rss_2.0International Journal of Computer Science in Sport FeedSciendo RSS Feed for International Journal of Computer Science in Sporthttps://sciendo.com/journal/IJCSShttps://www.sciendo.comInternational Journal of Computer Science in Sport Feedhttps://sciendo-parsed.s3.eu-central-1.amazonaws.com/6471f6f0215d2f6c89db6f13/cover-image.jpghttps://sciendo.com/journal/IJCSS140216Comparison between six-week exergaming, conventional balance and no exercise training program on older adults’ balance and gait speedhttps://sciendo.com/article/10.2478/ijcss-2024-0006<abstract> <title style='display:none'>Abstract</title> <p>We evaluated differences between a six-week exergame-training and a conventional balance training program on the balance and gait speed of older adults’ (&gt;65 years). Forty-two healthy participants were recruited from independent living and community centers and randomized to one of three groups: exergaming balance training (EBT), conventional balance training (CBT), or control (no training). The participants completed two balance measurements (Fullerton Advanced Balance Scale (FAB) and center of pressure (COP) excursion), and gait speed at pre, post-intervention, and after a three-week follow-up. Both EBT and CBT groups improved their scores on the FAB, COP displacement, and gait speed post-intervention (p&lt;0.05) and these changes were maintained and did not return to pre-training values after three weeks of detraining. The control group scores for FAB and gait velocity values declined (p&lt;0.001) but not COP excursions during the study. This six-week exergame training program improved balance control and gait speed in community-dwelling seniors in a similar fashion to conventional training. Participants’ physical abilities scores improved and were maintained following three weeks of detraining. Exergame-based training therefore may be considered as an intervention that can address balance control and gait speed in older adults. As well improved scores can be maintained with transient or sporadic activity.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00062024-06-05T00:00:00.000+00:00The application of Machine and Deep Learning for technique and skill analysis in swing and team sport-specific movement: A systematic reviewhttps://sciendo.com/article/10.2478/ijcss-2024-0007<abstract> <title style='display:none'>Abstract</title> <p>There is an ever-present need to objectively measure and analyze sports motion for the determination of correct patterns of motion for skill execution. Developments in performance analysis technologies such as inertial measuring units (IMUs) have resulted in enormous data generation. However, these advances present challenges in analysis, interpretation, and transformation of data into useful information. Artificial intelligence (AI) systems can process and analyze large amounts of data quickly and efficiently through classification techniques. This study aimed to systematically review the literature on Machine Learning (ML) and Deep Learning (DL) methods applied to IMU data inputs for evaluating techniques or skills in individual swing and team sports. Electronic database searches (IEEE Xplore, PubMed, Scopus, and Google Scholar) were conducted and aligned with the PRISMA statement and guidelines. A total of 26 articles were included in the review. The Support Vector Machine (SVM) was identified as the most utilized model, as per 7 studies. A deep learning approach was reported in 6 studies, in the form of a Convolutional Neural Network (CNN) architecture. The in-depth analysis highlighted varying methodologies across all sports inclusive of device specifications, data preprocessing techniques and model performance evaluation. This review highlights that each step of the ML modeling process is iterative and should be based on the specific characteristics of the movement being analyzed.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00072024-06-05T00:00:00.000+00:00A Pilot Study in Sensor Instrumented Training (SIT) - Ground Contact Time for Monitoring Fatigue and Curve Running Techniquehttps://sciendo.com/article/10.2478/ijcss-2024-0005<abstract> <title style='display:none'>Abstract</title> <p>This study examines the possibilities of sensor-instrumented training (SIT) in mid-distance running training sessions. Within this framework, variations of ground contact time (GCT) between straight and curved running, as well as GCT as a fatigue indicator, are explored. Seven experienced runners, with two elite female athletes, participated in two training protocols: 15 sets of 400 m with 1-minute rest and five sets of 300 m with 3-minute rest. GCT was calculated using two inertial measurement units (IMU) attached to the athletes’ feet. The running speed of all athletes was measured with wearable GPS devices. GCT showed variations between inner and outer feet, notably during curve running (300m: 2.56%; 400m: 2.35%). However, for the 300m runs, statistically insignificant GCT differences were more pronounced in straight runs (3.54%) than in curve runs (2.56%), contrasting with the typical assumption of higher differences in curve running. A fatigue-indicating pattern is visible in GCT, as well as speed curves. Other data of this study are consistent with prior research that has observed differences between the inner and outer foot during curve running, while our understanding of the development throughout the training session is enhanced. Using SIT can be a valuable tool for refining curve running technique. By incorporating novel sensing technology, the possibilities enhance our understanding of running kinematics and offer an excellent application of SIT in sports.