Explore the vast range of titles available.

Artificial Intelligence (AI) is transforming the field of sports science by providing unprecedented insights and tools that enhance training, performance, and health management. This work examines how AI is advancing the role of sports scientists, particularly in team sports environments, by improving training load management, sports performance, and player well-being. It explores key dimensions such as load optimization, injury prevention and return-to-play, sports performance, talent identification and scouting, off-training behavior, sleep quality, and menstrual cycle management. Practical examples illustrate how AI applications have significantly advanced each area and how they support and enhance the effectiveness of sports scientists. This manuscript also underscores the importance of ensuring that AI technologies are context-specific and communicated transparently. Additionally, it calls for academic institutions to update their curriculums with AI-focused education, preparing future sports professionals to fully harness its potential. Finally, the manuscript addresses future challenges, such as the unpredictable nature of team sports, emphasizing the need for interdisciplinary collaboration, including clear communication and mutual understanding between sports scientists and AI experts, and the critical balance between AI-driven insights and human expertise.

The aim of the study was to (i) analyze the match performance of professional female tennis players in different Grand Slams; (ii) model the relationships between match performance variables and relative quality; and (iii) build typical performance profiles for those players in Grand Slams. Data of a total of 1369 matches were collected within 2014-2017 four Grand Slams (Australian Open: n = 499; Roland Garros: n = 249; Wimbledon: n = 249 and US Open, n = 372). Correlations between 37 performance variables and relative quality (difference of expected rounds between two competing players of given ranking) were determined and automatically classified into two groups of magnitudes via two-step cluster analysis. Higher-correlated variables were used to build players' typical performance profiles via regression-based technique to give percentage evaluation scores (%ES), which means the percentage of matches where a performance variable value would be expected to be lower than the observed value considering the RQ of two competing players. Players had more service winners, double faults, return winners and return unforced errors in the Australian Open and US Open, implying a \"fast-fast\" serve strategy, and higher dominance ratio and better serving performance in Wimbledon. While receiving players had better chances to break opponents' service game in Roland Garros. Distance covered became similar in all Grand Slams. All studied variables showed obvious correlation with RQ expect for those of physical performance. The findings (i) indicate that female game in Grand Slams remained to be a contest over baseline, although players had good efficiency at net; (ii) demonstrate the influence of relative quality on serve and return, break point, net point and efficiency performance; and (iii) evidence the usefulness of applying %ES to evaluate performance of individual player.

Background and Objective Understanding and recognizing basketball offensive set plays, which involve intricate interactions between players, have always been regarded as challenging tasks for untrained humans, not to mention machines. In this study, our objective is to propose an artificial intelligence model that can automatically recognize offensive plays using a novel self-supervised learning approach. Methods The dataset was collected by SportVU from 632 games during the 2015–2016 season of the National Basketball Association (NBA), with a total of 90,524 possessions. A multi-agent motion prediction pretraining model was built on the basis of axial-attention transformer and trained with different masking strategies: motion prediction (MP), motion reconstruction (MR), and MP + MR joint strategy. A downstream play-level classification task and similarity search were used to evaluate the models’ performance. Results The results showed that the MP + MR joint masking strategy maximized the ability of the model compared with individual masking strategies. For the classification task, the joint strategy achieved a top-1 accuracy of 81.5% and top-3 accuracy of 97.5%. In the similarity search evaluation, the joint strategy attained a top-5 accuracy of 76% and top-10 accuracy of 59%. Additionally, with the same MP + MR joint masking strategy, our HoopTransformer model outperformed the two baseline models in the classification task and similarity search. Conclusion This study presents a self-supervised learning model and demonstrates the effectiveness and potential of the model in accurately comprehending and capturing player movements and complex interactions during offensive plays.

