BP neural network-based analysis of the applicability of NMF in side-step cutting.

Background: Although the spatio-temporal structure of muscle activation in cutting have been studied extensively, including time-varying motor primitives and time-invariant motor modules under various conditions, the factorisation methods suitable for cutting are unclear, and the extent to which each factorisation method loses information about movement during dimensionality reduction is uncertain. Research question: To clarify the extent to which NMF, PCA and ICA retain information about movement when downscaling, and to explore the factorisation method suitable for cutting. Methods: The kinematic data during cutting was captured with a Vicon motion capture system, from which the kinematic features of the pelvic centre of mass were calculated. NMF, PCA and ICA were used to obtain muscle synergies based on sEMG of the cutting at different angles, respectively. A back propagation neural network was constructed using temporal component of synergy as input and the kinematics data of pelvic as output. Calculation of the Hurst index using fractal analysis based on the temporal component of muscle synergy. Results: The quality of sEMG reconstruction is significantly higher with ICA (P < 0.01) than with NMF and PCA for the cutting. The NMF reconstruction has a high degree of preservation of movement, whereas the ICA loses movement information about the most of the swing phase, and the PCA loses information related to the change of direction. Hurst index less than 0.5 for all three angles of cutting. Significance: NMF is suitable for extracting muscle synergies in all directions of cutting. Information related to movement may be lost when using PCA and ICA to extract the synergy of cutting. The high individual variability of muscle synergy in cutting may be responsible for the loss of movement information in muscle synergy.

An analysis of the effect of motor experience on muscle synergy in the badminton jump smash.

The jump smash is badminton's most aggressive technical manoeuvre, which is often the key to winning a match. This paper aims to explore the neuromuscular control strategies of advanced and beginner players when jumping smash in different ways. Collecting sEMG and kinematic data from 18 subjects with different motor experiences when jumping smash. Nonnegative Matrix Factorization and K-Means clustering were used to extract muscle synergies and exclude irrelevant combined synergies. Uncontrolled manifold analysis was then used to explore the association between synergies and shoulder stability. In addition, motor output at the spinal cord level was assessed by mapping sEMG to each spinal cord segment. The study found that advanced subjects could respond to different jump smash styles by adjusting the coordinated activation strategies of the upper-limb and postural muscles. Long-term training can induce a rapid decrease in the degree of co-variation of the synergies before contact with a shuttlecock to better cope with an upcoming collision. It is recommended that beginners should focus more on training the coordination of upper-limb muscles and postural muscles.

A Study of Racket Weight Adaptation in Advanced and Beginner Badminton Players.

The jump smash is the most aggressive manoeuvre in badminton. Racket parameters may be the key factor affecting the performance of jump smash. Previous studies have focused only on the biomechanical characteristics of athletes or on racket parameters in isolation, with less observation of the overall performance of the human-racket system. This study aims to explore the effects of different racket weights on neuromuscular control strategies in advanced and beginner players. Nonnegative matrix factorisation (NMF) was used to extract the muscle synergies of players when jumping smash using different rackets (3U, 5U), and K-means clustering was used to obtain the fundamental synergies. Uncontrolled manifold (UCM) analyses were used to establish links between synergy and motor performance, and surface electromyography (sEMG) was mapped to each spinal cord segment. The study found significant differences (P < 0.05) in the postural muscles of skilled players and significant differences (P < 0.001) in the upper-limb muscles of beginners when the racket weight was increased. Advanced players adapt to the increase in racket weight primarily by adjusting the timing of the activation of the third synergy. Combined synergy in advanced players is mainly focused on the backswing, while that in beginners is mainly focused on the frontswing. This suggests that advanced players may be more adept at utilising the postural muscles and their coordination with the upper-limb muscles to adapt to different rackets. In addition, the motor experience can help athletes adapt more quickly to heavier rackets, and this adaptation occurs primarily by adjusting the temporal phase and covariation characteristics of the synergies rather than by increasing the number of synergies.

Characteristics of muscle synergy and anticipatory synergy adjustments strategy when cutting in different angles.