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00052024-06-05T00:00:00.000+00:00The Success-Score in Professional Football: a metric of playing style or a metric of match outcome?https://sciendo.com/article/10.2478/ijcss-2024-0004<abstract> <title style='display:none'>Abstract</title> <p>In the growing field of data analysis in soccer tracking data is analyzed utilizing increasingly complex methods to account for the dynamic, multifactorial nature of the game. One promising approach is the Success-Score combining ball control and space control. The resulting metric is hypothesized to indicate performance levels and to distinguish performance from playing style. Position datasets from one season of the German Bundesliga were analyzed by calculating Success-Scores based on different interval lengths for two different areas. The relative goalscoring frequency above resp. below the 80<sup>th</sup> percentile and the rank order correlation between goals and Success-Scores was used to assess the relevance of the Success- Score for goalscoring. The influence of the Success-Score on match outcome, accounting for possession and opponent quality was analyzed via mixed linear models. Results indicated a relation between goalscoring and the Success-Scores, as well as a considerable influence of the Success-Scores on match outcome. The mixed linear models allowed to conclude that Success-Scores capture performance rather than just playing style. The results highlight the potential of the general concept of the Success-Score, combining space and ball control. However, the practical value of the Success-Score in its current implementation appears limited and requires further development.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00042024-04-18T00:00:00.000+00:00Spin measurement system for table tennis balls based on asynchronous non-high-speed camerashttps://sciendo.com/article/10.2478/ijcss-2024-0003<abstract> <title style='display:none'>Abstract</title> <p>The spin of the ball plays a crucial role in table tennis tactics. However, it has rarely been measured and reported for the broadcast audience to better understand table tennis matches. This paper introduces a system designed to measure the spin of a table tennis ball without using electrically synchronized shutters or high-speed cameras. The system employs multiple unsynchronized cameras to detect the logos printed on the ball and estimates its three-dimensional translational motion to determine the spin rate (rotational velocity expressed in the revolutions per unit time) and spin axis (imaginary line around which the ball rotates). An experimental analysis indicated median errors of 0.78 rps and 12.5° in spin rate and axis, respectively. Additionally, the system exhibited sufficient resolution to analyze the spin rate and axis of a service ball in table tennis, distinguishing between spin axes that differ by 30° with 95.8% confidence. The developed system was used in the Japanese T-League to report the spin of several services after the live streaming of matches. The developed system successfully measured the spins of 92.1% of the served balls, confirming that the system has sufficient capability to feedback spin data immediately after a match.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00032024-03-09T00:00:00.000+00:00Automatic Detection of Faults in Simulated Race Walking from a Fixed Smartphone Camerahttps://sciendo.com/article/10.2478/ijcss-2024-0002<abstract> <title style='display:none'>Abstract</title> <p>Automatic fault detection is a major challenge in many sports. In race walking, judges visually detect faults according to the rules. Hence, automatic fault detection systems will help a training of race walking without experts’ visual judgement. Some studies have attempted to use sensors and machine learning to automatically detect faults. However, there are problems associated with sensor attachments and equipment such as a high-speed camera, which conflict with the visual judgement of judges, and the interpretability of the fault detection models. In this study, we proposed an automatic fault detection system for non-contact measurement. We used pose estimation and machine learning models trained based on the judgements of multiple qualified judges to realize fair fault judgement. We verified them using smartphone videos of normal race walking and walking with intentional faults in several athletes including the medalist of the Tokyo Olympics. The results show that the proposed system detected faults with an average accuracy of over 90%. We also revealed that the machine learning model detects faults according to the rules. In addition, the intentional faulty walking movement of the medalist was different from that of other walkers. This finding informs realization of a more general fault detection model.