation of surface energies of hexagonal close packed metals using computational intelligence technique , 2015, Appl. Soft Comput..

[32]  Hui Jiang,et al.  Grey relational grade in local support vector regression for financial time series prediction , 2012, Expert Syst. Appl..

[33]  Nicolas Babault,et al.  Effects of electrical stimulation pattern on quadriceps isometric force and fatigue in individuals with spinal cord injury , 2014, Muscle & nerve.

[34]  Terry J. Housh,et al.  The effect of leg flexion angle on the mechanomyographic responses to isometric muscle actions , 1998, European Journal of Applied Physiology and Occupational Physiology.

[35]  Mahesh Pal,et al.  Prediction of the end-depth ratio and discharge in semi-circular and circular shaped channels using support vector machines , 2006 .

[36]  G.D. Bell,et al.  A comparative study of simultaneous vibromyography and electromyography with active human quadriceps , 1992, IEEE Transactions on Biomedical Engineering.

[37]  Claudio Orizio,et al.  Influence of motor units recruitment and firing rate on the soundmyogram and EMG characteristics in cat gastrocnemius. , 1992, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[38]  Jung Kim,et al.  Estimation of elbow flexion force during isometric muscle contraction from mechanomyography and electromyography , 2010, Medical & Biological Engineering & Computing.

[39]  K. Akataki,et al.  Technical aspects of mechnomyography recording with piezoelectric contact sensor , 1998, Medical and Biological Engineering and Computing.

[40]  Ali R. Yildiz,et al.  A novel hybrid immune algorithm for global optimization in design and manufacturing , 2009 .

[41]  Tom Chau,et al.  A self-contained, mechanomyography-driven externally powered prosthesis. , 2005, Archives of physical medicine and rehabilitation.

[42]  Muhsin Tunay Gençoglu,et al.  Prediction of flashover voltage of insulators using least squares support vector machines , 2009, Expert Syst. Appl..

[43]  Ali Selamat,et al.  Improved sensitivity based linear learning method for permeability prediction of carbonate reservoir using interval type-2 fuzzy logic system , 2014, Appl. Soft Comput..

[44]  G. Dudley,et al.  Mapping of electrical muscle stimulation using MRI. , 1993, Journal of applied physiology.

[45]  Sunday O. Olatunji,et al.  Automatic Recognition of Off-line Handwritten Arabic (Indian) Numerals Using Support Vector and Extreme Learning Machines , 2009 .

[46]  D T Barry,et al.  Acoustic myography as a control signal for an externally powered prosthesis. , 1986, Archives of physical medicine and rehabilitation.

[47]  M. Bennett,et al.  Strength Response in Human Quadriceps Femoris Muscle During 2 Neuromuscular Electrical Stimulation Programs , 2003 .

[48]  Wu Meng,et al.  Application of Support Vector Machines in Financial Time Series Forecasting , 2007 .

[49]  Tom Chau,et al.  The design and testing of a novel mechanomyogram-driven switch controlled by small eyebrow movements , 2010, Journal of NeuroEngineering and Rehabilitation.

[50]  Motoki Kouzaki,et al.  Mechanomyogram from the different heads of the quadriceps muscle during incremental knee extension , 1998, European Journal of Applied Physiology and Occupational Physiology.

[51]  Kabiru O. Akande,et al.  Support Vector Machines Approach for Estimating Work Function of Semiconductors: Addressing the Limitation of Metallic Plasma Model , 2014 .

[52]  D. M. Selkowitz Improvement in isometric strength of the quadriceps femoris muscle after training with electrical stimulation. , 1985, Physical therapy.

[53]  J Mizrahi,et al.  Transcutaneous FES of the paralyzed quadriceps: is knee torque affected by unintended activation of the hamstrings? , 2000, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[54]  Claudio Orizio,et al.  Torque and surface mechanomyogram parallel reduction during fatiguing stimulation in human muscles , 2006, European Journal of Applied Physiology.

[55]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[56]  Sunday O. Olatunji,et al.  Investigating the effect of correlation-based feature selection on the performance of support vector machines in reservoir characterization , 2015 .

[57]  Yunqian Ma,et al.  Practical selection of SVM parameters and noise estimation for SVM regression , 2004, Neural Networks.

[58]  T. Housh,et al.  Mechanomyographic amplitude and mean power frequency versus torque relationships during isokinetic and isometric muscle actions of the biceps brachii. , 2004, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[59]  Mat Kiah M.L. Support vector regression methodology for wind turbine reaction torque prediction with power- split hydrostatic continuous variable transmission , 2014 .