BACKGROUND: Cutting is a quick change of direction that challenges body balance and stability. As the cut-angle increases, the elite athlete can achieve higher performance by pre-adjusting the posture of the lower limb joints. However, it is unclear how the cut-angle affects the neuromuscular control of cutting and the step before cutting, which is essential for daily training and preventing injury in large-angle cutting. RESEARCH QUESTION: The purpose of this study was to determine how neuromuscular control strategies change under different angles for cutting and the step before cutting METHODS: Non-negative matrix factorisation and K-means clustering were used to extract muscle synergy in the trunk and lower limbs of 12 athletes when cutting at different angles. Uncontrolled manifold analysis was used to clarify whether the muscle synergy fluctuations in the step before cutting were beneficial in stabilising the COP during the cutting. RESULTS: This study found that the angle did not affect the number of muscle synergies either in the cutting or the step before the cutting. As the angle increases, the activation timing of synergy module 2 during cutting moves forward and is tightly integrated with module 1. The combined synergy at 90° accounted for the largest proportion of either cutting or the step before cutting and had a lower synergy index. SIGNIFICANCE: Muscle synergy can respond to large-angle cutting through flexible combinations. The muscle synergy for 90° cutting is less regular and has a lower degree of anticipatory synergy adjustments, which may result in poorer postural stability and an increased risk of lower limb joint injury during cutting.

A long short-term memory modeling-based compensation method for muscle synergy.

Muscle synergy containing temporal and spatial patterns of muscle activity has been frequently used in prediction of kinematic characteristics. However, there is often some discrepancy between the predicted results based on muscle synergy and the actual movement performance. This study aims to propose a new method for compensating muscle synergy that allows the compensated synergy signal to predict kinematic characteristics more accurately. The study used the change of direction in running as background. Non-negative matrix factorisation was used to extract the muscle synergy during the change of direction at different angles. A non-linear association between synergy and the height of pelvic mass centre was established using long and short-term memory neural networks. Based on this model, the height fluctuations of the pelvic centre of mass are used as input and predict the fluctuations of the synergy which were used to compensate for the original synergy in different ways. The accuracy of the synergies compensated in different ways in predicting pelvic centre of mass movement was then assessed by back propagation neural networks. It was found that the compensated synergy significantly improves accuracy in predicting pelvic centre of mass displacement (R2, p < 0.05). The predicted results of all-compensation are significantly different from actual performance in the end-swing (p < 0.05). The predicted results of half-compensation do not differ significantly from the actual performance, and its damage to the original synergy is smaller and does not increase with angle compared to all-compensation. The all-compensation may be affected by individual variability and lead to increased errors. The half-compensation can improve the predictive accuracy of the synergy while reducing the adjustment to the original synergy.

The Influence of Experience on Neuromuscular Control of the Body When Cutting at Different Angles.

Cutting is an offensive technique commonly used in football and basketball to pass the opponent's defence by changing direction quickly in running. This paper aims to investigate the effect of experience and angle on the neuromuscular control strategies of the trunk and lower limbs during cutting. Non-negative matrix factorisation and K-means were used to extract muscle synergies (muscles that are activated in parallel) of 12 subjects with cut experience and 9 subjects without experience based on the sEMG signal collected from cutting at three cut angles (45°, 90°, and 135°), which was also mapped into the spinal motor output. Uncontrolled manifold analysis was used to establish the relationship between muscle synergies and COP. This study found that experienced subjects tended to use the lower limb muscles rather than the postural muscles as stabiliser muscles compared to novices. Experienced subjects can recruit an additional set of muscle synergy to cope with large-angle cuts. In addition, experienced subjects can activate the second muscle synergy, involving the hip and ankle stabilisation muscles, in advance to improve postural stability when cutting in large-angle. Synergy index of experienced subjects dropped rapidly before the quick stop and was relatively high during the change of direction. These results suggest that experience can modify the postural stabilisation mechanisms during cutting, and prompt the lower limb muscle synergy to produce anticipatory adjustment to improve postural stability in the anterior-posterior and internal-external directions.