Search Results (13)

Background/Objectives: Quantitative approaches to talent identification in youth soccer often rely on either closed-skill assessments or small-sided games, but each carries inherent uncertainties that can reduce selection accuracy. Effective talent selection requires integrating both sources of data while accounting for their limitations. This study aimed to develop and validate a framework that combines closed-skill tests with competitive 1v1 game outcomes to optimize early-stage player selection. Methods: We assessed the dribbling and sprinting performances of 30 Brazilian youth players and used 1308 individual 1v1 bouts (70–90 bouts/individual) to estimate competitive abilities using a Bayesian ordinal regression model. Based on our empirical results, we then ran simulations to determine how many players should be selected when the aim is to reduce a player pool of 100 individuals so that the ‘true’ top 10 performers are reliably included and to determine how the weighting between data from closed-skill tests and games should change with increasing match observations. Results: Dribbling speed was a strong predictor of 1v1 success (β = –0.76, 95% CI: [–1.16, –0.40]), while sprint speed (β = 0.01, 95% CI: [–0.36, 0.40]) showed no significant association with 1v1 success. Simulations revealed that 26.0 ± 2.5 players were needed after five 1v1 contests per player to capture the true top 10% and then decreased to 18.0 ± 1.5 players after 20 contests. Optimal weighting shifted from a greater reliance on dribbling-based data (α > 0.80 at Game 0) to more match-based data after 10–20 contests per player (α = 0.16 at Game 20), but utilizing both sources of data improved selection accuracies and efficiencies. Conclusions: This study provides an uncertainty-aware protocol for talent identification that optimizes the integration of data from closed-skill tests and in-game performances within a dynamic selection framework that enhances precision and forms the basis for efficient early-stage scouting of large cohorts of players. Full article

We examined the effects of carbohydrate ingestion on endurance performance and fatigue during a soccer simulation in adolescent soccer players and evaluated the protocol’s reliability. Nine (13.5 ± 0.4 years pre-PHV) soccer players performed two soccer simulation intermittent exercise sessions on the treadmill (60 min) while consuming 4 boluses of either a CHO or PLC beverage in random, counterbalanced order. Before and immediately after each exercise session, MVC was measured for the quadriceps and the hand. Participants also performed a TTE on a cycle ergometer on three occasions, after each simulation exercise session (CHO and PLC), and on another day in a rested state (CON). The simulation protocol produced an ICC of 0.96 ([0.77–0.98 95%CI], p = 0.01) for VO₂, with 2.24%CV between trials, suggesting strong reliability. TTE was higher (p = 0.01) in the CHO condition (123 ± 33 s) compared to PLC (85 ± 5 s) by 29%. The relative reduction in MVC_LEG was more pronounced in the PLC (22 ± 11%) condition than in CHO (14 ± 6%) (p = 0.05). Compared to the PLC, CHO resulted in lower RPE_local during the second half of the simulation protocol (p < 0.05). Carbohydrate ingestion can improve endurance performance and reduce peripheral fatigue during a reliable soccer simulation that resembles the physiological demands of a youth soccer match. Full article

The field of physically interactive electronic games is rapidly evolving, driven by the fact that it combines the benefits of physical activities and the attractiveness of electronic games, as well as advancements in sensor technologies. In this paper, a new game was introduced, which is a special version of Bubble Soccer, which we named Q-eBall. It creates a dynamic and engaging experience by combining simulation and physical interactions. Q-eBall is equipped with a fall detection system, which uses an embedded electronic circuit integrated with an accelerometer, a gyroscopic, and a pressure sensor. An evaluation of the performance of the fall detection system in Q-eBall is presented, exploring its technical details and showing its performance. The system captures the data of players’ movement in real-time and transmits it to the game controller, which can accurately identify when a player falls. The automated fall detection process enables the game to take the required actions, such as transferring possession of the visual ball or applying fouls, without the need for manual intervention. Offline experiments were conducted to assess the performance of four machine learning models, which were K-Nearest Neighbors (KNNs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), for falls detection. The results showed that the inclusion of pressure sensor data significantly improved the performance of all models, with the SVM and LSTM models reaching 100% on all metrics (accuracy, precision, recall, and F1-score). To validate the offline results, a real-time experiment was performed using the pre-trained SVM model, which successfully recorded all 150 falls without any false positives or false negatives. These findings prove the reliability and effectiveness of the Q-eBall fall detection system in real time. Full article