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00022024-03-09T00:00:00.000+00:00The Use of Momentum-Inspired Features in Pre-Game Prediction Models for the Sport of Ice Hockeyhttps://sciendo.com/article/10.2478/ijcss-2024-0001<abstract> <title style='display:none'>Abstract</title> <p>We make a unique contribution to momentum research by proposing a way to quantify momentum with performance indicators (i.e., features). We argue that due to measurable randomness in the NHL, sequential outcomes’ dependence or independence may not be the best way to approach momentum. Instead, we quantify momentum using a small sample of a team’s recent games and a linear line of best-fit to determine the trend of a team’s performances before an upcoming game. We show that with the use of SVM and logistic regression these momentum- based features have more predictive power than traditional frequency-based features in a pre-game prediction model which only uses each team’s three most recent games to assess team quality. While a random forest favors the use of both feature sets combined. The predictive power of these momentum-based features suggests that momentum is a real phenomenon in the NHL and may have more effect on the outcome of games than suggested by previous research. In addition, we believe that how our momentum-based features were designed and compared to frequency-based features could form a framework for comparing the short-term effects of momentum on any individual sport or team.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2024-00012024-02-24T00:00:00.000+00:00Pacing Patterns of Half-Marathon Runners: An analysis of ten years of results from Gothenburg Half Marathonhttps://sciendo.com/article/10.2478/ijcss-2023-0014<abstract> <title style='display:none'>Abstract</title> <p>The Gothenburg Half Marathon is one of the world’s largest half marathon races with over 40 000 participants each year. In order to reduce the number of runners risking over-straining, injury, or collapse, we would like to provide runners with advice to appropriately plan their pacing. Many participants are older or without extensive training experience and may particularly benefit from such pacing assistance. Our aim is to provide this with the help of machine learning. We first analyze a large publicly available dataset of results from the years 2010 - 2019 (n = 423 496) to identify pacing patterns related to age, sex, ability, and temperature of the race day. These features are then used to train machine learning models for predicting runner’s finish time and to identify which runners are at risk of making severe pacing errors and which ones seem set to pace well. We find that prediction of finish time improves over the current baseline, while identification of pacing patterns correctly identifies over 70% of runners at risk of severe slowdowns, albeit with many false positives.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00142024-02-03T00:00:00.000+00:00Attack with Empty Goal (7 vs 6) in Team Handball - Analysis of Men’s EHF Euro 2022https://sciendo.com/article/10.2478/ijcss-2023-0012<abstract> <title style='display:none'>Abstract</title> <p>Team handball is constantly evolving. Since the beginning of the century some changes has been introduced but no rule has been as controversial and not consensual as the one introduced in 2016 that allows the change of a goalkeeper for a field player (Empty goal) allowing teams to play 7 vs. 6 (Prudente et al., 2022). With this study we intend to analyze and characterize the attack with empty goal (7 vs. 6) of the 12 best ranked teams in Men’s EHF Euro 2022. Observational Methodology was used and it was built, validated by experts and subsequently used a mixed ad hoc instrument combining a 12 criteria field format with 77 category category system to observe and register data. Data were gathered from 28 matches involving teams classified in the first twelve places in the 2022 Men’s EHF Euro 2022. These were recorded from TV broadcasts, and the total number of offensive sequences carried out in an organized attack game method 7 vs. 6 with empty goal (n = 121) was analyzed. For data analysis, prospective and retrospective sequential analysis and the technique of polar coordinates was used. The main results show a stronger association between: a) No Goal by Technical Fault and succeeded direct goal attempt; b) Direct Goal Attempt and Goal. Results also show that best ranked teams used less 7 vs. 6 attack system. According to the main results, teams that used 7 vs. 6 and lost the ball by technical fault had a stronger association with a direct goal attempt by the opponent team. That is positively associated with goal. This leads to a practical recommendation that teams that want to use 7 vs. 6 should practice this special option in order to achieve more efficiency, reducing the number of technical faults and consequently the opponents goal to goal attempts.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00122023-11-06T00:00:00.000+00:00Success-Score in Professional Soccer – Is there a sweet spot in the analysis of space and ball control?https://sciendo.com/article/10.2478/ijcss-2023-0013<abstract> <title style='display:none'>Abstract</title> <p>In contrast to simple performance indicators in the practical application of quantitative analysis in professional soccer, the inclusion of certain contextual elements can improve both the predictive quality and interpretability of these. Therefore, the Success-Score is intended to identify the factors relevant to success by linking ball control and space control.</p> <p>Position datasets from 14 games of the Bundesliga were used to calculate Success-Scores for several interval lengths for the penalty area and the 30-meter-zone. The relative goalscoring frequency above resp. below the 80<sup>th</sup> percentile, the rank correlation in terms of goals scored pursuant to the sorting of the Success-Score as well as possible distinctions in the Success-Score between two teams of different quality were examined.