An ICA-EBM-Based sEMG Classifier for Recognizing Lower Limb Movements in Individuals With and Without Knee Pathology

Surface electromyography (sEMG) data acquired during lower limb movements has the potential for investigating knee pathology. Nevertheless, a major challenge encountered with sEMG signals generated by lower limb movements is the intersubject variability, because the signals recorded from the leg or thigh muscles are contingent on the characteristics of a subject such as gait activity and muscle structure. In order to cope with this difficulty, we have designed a three-step classification scheme. First, the multichannel sEMG is decomposed into activities of the underlying sources by means of independent component analysis via entropy bound minimization. Next, a set of time-domain features, which would best discriminate various movements, are extracted from the source estimates. Finally, the feature selection is performed with the help of the Fisher score and a scree-plot-based statistical technique, prior to feeding the dimension-reduced features to the linear discriminant analysis. The investigation involves 11 healthy subjects and 11 individuals with knee pathology performing three different lower limb movements, namely, walking, sitting, and standing, which yielded an average classification accuracy of 96.1% and 86.2%, respectively. While the outcome of this study per se is very encouraging, with suitable improvement, the clinical application of such an sEMG-based pattern recognition system that distinguishes healthy and knee pathological subjects would be an attractive consequence.

[1]  Gamini Dissanayake,et al.  Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals , 2012, Expert Syst. Appl..

[2]  Tulay Adali,et al.  A novel entropy estimator and its application to ICA , 2009, 2009 IEEE International Workshop on Machine Learning for Signal Processing.

[3]  Mu Zhu,et al.  Automatic dimensionality selection from the scree plot via the use of profile likelihood , 2006, Comput. Stat. Data Anal..

[4]  Sung-Ho Hwang,et al.  Feature Evaluation and Pattern Recognition of Lower Limb Muscle EMG during Postural Balance Control , 2006 .

[5]  Kazuo Kiguchi,et al.  A Study on Lower-Limb Muscle Activities during Daily Lower-Limb Motions , 2007 .

[6]  Aapo Hyvärinen,et al.  Fast and robust fixed-point algorithms for independent component analysis , 1999, IEEE Trans. Neural Networks.

[7]  Ganesh R. Naik,et al.  Identification of Hand and Finger Movements Using Multi Run ICA of Surface Electromyogram , 2012, Journal of Medical Systems.

[8]  J. Ekholm,et al.  Quantified electromyography of lower-limb muscles during level walking. , 2020, Scandinavian journal of rehabilitation medicine.

[9]  Akihiro Kanamori,et al.  Decrease of knee flexion torque in patients with ACL reconstruction: combined analysis of the architecture and function of the knee flexor muscles , 2006, Knee Surgery, Sports Traumatology, Arthroscopy.

[10]  I. W. Hunter,et al.  Estimation of the conduction velocity of muscle action potentials using phase and impulse response function techniques , 1987, Medical and Biological Engineering and Computing.

[11]  He Huang,et al.  A Strategy for Identifying Locomotion Modes Using Surface Electromyography , 2009, IEEE Transactions on Biomedical Engineering.

[12]  Rangaraj M. Rangayyan,et al.  Fractal analysis of knee-joint vibroarthrographic signals via power spectral analysis , 2013, Biomed. Signal Process. Control..

[13]  Mika P. Tarvainen,et al.  Non-Linear EMG Parameters for Differential and Early Diagnostics of Parkinson’s Disease , 2013, Front. Neurol..

[14]  Reza Rostami,et al.  Classifying depression patients and normal subjects using machine learning techniques , 2011, 2011 19th Iranian Conference on Electrical Engineering.

[15]  N. V. Thakor,et al.  Classification of gait phases from lower limb EMG: Application to exoskeleton orthosis , 2013, 2013 IEEE Point-of-Care Healthcare Technologies (PHT).

[16]  Jeffrey M. Hausdorff,et al.  Fractal dynamics in physiology: Alterations with disease and aging , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Kevin J Deluzio,et al.  Neuromuscular and Lower Limb Biomechanical Differences Exist between Male and Female Elite Adolescent Soccer Players during an Unanticipated Side-cut Maneuver , 2007, The American journal of sports medicine.

[18]  José Luis Rodríguez-Sotelo,et al.  Knee functional state classification using surface electromyographic and goniometric signals by means artificial neural networks , 2015 .

[19]  Michael Goldfarb,et al.  Multiclass Real-Time Intent Recognition of a Powered Lower Limb Prosthesis , 2010, IEEE Transactions on Biomedical Engineering.

[20]  T. Higuchi Approach to an irregular time series on the basis of the fractal theory , 1988 .

[21]  Brian Litt,et al.  A comparison of waveform fractal dimension algorithms , 2001 .