Training in team sports such as soccer requires advanced technical and tactical skills for effective decision-making, particularly when executing a shot. This study validates an innovative instrument, a training platform (TP), designed to measure and enhance decision-making in dual-task scenarios. The TP aims to improve visual–motor reactions in multitask environments that simulate real game conditions. Equipped with an LED panel, main circuitry, ball sensor, and targets, the TP challenges players to kick the ball in response to the illumination of the final LED array on the panel while hitting a designated target. The study evaluated three parameters: reaction time (RT), ball speed (BS) and accuracy. To validate the TP against a gold standard (GS), we conducted correlation analyses. The results exhibited very strong correlations for both RT (r = 0.997) and BS (r = 0.994). The mean differences between TP and GS measurements were 13 ± 15 ms for RT and 0.1 ± 0.5 km/h for BS. Bland–Altman plots revealed trend lines obtained by a simple linear regression of r = −0.507, p = 0.307 for RT and r = 0.134, p = 0.077 for BS. The TP effectively simulates game scenarios, offering advantages such as low-cost components, installation flexibility, test variability, instant feedback, and integration of physical and cognitive components of sports performance. Full article

The payoff of an agent depends on both the environment and the actions of other agents. Thus, the ability to model and predict the strategies and behaviors of other agents in an interactive decision-making scenario is one of the core functionalities in intelligent systems. State-of-the-art methods for opponent modeling mainly use an explicit model of opponents’ actions, preferences, targets, etc., that the primary agent uses to make decisions. It is more important for an agent to increase its payoff than to accurately predict opponents’ behavior. Therefore, we propose a framework synchronizing the opponent modeling and decision making of the primary agent by incorporating opponent modeling into reinforcement learning. For interactive decisions, the payoff depends not only on the behavioral characteristics of the opponent but also the current state. However, confounding the two obscures the effects of state and action, which then cannot be accurately encoded. To this end, state evaluation is separated from action evaluation in our model. The experimental results from two game environments, a simulated soccer game and a real game called quiz bowl, show that the introduction of opponent modeling can effectively improve decision payoffs. In addition, the proposed framework for opponent modeling outperforms benchmark models. Full article

Mobile games continue to gain popularity, and their revenues are increasing accordingly. However, due to the inherent constraints of small screen sizes and restrictions of computing, it has been considered challenging to simulate the complex gameplay of soccer games. To this end, this paper aims to design and develop a simplified version of a five vs. five hyper-casual futsal game with only three player positions: goalkeeper, striker, and defender. It also tests a demo game to verify whether it is possible to implement an AI agent−player for each position to machine-learn and to run on a mobile device. A demo game with an AI agent−player was simulated using both PPO and SAC algorithms, and the feasibility and stability of the algorithms were compared. The results showed that each AI agent−player achieved the assigned objectives for each position and successfully machine-learned. When the algorithms were compared, the SAC algorithm showed a more stable state than the PPO algorithm when SAC directed the gameplay and interactive AI techniques. This paper shows the great potential of the application of machine-learned AI agent−players for soccer simulators on mobile platforms. Full article

Ketone supplementation has been proposed to enhance cognition during exercise. To assess whether any benefits are due to reduced cognitive fatigue during the latter portions of typical sport game action, we induced cognitive fatigue, provided a ketone monoester supplement (KME) vs. a non-caloric placebo (PLAC), and assessed cognitive performance during a simulated soccer match (SSM). In a double-blind, balanced, crossover design, nine recreationally active men (174.3 ± 4.2 cm, 76.6 ± 7.4 kg, 30 ± 3 y, 14.2 ± 5.5 % body fat, $\dot{V}$O₂ max = 55 ± 5 mL·kg BM⁻¹·min⁻¹; mean ± SD) completed a 45-min SSM (3 blocks of intermittent, variable intensity exercise) consuming either KME (25 g) or PLAC, after a 40-min mental fatiguing task. Cognitive function (Stroop and Choice Reaction Task [CRT]) and blood metabolites were measured throughout the match. KME reduced concentrations of both blood glucose (block 2: 4.6 vs. 5.2 mM, p = 0.02; block 3: 4.7 vs. 5.3 mM, p = 0.01) and blood lactate (block 1: 4.7 vs. 5.4 mM, p = 0.05; block 2: 4.9 vs. 5.9 mM, p = 0.01) during the SSM vs. PLAC, perhaps indicating a CHO sparing effect. Both treatments resulted in impaired CRT performance during the SSM relative to baseline, but KME displayed a reduced (p < 0.05) performance decrease compared to PLAC (1.3 vs. 3.4% reduction in correct answers, p = 0.02). No other differences in cognitive function were seen. These data suggest that KME supplementation attenuated decrements in CRT during repeated, high intensity, intermittent exercise. More study is warranted to assess fully the potential cognitive/physical benefits of KME for athletes. Full article

