Multi-dimensional coordination in cross-country skiing analyzed using self-organizing maps

Analysis of change of direction performance with dominant and non-dominant leg using linear and nonlinear approaches

This study was aimed to analyse the lower limb kinematics during the change of direction (COD) performance with the dominant (DL) and non-dominant (NDL) leg using linear (traditional kinematics) and nonlinear (Self Organising Map-based cluster analysis) approaches. Three 5-0-5 COD performances with the DL and three with the NDL were performed by 23 (aged 21.6 ± 2.3 years) collegiate athletes. No significant difference was observed between the COD duration, and approach speed of DL and NDL. Significantly greater ankle abductions, knee and hip external rotations were identified in COD with DL, compared to NDL (p < .001, d > 0.8). Self Organising Maps portrayed a completely different coordination pattern profile during change of direction performance with the DL and NDL. The cluster analysis illustrated similar inter-individual coordination patterning when participants turned with their DL or NDL. No visible relationship was observed in the cluster analysis of the lower limb joint angles and angular velocities. Outcomes of this study portrayed that coordination patterning (combination of joint angles and the rate of change of angles) could portray the movement patterning differences in different tasks, while a sole investigation on the joint angles or angular velocities may not reveal the underlying mechanisms of movement patterning.

Whole body coordination patterning in volleyball spikes under various task constraints: exploratory cluster analysis based on self-organising maps

Task and environment-related constraints can influence spike performance in volleyball players. This study was designated to investigate the impact of awareness of the presence or absence of a defensive block by the opponents on the performance and coordination pattern of spikes in elite volleyball attackers. Simulating a real-game scenario, 10 elite youth attackers (aged 15.5 ± 0.7 years) executed six spikes each with prior notification about the presence/absence of defences and six spikes without any notification. In each condition, they were blocked by two opponents in three trials. The coordination patterning of the attackers was explored using cluster analysis based on a Self-Organising Map (SOM). The SOMs and the cluster analysis showed that the coordination pattern of the spike execution was very individual-specific; however, in the third layer of the cluster analysis, it was revealed that the movement pattern of spike execution had similarities in the scenario wherein the players had prior awareness of the defences. Providing the attackers with information on the opponents' condition or performance could shift the attackers' focus from a game-oriented condition to the rivals' behaviour, which consequently resulted in deterioration of their spike performance.

Proximal-to-Distal Sequencing and Coordination Variability in the Volleyball Spike of Elite Youth Players: Effects of Gender and Growth

The aim of this article was to examine changes in elite youth volleyball players’ performance, proximal-to-distal sequencing, and coordination variability of the spike motion between the start and after 1 year of a talent development program. Eight boys and eight girls in late puberty/early adolescence were measured with 3D motion capturing for 2 consecutive years. Performance and performance variability increased and decreased, respectively, but both changes were not significantly correlated with growth. Gender differences were identified for proximal-to-distal sequencing, but a very strong similarity between both years was observed for all seven degrees of freedom (pelvis and trunk rotation, trunk flexion, shoulder horizontal adduction, shoulder internal rotation, elbow extension, and wrist flexion). The fact that this sequence was kept stable, despite marked growth effects, likely indicates that this sequence is biomechanically efficient and the motor control systems try to preserve it. Coordination variability was analyzed by coordination profiling with self-organizing maps. The decrease in coordination variability correlated strongly and significantly with increase in body height. Participants with stronger growth rates were observed to show smaller decreases in coordination variability, which possibly represents a mechanism to explore various coordination patterns to adapt to the more rapidly changing organismic constraints.

