The non-complexity of tennis, coupled with its health benefits, renders it appealing and encourages varying competitions at different levels of age, gender, and expertise. However, the rapid increase in the participation rates witnesses a surge in injury occurrences, prompting the need for in-depth analysis to facilitate immediate intervention. We employed a media content analysis technique in which tennis-associated articles published in the last 5 years were examined. A total of 207 news reports were gathered and screened for analysis. Subsequently, 71 articles were excluded from the study due to content duplications or summary updates of existing news articles, while 23 news articles were also excluded from the study due to inappropriateness. Finally, 113 news reports directly related to injury in tennis were coded and analyzed. We examined various types of injuries reported from the screened articles with respect to their status (fresh, recurrent, and recovery) across expertise levels i.e., elite, or amateur. Similarly, the incidence of injury occurrences based on the types of tournaments the players engage in was also investigated. A chi-square analysis was employed to achieve the objectives of the study. Occurrences of tennis-associated injuries are disseminated across expertise levels [ χ ( 18 ) 2 = 16.542; p = 0.555], with knee, hip, elbow, and shoulder injuries being highly prevalent in both elite and amateur players. Nevertheless, it was noted that elite players suffered a staggering 72.60% of injury-related problems, while amateur players sustained 27.40% of injuries. Moreover, the status of injury spreads based on types of tournaments [ χ ( 4 ) 2 = 3.374; p = 0.497], with higher occurrences of fresh and recurrent injuries, while low recovery rates were observed. The findings further demonstrated that injuries are sustained regardless of tournament types [ χ ( 36 ) 2 = 39.393; p = 0.321]. However, most of the injuries occurred at international tournaments (85%). Whereas, only 5.30% of the injuries occurred at national/regional tournaments while 9.70% were unidentified. It could be deduced from the findings of this investigation that elite players are more prone to injuries compared with amateur players. Furthermore, the most common tennis-related injuries affect the lower, trunk, and upper regions of the body, respectively. A large number of the reported tennis injuries are fresh and recurrent, with a few recoveries. The international tennis tournaments are highly attributed to injury occurrences as opposed to the national/regional tournaments. The application of the media-based data mining technique is non-trivial in projecting injury-related problems that could be used to facilitate the development of an injury index peculiar to the tennis sport for prompt intervention.
The success and enjoyment of a football match depend heavily on referees and their ability to ensure fair play and uphold the rules of the game. However, there is limited research investigating the disciplinary measures and booking activities of referees in top European football leagues. In the current investigation, we explored the disciplinary measures and booking activities of top-European football league referees. The dataset of the referee activities concerning 15 indicators containing 602 matches from five consecutive seasons across the five top European leagues, namely, the English Premier League, Spanish Laliga, Italian Serie A, French Ligue1, and German Bundesliga were utilized for this study. K-means cluster analysis was used to define the activity levels of the referees. The Mann-Whitney U test was employed to determine the differences in the levels of the referees' activity with respect to the disciplinary measures, while binary regression analysis was applied to examine the association between the disciplinary measures and the activity levels of the referees. Two groups of activities were defined by k-means, that is, high and low activity. The Mann-Whitney U test revealed statistically significant differences in all 15 indicators examined between high and low activity. However, the regression model demonstrated that only fouls, yellow cards, and air challenges could significantly describe referees' activity levels. These indicators appear to be predictors of high referee activity in elite European Football. Specific training on dealing with increased aggression and foul behaviour coupled with improved game organisational management could be further incorporated into referees' training programmes amongst other measures.
The identification and prediction of athletic talent are pivotal in the development of successful sporting careers. Traditional subjective assessment methods have proven unreliable due to their inherent subjectivity, prompting the rise of data-driven techniques favoured for their objectivity. This evolution in statistical analysis facilitates the extraction of pertinent athlete information, enabling the recognition of their potential for excellence in their respective sporting careers. In the current study, we applied a logistic regression-based machine learning pipeline (LR) to identify potential skateboarding athletes from a combination of fitness and motor skills performance variables. Forty-five skateboarders recruited from a variety of skateboarding parks were evaluated on various skateboarding tricks while their fitness and motor skills abilities that consist of stork stance test, dynamic balance, sit ups, plank test, standing broad jump, as well as vertical jump, were evaluated. The performances of the skateboarders were clustered and the LR model was developed to classify the classes of the skateboarders. The cluster analysis identified two groups of skateboarders: high and low potential skateboarders. The LR model achieved 90% of mean accuracy specifying excellent prediction of the skateboarder classes. Further sensitivity analysis revealed that static and dynamic balance, lower body strength, and endurance were the most important factors that contributed to the model's performance. These factors are therefore essential for successful performance in skateboarding. The application of machine learning in talent prediction can greatly assist coaches and other relevant stakeholders in making informed decisions regarding athlete performance.
This study aims at classifying flat ground tricks, namely Ollie, Kickflip, Shove-it, Nollie and Frontside 180, through the identification of significant input image transformation on different transfer learning models with optimized Support Vector Machine (SVM) classifier. A total of six amateur skateboarders (20 ± 7 years of age with at least 5.0 years of experience) executed five tricks for each type of trick repeatedly on a customized ORY skateboard (IMU sensor fused) on a cemented ground. From the IMU data, a total of six raw signals extracted. A total of two input image type, namely raw data (RAW) and Continous Wavelet Transform (CWT), as well as six transfer learning models from three different families along with grid-searched optimized SVM, were investigated towards its efficacy in classifying the skateboarding tricks. It was shown from the study that RAW and CWT input images on MobileNet, MobileNetV2 and ResNet101 transfer learning models demonstrated the best test accuracy at 100% on the test dataset. Nonetheless, by evaluating the computational time amongst the best models, it was established that the CWT-MobileNet-Optimized SVM pipeline was found to be the best. It could be concluded that the proposed method is able to facilitate the judges as well as coaches in identifying skateboarding tricks execution.