</p> <p>Results revealed that interval lengths and the area under investigation largely affect the resulting Success-Score and its distribution. The Success-Score applied to the 30-meter-zone seems preferable when analyzing goalscoring. Dependent on the target of analysis, methodological and theoretical considerations need to be balanced in a sweet spot of the interval length.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00132023-10-26T00:00:00.000+00:00A comparison of tournament systems for the men’s World Handball Championshiphttps://sciendo.com/article/10.2478/ijcss-2023-0011<abstract> <title style='display:none'>Abstract</title> <p>The men’s Handball World Championship commences with eight round robin groups of four teams before the “main round” of four groups of six teams. These groups of six each include the top three teams from pairs of initial groups. The tournament draw uses pots of eight which risks two teams in the top four appearing in the same group of the main round. A further issue is that teams finishing between third and sixth in the main round groups are awarded tournament places between ninth and 24th without any further matches. Therefore, the purpose of this investigation was to compare the current tournament system with alternatives using pots of four teams in the draw, and / or adding a knockout stage to place teams from ninth to 24th. These four tournament systems were simulated 100,000 times, using underlying regression models for the goals scored based on their World ranking points. Introducing pots of four increased the chance of reaching the quarter-finals for teams ranked one to four and nine to 12 by 1.3% and 1.6% respectively. It is recommended that the draw uses pots of four teams associated with pairs of initial groups that lead to common main draw groups.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00112023-10-06T00:00:00.000+00:00Acceptance and Intended Use of a Feedback System for Fencing https://sciendo.com/article/10.2478/ijcss-2023-0009<abstract><title style='display:none'>Abstract</title> <p>Fencing is a sport requiring high levels of physical and mental abilities from athletes. Amongst others traits, fencers need to be able to hit small targets with high accuracy. In order to be able to investigate changes in the accuracy of fencers over prolonged periods of training, a training device needs to be accepted by its users. This article presents a low-cost feedback system that can be used to train and monitor accuracy. The system was evaluated for its acceptance and intended use by potential users using a qualitative version of the Unified Theory of Acceptance and Use of Technology (UTAUT2) (Venkatesh et al. 2012). Nine athletes participated in the evaluation. After conducting a standardized session, qualitative interviews were conducted with the athletes. Categorization was performed inductively along the dimensions of the UTAUT2 model. Results showed that the athletes were satisfied with the prototype and expressed their desire for a system with a simple setup. No effect of gender on usage intentions was found. However, an effect of age and/or experience on how athletes intend to use such as system was identified. More experienced athletes intended to use the system in dedicated parts of their training while novice athletes desired to integrate it into existing training sessions. </p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00092023-10-04T00:00:00.000+00:00The Kos Angle, an optimizing parameter for football expected goals (xG) modelshttps://sciendo.com/article/10.2478/ijcss-2023-0010<abstract><title style='display:none'>Abstract</title> <p>The utilization of metrics such as expected goals (xG) has the potential to provide teams with a competitive edge. By incorporating xG into their analysis and decision-making processes, teams can gain valuable insights. This study proposes a new approach to football xG modeling using Kos Angle which represents the shooting angle, from which we substract the angles occupied by players inside the shot angle. The objective of this study is to evaluate the impact of the Kos Angle feature on the performance of football xG models. After developing the mathematical formula of the Kos Angle, we selected additional features and built different xG models. Subsequently, the impact of the Kos Angle feature on the models’ performances was evaluated, revealing an increase in Recall and Precision and a decrease in Brier score and RMSE. We also found that the Kos Angle accounted for a significant portion of the models’ predictive power. By providing a more realistic representation of shot situations, the addition of the Kos Angle feature allows the improvement of xG models performances, which can give a more valuable insights to football professionals who rely on xG metrics and their variations. </p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00102023-09-13T00:00:00.000+00:00Developing a High-Performance Sports Results Prediction Artificial Neural Network: Case Study on World Championship Boxinghttps://sciendo.com/article/10.2478/ijcss-2023-0008<abstract> <title style='display:none'>Abstract</title> <p>Major sports events are watched by millions around the world and the prediction of event outcomes is a subject of interest to many stakeholders which underlines the relevance of continuous development and improvement of prediction models. This study uses a factorial design methodology to develop and test 18 Artificial Neural Network (ANN) models for the