Computationally Efficient Personalized EMG-Driven Musculoskeletal Model of Wrist Joint

Abstract

Myoelectric control has gained much attention which translates the human intentions into control commands for exoskeletons. The electromyogram (EMG)-driven musculoskeletal (MSK) model shows prominent performance given its ability to interpret the underlying neuromechanical processes among the musculoskeletal system. This model-based scheme contains inherent physiological parameters, e.g., isometric muscle force, tendon slack length, or optimal muscle fibre length, which need to be tailored for each individual via minimising the differences between the experimental measurement and model estimation. However, the creation of the personalised EMGdriven MSK model through the evolutionary algorithms is timeconsuming, hurdling the use of the EMG-driven MSK model in practical scenarios. This paper proposes a computational efficient optimisation method to estimate the subject-specific physiological parameters for a wrist MSK model based on the direct collocation method. By constraining control variables to the experimentally measured EMG signals and introducing the physiological parameters into control variables, fast optimisation is achieved by identifying the discretised parameters at each grid simultaneously. Experimental evaluations on 12 healthy subjects are performed. Results demonstrate the proposed method outperforms the baseline optimisation algorithms used in the literature, including genetic algorithm, simulated annealing algorithm, and particle swarm optimisation algorithm. The proposed direct collocation method shows the possibility to alleviate the costly optimisation procedure and facilitate the use of the MSK model in practical applications.

A Physics-Informed Low-Shot Adversarial Learning for sEMG-Based Estimation of Muscle Force and Joint Kinematics

“…Huang et al [16] gathered sEMG signals utilizing a high-density electrode grid and employed the non-negative matrix factorization algorithm for the joint kinetics estimation. Although such physics-based models explicitly explain and map sEMG signals to joint kinematics, the high cost of their static optimization has always limited the practical applications of these models [17], [18]. the multi-layer convolution architecture has been explored to establish relationships between movement variables and neuromuscular status [21], [22].…”

“…The evaluation metrics include 1) the metrics for evaluating 391 the quality of the generated samples including the information 392 entropy associated peak signal-to-noise ratio (PSNR) [46], 393 coefficient of Determination (R 2 ) [47], root mean square 394 error (RMSE) [18], Spearman's Rank Correlation Coefficient 395 (SRCC) [48], and 2) the metrics for evaluating the mode collapse of GANs, including 1) inception score (IS) [34], and 2) Frechet inception distance (FID) [49].…”

Physics-Informed Deep Learning for Muscle Force Prediction With Unlabeled sEMG Signals

“…During the data collection process, participants were instructed to maintain a straight torso with their shoulder Each participant completed two repetitive trials at different speeds with a three-minute break between the speed changes to prevent muscle fatigue [42].…”

Consistent control information driven musculoskeletal model for multiday myoelectric control

“…Recent advances in EMG-driven musculoskeletal models (MMs) have investigated the mechanisms of motion generation, namely the way of transforming neural commands to mechanical outputs (i.e. human joint motions) through biomechanical modelling [16][17][18]. Regarding the model robustness, Crouch et al developed a lumped-parameter MM to decode multi-joint movements and further proved its stable performance in two-day online control [19,20].…”