Evaluation of matrix factorisation approaches for muscle synergy extraction.

The muscle synergy concept provides a widely-accepted paradigm to break down the complexity of motor control. In order to identify the synergies, different matrix factorisation techniques have been used in a repertoire of fields such as prosthesis control and biomechanical and clinical studies. However, the relevance of these matrix factorisation techniques is still open for discussion since there is no ground truth for the underlying synergies. Here, we evaluate factorisation techniques and investigate the factors that affect the quality of estimated synergies. We compared commonly used matrix factorisation methods: Principal component analysis (PCA), Independent component analysis (ICA), Non-negative matrix factorization (NMF) and second-order blind identification (SOBI). Publicly available real data were used to assess the synergies extracted by each factorisation method in the classification of wrist movements. Synthetic datasets were utilised to explore the effect of muscle synergy sparsity, level of noise and number of channels on the extracted synergies. Results suggest that the sparse synergy model and a higher number of channels would result in better estimated synergies. Without dimensionality reduction, SOBI showed better results than other factorisation methods. This suggests that SOBI would be an alternative when a limited number of electrodes is available but its performance was still poor in that case. Otherwise, NMF had the best performance when the number of channels was higher than the number of synergies. Therefore, NMF would be the best method for muscle synergy extraction.

[1]  M. Tresch,et al.  The case for and against muscle synergies , 2022 .

[2]  James M Wakeling,et al.  Neuromechanics of muscle synergies during cycling. , 2009, Journal of neurophysiology.

[3]  Emilio Bizzi,et al.  Combinations of muscle synergies in the construction of a natural motor behavior , 2003, Nature Neuroscience.

[4]  Ryota Kanai,et al.  Time-locked Perceptual Fading Induced by Visual Transients , 2003 .

[5]  A. Hyvarinen A family of fixed-point algorithms for independent component analysis , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Dario Farina,et al.  Extracting Signals Robust to Electrode Number and Shift for Online Simultaneous and Proportional Myoelectric Control by Factorization Algorithms , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[7]  Lena H Ting,et al.  Muscle synergy organization is robust across a variety of postural perturbations. , 2006, Journal of neurophysiology.

[8]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[9]  F Lacquaniti,et al.  Neuromuscular adjustments of gait associated with unstable conditions. , 2015, Journal of neurophysiology.

[10]  Changmok Choi,et al.  Synergy matrices to estimate fluid wrist movements by surface electromyography. , 2011, Medical engineering & physics.

[11]  Martha Flanders,et al.  Muscular and postural synergies of the human hand. , 2004, Journal of neurophysiology.

[12]  E. Clancy,et al.  Two degrees of freedom quasi-static EMG-force at the wrist using a minimum number of electrodes. , 2017, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[13]  E. Bizzi,et al.  Central and Sensory Contributions to the Activation and Organization of Muscle Synergies during Natural Motor Behaviors , 2005, The Journal of Neuroscience.

[14]  Martin A. Giese,et al.  Editorial: Modularity in motor control: from muscle synergies to cognitive action representation , 2015, Front. Comput. Neurosci..

[15]  Dario Farina,et al.  EMG-based simultaneous and proportional estimation of wrist/hand kinematics in uni-lateral trans-radial amputees , 2011, Journal of NeuroEngineering and Rehabilitation.

[16]  Corey B. Hart,et al.  Distinguishing synchronous and time-varying synergies using point process interval statistics: motor primitives in frog and rat , 2013, Front. Comput. Neurosci..

[17]  Rajiv Ranganathan,et al.  Extracting synergies in gait: using EMG variability to evaluate control strategies. , 2012, Journal of neurophysiology.

[18]  Kamran Iqbal,et al.  Real-Time Task Discrimination for Myoelectric Control Employing Task-Specific Muscle Synergies , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[19]  W. Kargo,et al.  Early Skill Learning Is Expressed through Selection and Tuning of Cortically Represented Muscle Synergies , 2003, The Journal of Neuroscience.

[20]  Fumitoshi Matsuno,et al.  Hand and Wrist Movement Control of Myoelectric Prosthesis Based on Synergy , 2015, IEEE Transactions on Human-Machine Systems.

[21]  Dario Farina,et al.  The Extraction of Neural Information from the Surface EMG for the Control of Upper-Limb Prostheses: Emerging Avenues and Challenges , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[22]  Eric Moulines,et al.  A blind source separation technique using second-order statistics , 1997, IEEE Trans. Signal Process..

[23]  Iwona Stepniewska,et al.  Microstimulation reveals specialized subregions for different complex movements in posterior parietal cortex of prosimian galagos. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[24]  Francesco Lacquaniti,et al.  Control of Fast-Reaching Movements by Muscle Synergy Combinations , 2006, The Journal of Neuroscience.

[25]  Manfredo Atzori,et al.  Electromyography data for non-invasive naturally-controlled robotic hand prostheses , 2014, Scientific Data.

[26]  L. Ting,et al.  Muscle synergies characterizing human postural responses. , 2007, Journal of neurophysiology.

[27]  Andrea d'Avella,et al.  Effective force control by muscle synergies , 2014, Front. Comput. Neurosci..

[28]  E. Bizzi,et al.  Muscle synergies encoded within the spinal cord: evidence from focal intraspinal NMDA iontophoresis in the frog. , 2001, Journal of neurophysiology.