Due to a colossal soccer market, soccer analysis has attracted considerable attention from industry and academia. In-game outcome prediction has great potential in various applications such as game broadcasting, tactical decision making, and betting. In some sports, the method of directly predicting in-game outcomes based on the ongoing game state is already being used as a statistical tool. However, soccer is a sport with low-scoring games and frequent draws, which makes in-game prediction challenging. Most existing studies focus on pre-game prediction instead. This paper, however, proposes a two-stage method for soccer in-game outcome prediction, namely in-game outcome prediction (IGSOP). When the full length of a soccer game is divided into sufficiently small time frames, the goal scored by each team in each time frame can be modeled as a random variable following the Bernoulli distribution. In the first stage, IGSOP adopts state-based machine learning to predict the probability of a scoring goal in each future time frame. In the second stage, IGSOP simulates the remainder of the game to estimate the outcome of a game. This two-stage approach effectively captures the dynamic situation after a goal and the uncertainty in the late phase of a game. Chinese Super League data have been used for algorithm training and evaluation, and the results demonstrate that IGSOP outperforms existing methods, especially in predicting draws and prediction during final moments of games. IGSOP provides a novel perspective to solve the problem of in-game outcome prediction in soccer, which has a potential ripple effect on related research. Full article

Soccer is an attractive and popular team sport that has high physiological and fitness stress, and therefore requires special and controlled training programs during the season. The aim of this study was to describe the weekly average and changes in training monotony (TM) and training strain (TS) throughout different periods of the season in professional football players based on the number of accelerations and decelerations, and also to analyze the difference between starters and non-starters players in TM and TS. Nineteen professional players from a soccer team competing in the Iranian Premier League (age, 28 ± 4.6 years; height, 181.6 ± 5.8 cm; body mass, 74.5 ± 5.6 kg, and body mass index, 21.8 ± 1.0 kg/m²) participated in a cohort study. Participants were divided into two groups based on the time of participation in the weekly competition: starters (N = 10) or non-starters (N = 9). The physical activities of the players were recorded during the training sessions and competitive matches of 43 weeks using GPSPORTS systems Pty Ltd. During pre- and end-season TS was not significantly different between starters and non-starters, while during early- and mid-season starters showed a higher TS than non-starter (p < 0.05). TS was higher during early- and mid-season compared to pre- and end-season. In all zones on both the TM and TS variables, non-starters experienced higher change percentages and coefficient of variation. TM during the season in all zones of accelerations was not significantly different between starters and non-starters. while during mid-season starters showed a higher TM than non-starters in all zones of decelerations (p < 0.05). TM data showed fluctuations and w-shaped graphs in the week-by-week survey. These results indicate that training during early- and mid-season is not enough for the physical development of non-starters soccer players. Coaches should be more careful when designing training for non-starters players, and they could consider the use of game simulation, preparatory match or intra-team match, or individual training programs. Full article