Performance analysis in soccer has attained greater importance for coaching staff in order to gather and manage useful information (i.e., physical, technical, and tactical) of their teams during consecutive seasons. Accordingly, we examined the evolution of physical and technical performance parameters in the Chinese Soccer Super League (CSL). Data were collected from 1,429 CSL matches from the 2012 season to the 2017 season using the Amisco Pro (Amisco, Nice, France) system. Fourteen technical performance-related indicators and 11 physical performance-related indicators were analysed using a mixed linear model for repeated measures. Significant main effects of season were followed up using the Bonferroni correction (multiple comparisons). Although there were some irregularities, performance variables generally showed significant upward trends across the six seasons (p<0.05), resulting in significant increases from the 2012 season to the 2017 season in the total sprint distance (2,069.7±509.3 m vs. 2,272±493.6 m; p<0.001; effect size [ES]: 0.40), number of sprints (100.1±22.8 vs. 104.8±20.8, p<0.001; ES: 0.22), high-speed distance (2568.4±503.5 m vs. 2823.1±479.2 m; (p<0.001; ES: 0.52), and high-speed effort (187.5±36.1 to 204.7±33.7; p<0.001; ES: 0.49). Furthermore, there were ~23% more crosses (p<0.001; ES: 0.45), ~12% more shots on target (p<0.001; ES: 0.22), and ~11% more opponent penalty area entries (p<0.001; ES: 0.20) during the 2017 season than in the 2012 season. Coaches and sports scientists should be mindful of this evolution when preparing training sessions and recruiting new players, and even when predicting future trends in the Chinese Soccer Super League.

Arbitrary zones are commonly used to describe and monitor external load (EL) during training and competitions. However, in recent years, relative speed zones have gained interest as they allow a more detailed description of the demands of each individual player, with their benefits largely unknown. This study aimed to (i) identify differences in EL methodological approaches using arbitrary and relative running speed zones; (ii) examine the effect of the methodological approaches to identify fast and slow basketball players during competition and training; and (iii) determine the effect of the season stage on the methodological approaches. Twelve players from a Spanish fourth-division basketball team were observed for a full season of matches and training using inertial devices with ultra-wideband indoor tracking technology and micro-sensors. Relative velocity zones were based on the maximum velocity achieved during each match quarter and were retrospectively recalculated into four zones. A linear mixed model (LMM) compared fast and slow players based on speed profiles between arbitrary and relative thresholds and during each competition stage. All players surpassed peak speeds of 24 km·h−1 during the season, exceeding typical values reported in elite basketball (20–24.5 km·h−1). Arbitrary thresholds produced greater distances in high-speed running (Zones 3 and 4) and yielded lower values in low-speed activity (Zone 1), with differences of ~100 m and ~120–250 m, respectively (p < 0.001), particularly for fast-profile players. These discrepancies were consistent across most stages of the season, although relative zones better captured variations in Zone 1 across time. Training sessions also elicited +8.7% to +40.7% greater distances > 18 km·h−1 compared to matches. The speed zone methodology substantially influenced EL estimates and affected how player EL was interpreted across time. Arbitrary and relative approaches offer unique applications, with coaches and sport scientists encouraged to be aware that using a one-size-fits-all approach may lead to misrepresentation of individual player demands, especially when tracking changes in performance or managing fatigue throughout a competitive season.

The aim of the present study was to compare external loads (EL) between elite, junior, male and female basketball players. Male (n = 25) and female players (n = 48) were monitored during 11 competitive matches (3 matches per team). EL was measured using local positioning system and microsensor technology to determine total, high-intensity (14–21 km·h−1), and sprint (>21 km·h−1) distance (m) covered, total (n) and relative (n·min−1) accelerations and decelerations, ratio of accelerations:decelerations, and total (arbitrary units [AU]) and relative (AU·min−1) player load. EL was compared between sexes overall and according to each playing position (guards, forwards, and centers). Males covered larger (p < 0.05) high-intensity and sprint distances, and completed more (p < 0.05) decelerations than females; while female players experienced a greater (p < 0.05) ratio of accelerations:decelerations. Greater decelerations (p < 0.05) were observed for males in the guard position compared to females, while more (p < 0.05) accelerations·min−1 were apparent for females in the forward position compared to males. The current findings indicate differences in EL, particularly the high-intensity and acceleratory demands, exist between elite, junior, male and female basketball players during competition and are affected by playing position. These outcomes can be used in developing sex- and position-specific training plans, and in turn improving the physical preparedness of junior basketball players for competition demands at the elite level.