Evaluation of coordination hysteresis in a multidimensional movement task with continuous relative phase and Self-Organizing Maps

Hysteresis in the coordination of movement can be described in the language of coordination dynamics as an asymmetrical response of a system's order parameter with respect to opposite changes in a control parameter. For movement tasks involving a large number of active degrees-of-freedom, the order parameter can be modelled with a pattern recognition approach like Self-Organizing Maps (SOM). This study explored this method in a rope-skipping task, which involves the coordinated oscillation of several segments in the lower and upper limb and trunk and we compared the results to a classical order parameter like continuous relative phase. Five rope skippers completed a task which involved 30 s continuous forward rope-skipping during which the frequency (set by a metronome) increased linearly, immediately followed by 30 s during which the frequency decreased linearly. CRP was analyzed with statistical parametric mapping and a hysteresis measure for the SOM was calculated based on inter-trial variability. Both the CRP and the SOMs showed that the coordination patterns changed differently during the two conditions, signifying hysteresis. While the CRP captures only the relative coordination of two segments, the SOM is able to accommodate the whole-body multidimensional coordination. Hysteresis is often used as proxy for higher-order information about the movement system. While the low sample size in this study does not allow us to generalize the results, the present methodology can be used in further studies to advance our theoretical understanding of dynamical systems in complex whole-body movements.

Changes in balance coordination and transfer to an unlearned balance task after slackline training: a self-organizing map analysis

How humans maintain balance and change postural control due to age, injury, immobility or training is one of the basic questions in motor control. One of the problems in understanding postural control is the large set of degrees of freedom in the human motor system. Therefore, a self-organizing map (SOM), a type of artificial neural network, was used in the present study to extract and visualize information about high-dimensional balance strategies before and after a 6-week slackline training intervention. Thirteen subjects performed a flamingo and slackline balance task before and after the training while full body kinematics were measured. Range of motion, velocity and frequency of the center of mass and joint angles from the pelvis, trunk and lower leg (45 variables) were calculated and subsequently analyzed with an SOM. Subjects increased their standing time significantly on the flamingo (average +2.93 s, Cohen's d = 1.04) and slackline (+9.55 s, d = 3.28) tasks, but the effect size was more than three times larger in the slackline. The SOM analysis, followed by a k-means clustering and marginal homogeneity test, showed that the balance coordination pattern was significantly different between pre- and post-test for the slackline task only (χ ² = 82.247; p < 0.001). The shift in balance coordination on the slackline could be characterized by an increase in range of motion and a decrease in velocity and frequency in nearly all degrees of freedom simultaneously. The observation of low transfer of coordination strategies to the flamingo task adds further evidence for the task-specificity principle of balance training, meaning that slackline training alone will be insufficient to increase postural control in other challenging situations.

Quantifying Postural Control during Exergaming Using Multivariate Whole-Body Movement Data: A Self-Organizing Maps Approach

Background

Exergames are becoming an increasingly popular tool for training balance ability, thereby preventing falls in older adults. Automatic, real time, assessment of the user’s balance control offers opportunities in terms of providing targeted feedback and dynamically adjusting the gameplay to the individual user, yet algorithms for quantification of balance control remain to be developed. The aim of the present study was to identify movement patterns, and variability therein, of young and older adults playing a custom-made weight-shifting (ice-skating) exergame.

Methods

Twenty older adults and twenty young adults played a weight-shifting exergame under five conditions of varying complexity, while multi-segmental whole-body movement data were captured using Kinect. Movement coordination patterns expressed during gameplay were identified using Self Organizing Maps (SOM), an artificial neural network, and variability in these patterns was quantified by computing Total Trajectory Variability (TTvar). Additionally a k Nearest Neighbor (kNN) classifier was trained to discriminate between young and older adults based on the SOM features.

Results

Results showed that TTvar was significantly higher in older adults than in young adults, when playing the exergame under complex task conditions. The kNN classifier showed a classification accuracy of 65.8%.

Conclusions

Older adults display more variable sway behavior than young adults, when playing the exergame under complex task conditions. The SOM features characterizing movement patterns expressed during exergaming allow for discriminating between young and older adults with limited accuracy. Our findings contribute to the development of algorithms for quantification of balance ability during home-based exergaming for balance training.