[22]  Katarzyna Radecka,et al.  Automated diagnosis of knee pathology using sensory data , 2014, 2014 4th International Conference on Wireless Mobile Communication and Healthcare - Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH).

[23]  Barbara E. Shapiro,et al.  Electromyography and neuromuscular disorders : clinical-electrophysiologic correlations , 1997 .

[24]  JoAnne K. Gronley,et al.  Use of cluster analysis for gait pattern classification of patients in the early and late recovery phases following stroke. , 2003, Gait & posture.

[25]  Hylton B Menz,et al.  Effect of foot posture, foot orthoses and footwear on lower limb muscle activity during walking and running: a systematic review. , 2009, Gait & posture.

[26]  Tülay Adali,et al.  Blind spatiotemporal separation of second and/or higher-order correlated sources by entropy rate minimization , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[27]  Ganesh R. Naik,et al.  Nonnegative Matrix Factorization for the Identification of EMG Finger Movements: Evaluation Using Matrix Analysis , 2015, IEEE Journal of Biomedical and Health Informatics.

[28]  A. Asuncion,et al.  UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences , 2007 .

[29]  Dinesh Kumar,et al.  Applications of ICA and fractal dimension in sEMG signal processing for subtle movement analysis: a review , 2011, Australasian Physical & Engineering Sciences in Medicine.

[30]  M. Torry,et al.  Gender Differences in Lower Extremity Landing Mechanics Caused by Neuromuscular Fatigue , 2008, The American journal of sports medicine.

[31]  Yilmaz Kaya,et al.  A novel approach for SEMG signal classification with adaptive local binary patterns , 2015, Medical & Biological Engineering & Computing.

[32]  Tülay Adali,et al.  Independent Component Analysis by Entropy Bound Minimization , 2010, IEEE Transactions on Signal Processing.

[33]  D. Gravel,et al.  Normality and stationarity of EMG signals of elbow flexor muscles during ramp and step isometric contractions. , 1997, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[34]  G. Melchiorri,et al.  A method for positioning electrodes during surface EMG recordings in lower limb muscles , 2004, Journal of Neuroscience Methods.

[35]  S. Thomas George,et al.  Range-Based ICA Using a Nonsmooth Quasi-Newton Optimizer for Electroencephalographic Source Localization in Focal Epilepsy , 2015, Neural Computation.

[36]  Deok-Hwan Kim,et al.  Multiple gait phase recognition using boosted classifiers based on sEMG signal and classification matrix , 2014, ICUIMC.

[37]  Tao Zhang,et al.  Noise-assisted multivariate empirical mode decomposition for multichannel EMG signals , 2017, Biomedical engineering online.

[38]  Nasser Mozayani,et al.  A new criterion to distinguish stochastic and deterministic time series with the Poincaré section and fractal dimension. , 2009, Chaos.

[39]  Roberto Merletti,et al.  Electromyography. Physiology, engineering and non invasive applications , 2005 .

[40]  Dinesh Kant Kumar,et al.  Decoding subtle forearm flexions using fractal features of surface electromyogram from single and multiple sensors , 2010, Journal of NeuroEngineering and Rehabilitation.

[41]  Jørgen Skotte,et al.  Kettlebell swing targets semitendinosus and supine leg curl targets biceps femoris: an EMG study with rehabilitation implications , 2012, British Journal of Sports Medicine.

[42]  Fan Zhang,et al.  Continuous Locomotion-Mode Identification for Prosthetic Legs Based on Neuromuscular–Mechanical Fusion , 2011, IEEE Transactions on Biomedical Engineering.

[43]  Hylton B Menz,et al.  Reliability of lower limb electromyography during overground walking: a comparison of maximal- and sub-maximal normalisation techniques. , 2010, Journal of biomechanics.

[44]  Adrian D. C. Chan,et al.  Myoelectric Control Development Toolbox , 2007 .

[45]  M. Ferrarin,et al.  A multiple-task gait analysis approach: kinematic, kinetic and EMG reference data for healthy young and adult subjects. , 2011, Gait & posture.

[46]  Tülay Adali,et al.  An effective decoupling method for matrix optimization and its application to the ICA problem , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[47]  Levi J. Hargrove,et al.  A training strategy to reduce classification degradation due to electrode displacements in pattern recognition based myoelectric control , 2008, Biomed. Signal Process. Control..

[48]  Guido Bugmann,et al.  A note on the probability distribution function of the surface electromyogram signal☆ , 2013, Brain Research Bulletin.

[49]  J. Rafiee,et al.  Feature extraction of forearm EMG signals for prosthetics , 2011, Expert Syst. Appl..

[50]  Dinesh Kumar,et al.  Estimation of independent and dependent components of non-invasive EMG using fast ICA: validation in recognising complex gestures , 2011, Computer methods in biomechanics and biomedical engineering.