Recent studies have explored the organization of player movements in team sports using a range of statistical tools. However, the factors that best explain the performance of association football teams remain elusive. Arguably, this is due to the high-dimensional behavioural outputs that illustrate the complex, evolving configurations typical of team games. According to dynamical system analysts, movement patterns in team sports exhibit nonlinear self-organizing features. Nonlinear processing tools (i.e. Artificial Neural Networks; ANNs) are becoming increasingly popular to investigate the coordination of participants in sports competitions. ANNs are well suited to describing high-dimensional data sets with nonlinear attributes, however, limited information concerning the processes required to apply ANNs exists. This review investigates the relative value of various ANN learning approaches used in sports performance analysis of team sports focusing on potential applications for association football. Sixty-two research sources were summarized and reviewed from electronic literature search engines such as SPORTDiscus, Google Scholar, IEEE Xplore, Scirus, ScienceDirect and Elsevier. Typical ANN learning algorithms can be adapted to perform pattern recognition and pattern classification. Particularly, dimensionality reduction by a Kohonen feature map (KFM) can compress chaotic high-dimensional datasets into low-dimensional relevant information. Such information would be useful for developing effective training drills that should enhance self-organizing coordination among players. We conclude that ANN-based qualitative analysis is a promising approach to understand the dynamical attributes of association football players.
The study of postural control has been dominated by experiments on the maintenance of quiet upright standing balance on flat stationary support surfaces that reveal only limited modes of potential configurations of balance stability/instability. Here we examine the self-organization properties of postural coordination as revealed in a dynamic balance task with a moving platform. We scaled a control parameter (platform frequency) to investigate the evolving nature of the coupled oscillator dynamics between center of mass (CoM) and platform. Recurrent map measures were used to reveal whether episodic postural control strategies exist that can be scaled by systematically changing the magnitude of platform motion. The findings showed that at higher platform frequencies (1.2 Hz), the CoM-Platform coupling was less deterministic than lower platform frequencies and evolved to intermittent postural control strategies that oscillated between periodic-chaotic transitions to maintain upright postural balance. Collectively, the recurrence map measures indicated that quasi-static postural attractor states were progressively emerging to the changing task constraints of platform frequency in the maintenance of postural stability. It appears that several dynamic modes of intermittent coupling in postural control can interchangeably co-exist and are expressed as a function of the control parameter of platform frequency.
Background: Despite extensive research on falls among individuals with stroke, little is known regarding the impact of neurological conditions with comorbid diagnoses and motor functional capacity on the risk of falls in these individuals. Hence, the purpose of this study was to determine the fall risk and the contribution of reduced motor functional capacity to fall risk in individuals with stroke, dementia, and stroke plus dementia.Methods: Data from the National Health and Aging Trends Study (NHATS), a nationallyrepresentative sample of Medicare beneficiaries, were analyzed for this cross-sectional study. The odds of self-reported falls within the past month in three subgroups of neurological conditions [stroke (n=751), dementia (n=369), and stroke plus dementia (n=141)] were evaluated with a reference group of individuals with no stroke/dementia [i.e., controls (n=6337)] using logistic regression models.
Results:The prevalence of a recent fall was significantly higher (P<0.05) in the three neurological disorder groups compared with controls. After adjusting for sociodemographics, mobility device use, and other comorbidities (i.e., chronic disease, vision impairment, and major surgery), the odds of a recent fall were significantly elevated in individuals with stroke (odds ratio [OR]=1.45), dementia (OR=2.45), and stroke plus dementia (OR=2.64) compared with controls. After further adjustment for the lower motor functional capacity, the elevated odds in individuals with stroke were attenuated (OR=1.16); however, the odds remained significantly elevated in individuals with dementia (OR=1.67) and stroke plus dementia (OR=1.82).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.