Background: This field experiment investigated the acute effects of brief mindfulness-based intervention (MBI) coupled with carbohydrate (CHO) intake on players’ recovery from half-time break in a simulated soccer competition. Methods: In a single-blinded randomized crossover experiment, 14 male players received 3 treatments (Control: non-carbohydrate solution + travelling introduction audio; CHO: CHO–electrolyte solution + travelling introduction audio; and CHO_M: CHO–electrolyte solution + MBI) during simulated half-time breaks. Vertical jump, sprint performance, mindfulness level, rate of perceived exertion, muscle pain, mental fatigue, blood glucose, and lactate were measured immediately before, during, and after the exercise. Results: (1) MBI significantly increased participants’ mindfulness level (Control vs. CHO_M, p < 0.01; CHO vs. CHO_M, p < 0.01) and decreased mental fatigue for CHO_M condition (pre vs. post, p < 0.01); (2) participants in the CHO_M condition performed better in the repeated sprint tests than in the Control and CHO condition (Control vs. CHO_M, p = 0.02; CHO vs. CHO_M, p = 0.02). Conclusion: Findings of this study provide preliminary evidence of the positive effect of MBI coupled with CHO ingestion on athletes’ recovery from fatigue in the early stage of the second half of a game. Full article

Rules determine how team sport matches occur. Match-induced fatigue is specific to each sport, and may be associated with injury incidence. For example, the injury rate in soccer is distinctly higher during matches than in training sessions. Understanding the differences between team sports rules might be useful for enhancing rules (e.g., safer sport). Therefore, this study aimed to evaluate the impact of the rule-induced physical demands between soccer, futsal, basketball, and handball, focusing on substitution rules. Data from the elite team sports’ rules (e.g., absolute and relative court dimensions; the number of players, substitutions allowed, total game time, time-outs) were collected, including the changes due to the coronavirus disease (COVID-19) pandemic in soccer substitutions, and comparisons were performed. The data showed that soccer has higher rule-induced physical demands: e.g., substantially lower substitution rate, higher dimensions in absolute (eight to fifteen times), and relative (four to eight times) values. Simulations also showed that soccer has extremely large differences, even considering COVID-19 substitution changes (from three to up to five). We conclude that elite soccer has remarkably higher overall rule-induced physical demands than elite futsal, basketball and handball, and increasing soccer substitutions permanently (e.g., unlimited) might mitigate overall soccer demands. Full article

In recent times, football (soccer) has aroused an increasing amount of attention across continents and entered unexpected dimensions. In this course, the number of bookmakers, who offer the opportunity to bet on the outcome of football games, expanded enormously, which was further strengthened by the development of the world wide web. In this context, one could generate positive returns over time by betting based on a strategy which successfully identifies overvalued betting odds. Due to the large number of matches around the globe, football matches in particular have great potential for such a betting strategy. This paper utilizes machine learning to forecast the outcome of football games based on match and player attributes. A simulation study which includes all matches of the five greatest European football leagues and the corresponding second leagues between 2006 and 2018 revealed that an ensemble strategy achieves statistically and economically significant returns of 1.58% per match. Furthermore, the combination of different machine learning algorithms could neither be outperformed by the individual machine learning approaches nor by a linear regression model or naive betting strategies, such as always betting on the victory of the home team. Full article

Soccer is a complex team sport and success in this discipline depends on different factors such as physical fitness, player technique and team tactics, among others. In the last few years, several studies have described the impact of caffeine intake on soccer physical performance, but the results of these investigations have not been properly reviewed and summarized. The main objective of this review was to evaluate critically the effectiveness of a moderate dose of caffeine on soccer physical performance. A structured search was carried out following the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines in the Medline/PubMed and Web of Science databases from January 2007 to November 2018. The search included studies with a cross-over and randomized experimental design in which the intake of caffeine (either from caffeinated drinks or pills) was compared to an identical placebo situation. There were no filters applied to the soccer players’ level, gender or age. This review included 17 articles that investigated the effects of caffeine on soccer-specific abilities (n = 12) or on muscle damage (n = 5). The review concluded that 5 investigations (100% of the number of investigations on this topic) had found ergogenic effects of caffeine on jump performance, 4 (100%) on repeated sprint ability and 2 (100%) on running distance during a simulated soccer game. However, only 1 investigation (25%) found as an effect of caffeine to increase serum markers of muscle damage, while no investigation reported an effect of caffeine to reduce perceived fatigue after soccer practice. In conclusion, a single and moderate dose of caffeine, ingested 5–60 min before a soccer practice, might produce valuable improvements in certain abilities related to enhanced soccer physical performance. However, caffeine does not seem to cause increased markers of muscle damage or changes in perceived exertion during soccer practice. Full article