Volumen 18 (2019): Heft 3 (December 2019)

Along with advancements in science and technology, anthropometric measurements using electronic devices have become possible, and research is being actively conducted on this topic. Recently, devices using Bluetooth that are portable because of their small size have been developed to allow real-time measurements and recording. This study investigated the concurrent validity and intra-trial reliability of a recently developed Bluetooth-embedded inertial measurement unit. Thirty-seven healthy, young adult participants (age = 22.1±1.2 years, height = 166.8±1.6 cm, mass = 61.9±12.3 kg) were included in the study. The knee extension angles during active knee extension were measured for validity, using both the Bluetooth-embedded inertial measurement unit and the standard goniometer. Intra-trial reliability was tested for consistency during repeated measurements. The intra-class correlation coefficients value for the concurrent validity between the Bluetooth-embedded inertial measurement unit and standard goniometer was 0.991, and the values for the intra-trial reliability of the two devices were 0.973 and 0.963, respectively. Based on its high validity and reliability, the Bluetooth-embedded device may be useful for evaluating functional impairment and exercise performance ability by real-time measurements of joint ranges of motion in clinical rehabilitation or sports fields.

Numerous mobile applications are available that aim at supporting sustainable physical activity and fitness training in sedentary or low-trained healthy people. However, the evaluation of the quality of these applications often suffers from severe shortcomings such as reduction to selective aspects, lack of theory or suboptimal methods. What is still missing, is a framework that integrates the insights of the relevant scientific disciplines.

In this paper, we propose an integrative framework comprising four modules: training, behavior change techniques, sensors and technology, and evaluation of effects. This framework allows to integrate insights from training science, exercise physiology, social psychology, computer science, and civil engineering as well as methodology. Furthermore, the framework can be flexibly adapted to the specific features of the mobile applications, e.g., regarding training goals and training methods or the relevant behavior change techniques as well as formative or summative evaluation.

This paper investigates the use of network analysis to identify key players on teams, and patterns of passing within teams, in association football. Networks are constructed based on passes made between players, and several centrality measures are investigated in combination with three different methods for evaluating individual passes. Four seasons of data from the Norwegian top division are used to identify key players and analyze matches from a selected team. The networks examined in this work have weights based on three different aspects of the passes made: their probability of being completed, the probability that the team keeps possession after the completed pass, and the probability of the pass being part of a sequence leading to a shot. The results show that using different metrics and network weights leads to the identification of key passers in different phases of play and in different positions on the pitch.

Competitive balance is a key concept in sport because it creates an uncertainty on the outcome that leads to increased interest and demand for these events. The Spanish Professional Football League (LaLiga) has been one of the top European leagues in the last decade, and it has given rise to a particular research interest regarding its characteristics and structure. Since season 1995/96, LaLiga changed the number of points given to the winning teams, by awarding three points per victory instead of two. In this paper, we assess the impact of such a change on the competitive balance of LaLiga. Our analysis focuses on teams with varying levels of performance and follows a three-step approach. First, we cluster the teams according to their historical performance using an adjusted measure based on their credible intervals of winning ratios. Second, we calculate Kendall’s tau coefficient (according to our adjusted measure) in order to obtain the overall ranking turnover of teams between consecutive seasons. Third, we assess the causal impact of the adoption of the new scoring system, based on Kendall’s tau coefficients, for each cluster of teams. Our results show that the overall competitive balance decreased after the adoption of the new scoring system. However, the impact was not the same for all teams, being more significant for top teams and less significant for bottom teams. Moreover, our predictions using adjusted ARIMA models indicate that this difference in the competitive balance will persist for future seasons.

As a up and coming sport, powerlifting is gathering more and more attetion. Powerlifters vary in their strength levels and performances at different ages as well as differing in height and weight. Hence the questions arises on how to establish the relationship between age and weight. It is difficult to judge the performance of athletes by artificial expertise, as subjective factors affecting the performance of powerlifters often fail to achieve the desired results. In recent years, artificial intelligence has made groundbreaking strides. Therefore, using artificial intelligence to predict the performance of athletes is among one of many interesting topics in sports competitions. Based on the artificial intelligence algorithm, this research proposes an analysis model of powerlifters’ performance. The results show that the method proposed in this paper can predict the best performance of powerlifters. Coefficient of determination-R2=0.86 and root-mean-square error of prediction-RMSEP=20.98 demonstrate the effectiveness of our method.

In Australian football (AF), few studies have assessed combinations of pre- game factors and their relation to game outcomes (win/loss) in multivariable analyses. Further, previous research has mostly been confined to association-based linear approaches and post-game prediction, with limited assessment of predictive machine learning (ML) models in a pre-game setting. Therefore, our aim was to use ML techniques to predict game outcomes and produce a hierarchy of important (win/loss) variables. A total of 152 variables (79 absolute and 73 differentials) were used from the 2013–2018 Australian Football League (AFL) seasons. Various ML models were trained (cross-validation) on the 2013–2017 seasons with the–2018 season used as an independent test set. Model performance varied (66.5-73.3% test set accuracy), although the best model (glmnet – 73.3%) rivalled bookmaker predictions in the same period (70.9%). The glmnet model revealed measures of team quality (a player-based rating and a team-based) in their relative form as the most important variables for prediction. Models that contained in-built feature selection or could model non-linear relationships generally performed better. These findings show that AFL game outcomes can be predicted using ML methods and provide a hierarchy of predictors that maximize the chance of winning.

Identifying potential future elite athletes is important in many sporting events. The successful identification of potential future elite athletes at an early age would help to provide high-quality coaching and training environments in which to optimize their development. However, a large variety of different skills and qualities are needed to succeed in elite sports, making talent identification generally a complex and multifaceted problem. Due to the rarity of elite athletes, datasets are inherently imbalanced, making classical statistical inference difficult. Therefore, we approach talent identification as an anomaly detection problem. We trained a nonlinear one-class support vector machine (one-class SVM) on a dataset (N=951) collected from 14-year-old junior soccer players to detect potential future elite players. The mean area under the receiver operating characteristic curve (AUC-ROC) over the tested hyperparameter combinations was 0.763 (std 0.007). The most accurate model was obtained when physical tests, measuring, for example, technical skills, speed, and agility, were used. According to our results, the proposed approach could be useful to support decision-makers in the process of talent identification.