[29]  Lena H Ting,et al.  A limited set of muscle synergies for force control during a postural task. , 2005, Journal of neurophysiology.

[30]  Andrea d'Avella,et al.  Matrix factorization algorithms for the identification of muscle synergies: evaluation on simulated and experimental data sets. , 2006, Journal of neurophysiology.

[31]  Rafael Raya,et al.  Emerging Therapies in Neurorehabilitation II , 2015 .

[32]  C. Sherrington Flexion‐reflex of the limb, crossed extension‐reflex, and reflex stepping and standing , 1910, The Journal of physiology.

[33]  Hervé Abdi,et al.  Wiley Interdisciplinary Reviews: Computational Statistics , 2010 .

[34]  Simon A. Overduin,et al.  Modulation of Muscle Synergy Recruitment in Primate Grasping , 2008, The Journal of Neuroscience.

[35]  L. Vinet,et al.  A ‘missing’ family of classical orthogonal polynomials , 2010, 1011.1669.

[36]  Shiro Ikeda,et al.  Independent component analysis for noisy data -- MEG data analysis , 2000, Neural Networks.

[37]  F. A. Mussa-lvaldi,et al.  Convergent force fields organized in the frog's spinal cord , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[38]  Emilio Bizzi,et al.  Muscle synergies evoked by microstimulation are preferentially encoded during behavior , 2014, Front. Comput. Neurosci..

[39]  E. Bizzi,et al.  Responses to spinal microstimulation in the chronically spinalized rat and their relationship to spinal systems activated by low threshold cutaneous stimulation , 1999, Experimental Brain Research.

[40]  Michael W. Berry,et al.  Algorithms and applications for approximate nonnegative matrix factorization , 2007, Comput. Stat. Data Anal..

[41]  Diego Torricelli,et al.  Muscle Synergies in Clinical Practice: Theoretical and Practical Implications , 2016 .

[42]  J. E. Jackson A User's Guide to Principal Components , 1991 .

[43]  Lena H Ting,et al.  Neuromechanics of muscle synergies for posture and movement , 2007, Current Opinion in Neurobiology.

[44]  J. Edward Jackson,et al.  A User's Guide to Principal Components: Jackson/User's Guide to Principal Components , 2004 .

[45]  Erkki Oja,et al.  Independent component analysis: algorithms and applications , 2000, Neural Networks.

[46]  Dario Farina,et al.  Identifying representative synergy matrices for describing muscular activation patterns during multidirectional reaching in the horizontal plane. , 2010, Journal of neurophysiology.

[47]  E. Bizzi,et al.  Linear combinations of primitives in vertebrate motor control. , 1994, Proceedings of the National Academy of Sciences of the United States of America.

[48]  Navid Lambert-Shirzad,et al.  On identifying kinematic and muscle synergies: a comparison of matrix factorization methods using experimental data from the healthy population. , 2017, Journal of neurophysiology.

[49]  Ning Jiang,et al.  Extracting Simultaneous and Proportional Neural Control Information for Multiple-DOF Prostheses From the Surface Electromyographic Signal , 2009, IEEE Transactions on Biomedical Engineering.

[50]  H. Abdi,et al.  Principal component analysis , 2010 .

[51]  Sylvain Dorel,et al.  Consistency of muscle synergies during pedaling across different mechanical constraints. , 2011, Journal of neurophysiology.

[52]  Kurt E. Beschorner,et al.  Shared and Task-Specific Muscle Synergies during Normal Walking and Slipping , 2017, Front. Hum. Neurosci..

[53]  M. Lemay,et al.  Modularity of motor output evoked by intraspinal microstimulation in cats. , 2004, Journal of neurophysiology.

[54]  Cornelius Schwarz,et al.  Spatial Segregation of Different Modes of Movement Control in the Whisker Representation of Rat Primary Motor Cortex , 2005, The Journal of Neuroscience.

[55]  Ilja Kuzborskij,et al.  Characterization of a Benchmark Database for Myoelectric Movement Classification , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[56]  Shinya Aoi,et al.  Neuromusculoskeletal models based on the muscle synergy hypothesis for the investigation of adaptive motor control in locomotion via sensory-motor coordination , 2016, Neuroscience Research.

[57]  Andrea d'Avella,et al.  Modularity in the motor system: decomposition of muscle patterns as combinations of time-varying synergies , 2001, NIPS.

[58]  E. Bizzi,et al.  The construction of movement by the spinal cord , 1999, Nature Neuroscience.

[59]  F A Mussa-Ivaldi,et al.  Computations underlying the execution of movement: a biological perspective. , 1991, Science.

[60]  S. Giszter,et al.  Modular Premotor Drives and Unit Bursts as Primitives for Frog Motor Behaviors , 2004, The Journal of Neuroscience.

[61]  Dario Farina,et al.  Intuitive, Online, Simultaneous, and Proportional Myoelectric Control Over Two Degrees-of-Freedom in Upper Limb Amputees , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[62]  William J Kargo,et al.  Individual Premotor Drive Pulses, Not Time-Varying Synergies, Are the Units of Adjustment for Limb Trajectories Constructed in Spinal Cord , 2008, The Journal of Neuroscience.