FPGA-based muscle synergy extraction for surface EMG gesture classification

Abstract Stroke survivors often exhibit gait dysfunction which compromises self-efficacy and quality of life. Muscle Synergy Analysis (MSA), derived from electromyography (EMG), has been argued as a method to quantify the complexity of descending motor commands and serve as a direct correlate of neural function. However, controversy remains regarding this interpretation, specifically attribution of MSA as a neuromarker. Here we sought to determine the relationship between MSA and accepted neurophysiological parameters of motor efficacy in healthy controls, high (HFH) and low (LFH) functioning stroke survivors. Surface EMG was collected from twenty-four participants while walking at their self-selected speed. Concurrently, transcranial magnetic stimulation (TMS) was administered, during walking, to elicit motor evoked potentials (MEPs) in the plantarflexor muscles during the pre-swing phase of gait. MSA was able to differentiate control and LFH individuals. Conversely, motor neurophysiological parameters including soleus MEP area, revealed that MEP latency differentiated control and HFH individuals. Significant correlations were revealed between MSA and motor neurophysiological parameters adding evidence to our understanding of MSA as a correlate of neural function and highlighting the utility of combining MSA with other relevant outcomes to aid interpretation of this analysis technique.

Download Full-text

A musculoskeletal model driven by muscle synergy-derived excitations for hand and wrist movements

Journal of Neural Engineering ◽

10.1088/1741-2552/ac4851 ◽

2022 ◽

Author(s):

Jiamin Zhao ◽

Yang Yu ◽

Xu Wang ◽

Shihan Ma ◽

Xinjun Sheng ◽

...

Keyword(s):

Surface Emg ◽

Musculoskeletal Model ◽

Muscle Synergy ◽

Superior Performance ◽

Model Driven ◽

Regression Methods ◽

Weighting Matrix ◽

Online Test ◽

Specific Muscle ◽

Human Motions

Abstract Objective. Musculoskeletal model (MM) driven by electromyography (EMG) signals has been identified as a promising approach to predicting human motions in the control of prostheses and robots. However, muscle excitations in MMs are generally derived from the EMG signals of the targeted sensor covering the muscle, inconsistent with the fact that signals of a sensor are from multiple muscles considering signal crosstalk in actual situation. To identify more accurate muscle excitations for MM in the presence of crosstalk, we proposed a novel excitation-extracting method inspired by muscle synergy for simultaneously estimating hand and wrist movements. Approach. Muscle excitations were firstly extracted using a two-step muscle synergy-derived method. Specifically, we calculated subject-specific muscle weighting matrix and corresponding profiles according to contributions of different muscles for movements derived from synergistic motion relation. Then, the improved excitations were used to simultaneously estimate hand and wrist movements through musculoskeletal modeling. Moreover, the offline comparison among the proposed method, traditional MM and regression methods, and an online test of the proposed method were conducted. Main results. The offline experiments demonstrated that the proposed approach outperformed the EMG envelope-driven MM and three regression models with higher R and lower NRMSE. Furthermore, the comparison of excitations of two MMs validated the effectiveness of the proposed approach in extracting muscle excitations in the presence of crosstalk. The online test further indicated the superior performance of the proposed method than the MM driven by EMG envelopes. Significance. The proposed excitation-extracting method identified more accurate neural commands for MMs, providing a promising approach in rehabilitation and robot control to model the transformation from surface EMG to joint kinematics.

Download Full-text

sEMG-Based Hand-Gesture Classification Using a Generative Flow Model

Sensors ◽

10.3390/s19081952 ◽

2019 ◽

Vol 19 (8) ◽

pp. 1952 ◽

Cited By ~ 2

Author(s):

Wentao Sun ◽

Huaxin Liu ◽

Rongyu Tang ◽

Yiran Lang ◽

Jiping He ◽

...