The aim of the current study was to analyse performance differences of football players 2-years prior and the year after signing a new contract (the following year) while taking playing position, nationality, player's role, team ability, and age into account. The sample was comprised of 249 players (n = 109 defenders, n = 113 midfielders; and n = 27 forwards) from four of the major European Leagues (Bundesliga, English FA Premier League, Ligue 1, and La Liga) during the seasons 2008 to 2015. The dependent variables studied were: shooting accuracy, defense (the sum of defensive actions, tackles, blocks, and interceptions), yellow cards, red cards, passing accuracy, tackle success, and minutes played per match. Two-step cluster analysis allowed classifying the sample into three groups of defenders (national important, foreign important, and less important players) and four groups of midfielders and forwards (national important, foreign important, national less important, and foreign less important players). Magnitude Based Inference (MBI) was used to test the differences between player's performances during the years of analyses. The main results (very likely and most likely effects) showed better performance in the year prior to signing a new contract than the previous year for foreign important defenders (decreased number of red cards), national important midfielders (increased number of minutes played), foreign important forwards (increased minutes played and defense), and national important forwards (increased minutes played). In addition, performance was lower the year after signing the contract compared to the previous one for less important defenders (decreasing defense), national less important midfielders (decreased minutes played), and foreign less important forwards (decreased defense). On the other hand, the players showed better performance in defense and more minutes played the year after signing the contract for less important defenders, national less important midfielders, and foreign less important forwards. These results may assist coaches to decide on when a new contract should be signed or the duration of the contract.

The aim of this study was to investigate the relationships among physical demands of two friendly matches (FMs) and three task training sessions (TS1,2,3) combining in a different way: a Small-Sided Game (SSG), Mini-Goals (MG), a ball Circuit Training (CT) and a Large-Sided Game (LSG): SSG+MG+LSG (TS1), SSG+CT+LSG (TS2) and MG+CT+LSG (TS3). The TS and match demands in running intensities were monitored in fourteen professional soccer players (age = 23.2 ± 2.7 years, height = 178 ± 6 cm, body mass = 73.2 ± 6.9 kg, mean and SD, respectively) using 10-Hz global positioning system devices, and players’ perception of exertion was recorded after each session or match using a visual analogue scale. A one-way repeated measures ANOVA with a Bonferroni correction coupled with magnitude-based inferences were used. A principal component (PC) analysis was conducted on all variables to account for covariance. Three PCs were retained, explaining 76% of the variance: Component 1 explained 46.9% with the associated variables: Total Distance (TD) and distance covered in ranges of speed from >2.2 to <5 m/s, Player Load and Work Rest Ratio; component 2 explained 19.7% and was composed of TD at > 5 m/s and maximal running speed (MRS); and component 3 explained 9.5% and was represented by TD < 2.2 m/s, decelerations and accelerations. The ANOVA results showed significant differences (p < 0.05) among TS vs. FM in TD3, TD4, TD5, and TD > 5, TD, deceleration rate, acceleration rate, maximal running speed, exertion index, work rest ratio, and self-reported exertion. Therefore, the training routines did not replicate the main set of high intensity efforts experienced in competitive conditions. Additionally, PC analysis could be applied in order to select the most representative training and competitive conditions.

Background: Several studies have examined the differences between the different small-sided game (SSG) formats. However, only one study has analysed how the different variables that define SSGs can modify the goalkeeper’s behavior. The aim of the present study was to analyze how the modification of the pitch size in SSGs affects the physical demands of the goalkeepers. Methods: Three professional male football goalkeepers participated in this study. Three different SSG were analysed (62 m × 44 m for a large pitch; 50 m × 35 m for a medium pitch and 32 m × 23 m for a small pitch). Positional data of each goalkeeper was gathered using an 18.18 Hz global positioning system. The data gathered was used to compute players’ spatial exploration index, standard ellipse area, prediction ellipse area The distance covered, distance covered in different intensities and accelerations/decelerations were used to assess the players’ physical performance. Results and Conclusions: There were differences between small and large SSGs in relation to the distances covered at different intensities and pitch exploration. Intensities were lower when the pitch size was larger. Besides that, the pitch exploration variables increased along with the increment of the pitch size.

In recent years, many CO2 capture technologies have been developed due to growing awareness about the importance of reducing greenhouse gas emissions. In this paper, publications from the last decade addressing this topic were analyzed, paying special attention to patent status to provide useful information for policymakers, industry, and businesses and to help determine the direction of future research. To show the most current patent activity related to carbon capture using membrane technology, we collected 2749 patent documents and 572 scientific papers. The results demonstrated that membranes are a developing field, with the number of applications growing at a steady pace, exceeding 100 applications per year in 2013 and 2014. North American assignees were the main contributors, with the greatest number of patents owned by companies such as UOP LLC, Kilimanjaro Energy Inc., and Membrane Technology and Research Inc., making up 26% of the total number of published patents. Asian countries (China, Japan, and Korea) and international offices were also important knowledge sources, providing 29% and 24% of the documents, respectively. Furthermore, this paper highlights 10 more valuable patents regarding their degree of innovation and citations, classified as Y02C 10/10 according to the Cooperative Patent Classification (CPC) criteria.