prediction of world championship boxing matches. The methodology was applied to evaluate the individual and collaborative effects of feature selection, ANN architecture and training data selection on the prediction performance of ANNs. Feature selection was found to be the most influential factor on prediction performance with a statistically significant Analysis of Variance (ANOVA) between the feature selection levels and the test accuracy (p-value of 0.012). The collaborative effect of training data selection and feature selection on prediction performance was found to be statistically significant with ANOVA p-value of 0.007. The best performing model achieved a test accuracy of 81.53% which is an improvement to current benchmarks for sports prediction. The findings of this study contribute to the development of future machine learning sports prediction models.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00082024-06-05T00:00:00.000+00:00Hierarchical Bayesian analysis of racehorse running ability and jockey skillshttps://sciendo.com/article/10.2478/ijcss-2023-0007<abstract> <title style='display:none'>Abstract</title> <p>In this paper, we proposed a new method of evaluating horse ability and jockey skills in horse racing. In the proposed method, we aimed to estimate unobservable individual effects of horses and jockeys simultaneously with regression coefficients for explanatory variables such as horse age and racetrack conditions and other parameters in the regression model. The data used in this paper are records on 1800­m races (excluding steeplechases) held by the Japan Racing Association from 2016 to 2018, including 4063 horses and 143 jockeys. We applied the hierarchical Bayesian model to stably estimate such a large amount of individual effects. We used the Markov chain Monte Carlo (MCMC) method coupled with Ancillarity- Sufficiency Interweaving Strategy for Bayesian estimation of the model and choose the best model with Widely Applicable Information Criterion as a model selection criterion. As a result, we found a large difference in the ability among horses and jockeys. Additionally, we observed a strong relationship between the individual effects and the race records for both horses and jockeys.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00072023-08-19T00:00:00.000+00:00Systematic Analysis of Position-Data-based Key Performance Indicatorshttps://sciendo.com/article/10.2478/ijcss-2023-0006<abstract> <title style='display:none'>Abstract</title> <p>In the past 20 years, performance analysis in soccer has accumulated a wide variety of key performance indicators (KPI’s) aimed at reflecting a team’s strength and success. Thanks to rapidly advancing technologies and data analytics more sophisticated metrics, requiring high resolution data acquisition and big data methods, are developed. This includes many position-data-based KPI’s, which incorporate precise spatial and temporal information about every player and the ball on the field.</p> <p>The present study contributes to this research by performing a large-scale comparison of several metrics mainly based on player positions and passing events. Their association with team’s success (derived from goals scored) and team’s strength (estimated from pre-game betting odds) is analysed.</p> <p>The systematic analysis revealed relevant results for further KPI research: First, the magnitude of overall correlation coefficients was higher for relative metrics than for absolute metrics. Second, the correlation of metrics with the strength of a team is stronger than the correlation with the game success of a team. Third, correlation analysis with team strength indicated more positive associations, while correlation analysis with success is most likely confounded by the intermediate score line of a game and revealed more negative associations.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00062023-06-16T00:00:00.000+00:00Detecting Outliers in Cardiopulmonary Exercise Testing Data of Ski Racers – A Comparison of Methods and their Effect on the Performance of Fatigue Predictionhttps://sciendo.com/article/10.2478/ijcss-2023-0005<abstract> <title style='display:none'>Abstract</title> <p>In sports science, cardiopulmonary data is used to assess exercise intensity, performance and health status of athletes and derive relevant target values. However, sensors may produce flawed data and data may include a wide variety of artifacts, which could potentially lead to false conclusions. Thus, appropriate and customized pre-processing algorithms are a vital prerequisite for producing reliable and valid analysis results. To find adequate outlier detection methods for this type of data, we compared three algorithms by applying them on seven ergospirometric measures of junior ski racing athletes and applied a model to predict fatigue during skiing based on the pre-processed data. While values that lie outside a realistic spectrum were consistently labelled as outliers by all methods, and mean values and standard deviations changed in similar ways, methods differed from each other when it comes to changing trends, recurring patterns, and subsequent outliers. Decomposing the sensor data into different components (trend, seasonality, remainder) before dealing with outliers increased average predictive performance the most. However, pre-processing remarkably improved prediction results for certain study participants and not for others. Thus, handling outliers correctly prior to deriving information from ergospirometric data is recommended but more research should be conducted to find methods that achieve more consistent improvement.