Keyword(s):

Deep Learning ◽

Flow Model ◽

Reverse Flow ◽

Clinical Applications ◽

Muscle Synergy ◽

Hand Gesture ◽

Hand Gestures ◽

Softmax Classifier ◽

Gesture Classification ◽

High Level

Conventional pattern-recognition algorithms for surface electromyography (sEMG)-based hand-gesture classification have difficulties in capturing the complexity and variability of sEMG. The deep structures of deep learning enable the method to learn high-level features of data to improve both accuracy and robustness of a classification. However, the features learned through deep learning are incomprehensible, and this issue has precluded the use of deep learning in clinical applications where model comprehension is required. In this paper, a generative flow model (GFM), which is a recent flourishing branch of deep learning, is used with a SoftMax classifier for hand-gesture classification. The proposed approach achieves 63 . 86 ± 5 . 12 % accuracy in classifying 53 different hand gestures from the NinaPro database 5. The distribution of all 53 hand gestures is modelled by the GFM, and each dimension of the feature learned by the GFM is comprehensible using the reverse flow of the GFM. Moreover, the feature appears to be related to muscle synergy to some extent.

Download Full-text

A testing system for a real-time gesture classification using surface EMG

IFAC-PapersOnLine ◽

10.1016/j.ifacol.2017.08.1602 ◽

2017 ◽

Vol 50 (1) ◽

pp. 11498-11503 ◽

Cited By ~ 19

Author(s):

Konstantin Akhmadeev ◽

Elena Rampone ◽

Tianyi Yu ◽

Yannick Aoustin ◽

Eric Le Carpentier

Keyword(s):

Real Time ◽

Surface Emg ◽

Testing System ◽

Gesture Classification

Download Full-text

Deep Learning Based Surface EMG Hand Gesture Classification for Low-Cost Myoelectric Prosthetic Hand

2020 Joint 9th International Conference on Informatics, Electronics & Vision (ICIEV) and 2020 4th International Conference on Imaging, Vision & Pattern Recognition (icIVPR) ◽

10.1109/icievicivpr48672.2020.9306613 ◽

2020 ◽

Author(s):

Nazmun Nahid ◽

Arafat Rahman ◽

M.A.R. Ahad

Keyword(s):

Deep Learning ◽

Low Cost ◽

Surface Emg ◽

Hand Gesture ◽

Prosthetic Hand ◽

Gesture Classification

Download Full-text

Is interindividual variability of EMG patterns in trained cyclists related to different muscle synergies?

Journal of Applied Physiology ◽

10.1152/japplphysiol.01305.2009 ◽

2010 ◽

Vol 108 (6) ◽

pp. 1727-1736 ◽

Cited By ~ 96

Author(s):

François Hug ◽

Nicolas A. Turpin ◽

Arnaud Guével ◽

Sylvain Dorel

Keyword(s):

Interindividual Variability ◽

Nonnegative Matrix ◽

Rectus Femoris ◽

Biceps Femoris ◽

Surface Emg ◽

Constant Load ◽

Muscle Synergy ◽

Muscle Synergies ◽

Lower Limb Muscles ◽

Emg Patterns

Our aim was to determine whether muscle synergies are similar across trained cyclists (and thus whether the same locomotor strategies for pedaling are used), despite interindividual variability of individual EMG patterns. Nine trained cyclists were tested during a constant-load pedaling exercise performed at 80% of maximal power. Surface EMG signals were measured in 10 lower limb muscles. A decomposition algorithm (nonnegative matrix factorization) was applied to a set of 40 consecutive pedaling cycles to differentiate muscle synergies. We selected the least number of synergies that provided 90% of the variance accounted for VAF. Using this criterion, three synergies were identified for all of the subjects, accounting for 93.5 ± 2.0% of total VAF, with VAF for individual muscles ranging from 89.9 ± 8.2% to 96.6 ± 1.3%. Each of these synergies was quite similar across all subjects, with a high mean correlation coefficient for synergy activation coefficients (0.927 ± 0.070, 0.930 ± 0.052, and 0.877 ± 0.110 for synergies 1– 3, respectively) and muscle synergy vectors (0.873 ± 0.120, 0.948 ± 0.274, and 0.885 ± 0.129 for synergies 1– 3, respectively). Despite a large consistency across subjects in the weighting of several monoarticular muscles into muscle synergy vectors, we found larger interindividual variability for another monoarticular muscle (soleus) and for biarticular muscles (rectus femoris, gastrocnemius lateralis, biceps femoris, and semimembranosus). This study demonstrated that pedaling is accomplished by the combination of the similar three muscle synergies among trained cyclists. The interindividual variability of EMG patterns observed during pedaling does not represent differences in the locomotor strategy for pedaling.

Download Full-text