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00052023-06-04T00:00:00.000+00:00A Decision Support System for Simulating and Predicting the Impacts of Various Tournament Structures on Tournament Outcomeshttps://sciendo.com/article/10.2478/ijcss-2023-0004<abstract> <title style='display:none'>Abstract</title> <p>Simulating and predicting tournament outcomes has become an increasingly popular research topic. The outcomes can be influenced by several factors, such as attack, defence and home advantage strength values, as well as tournament structures. However, the claim that different structures, such as knockout (KO), round-robin (RR) and hybrid structures, have their own time restraints and requirements has limited the evaluation of the best structure for a particular type of sports tournament using quantitative approaches. To address this issue, this study develops a decision support system (DSS) using Microsoft Visual Basic, based on the object-oriented programming approach, to simulate and forecast the impact of the various tournament structures on soccer tournament outcomes. The DSS utilized the attack, defence and home advantage values of the teams involved in the Malaysia Super League 2018 to make better prediction. The rankings produced by the DSS were then compared to the actual rankings using Spearman correlation to reveal the simulated accuracy level. The results indicate that a double RR produces a higher correlation value than a single RR, indicating that more matches played provide more data to create better predictions. Additionally, a random KO predicts better than a ranking KO, suggesting that pre-ranking teams before a tournament starts does not significantly impact the prediction. The findings of this study can help tournament organizers plan forthcoming games by simulating various tournament structures to determine the most suitable one for their needs.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00042023-05-27T00:00:00.000+00:00Sport-specific differences in key performance factors among handball, basketball and table tennis playershttps://sciendo.com/article/10.2478/ijcss-2023-0003<abstract> <title style='display:none'>Abstract</title> <p>Change of direction speed, reaction time, sprint speed, and explosive strength are important factors that determine athletes’ performance in the majority of sports. From the practical standpoint, it is of interest to investigate to what extent they differ among athletes of team and individual sports. We compared 7 handball, 11 basketball, and 15 male table tennis players in four reaction time tests, 505 Agility test, 5m and 20m sprints, squat, countermovement, and drop jumps. Basketball players performed better in reaction time to fast generating stimuli (12.6%, p=.001) and countermovement jump height (14.5%, p=.05) than handball players. In addition, they achieved a higher reactive strength index (25%, p=.01) than table tennis players. Handball players were faster in the 505 Agility test compared to table tennis players (4.6%, p=.04). Results revealed that performance of basketball players is mainly determined by explosive strength, handball players by change of direction speed, and table tennis by speed of response to visual stimuli. These differences may be ascribed to long-term adaptation to sport-specific stimuli. Novel assessment methods and devices should better determine key performance factors of athletes with regard to sport-specific tasks.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00032023-04-06T00:00:00.000+00:00Estimating the effect of hitting strategies in baseball using counterfactual virtual simulation with deep learninghttps://sciendo.com/article/10.2478/ijcss-2023-0001<abstract> <title style='display:none'>Abstract</title> <p>In baseball, every play on the field is quantitatively evaluated and the statistics have an effect on individual and team strategies. The weighted on base average (wOBA) is well known as a measure of a batter’s hitting contribution. However, this measure ignores the game situation, such as the runners on base, which coaches and batters are known to consider when employing multiple hitting strategies, yet, the effectiveness of these strategies is unknown. This is probably because (1) we cannot obtain the batter’s strategy and (2) it is difficult to estimate the effect of the strategies. Here, we propose a new method for estimating the effect using counterfactual batting simulation. The entire framework consists of two phases: (i) generate a counter-factual batter’s ability based on their actual performances and (ii) simulate games with the batting simulator. To realize (i), we propose a deep learning model that transforms batting ability when batting strategy is changed. This method can estimate the effects of various strategies, which has been traditionally difficult with actual game data. We found that, when the switching cost of batting strategies can be ignored, the use of different strategies increased runs. When the switching cost is considered, the conditions for increasing runs were limited. Our results suggest that players and coaches should be careful when employing multiple batting strategies given the trade-offs thereof. We also discuss practical baseball use-cases to use this simulation.</p> </abstract>ARTICLEtruehttps://sciendo.com/article/10.2478/ijcss-2023-00012023-01-17T00:00:00.000+00:00en-us-1