N. Baumgartner, C. Kranzinger, S. Kranzinger, C. Snyder, T. Stöggl, B. Resch
Abstract 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.
{"title":"Detecting Outliers in Cardiopulmonary Exercise Testing Data of Ski Racers – A Comparison of Methods and their Effect on the Performance of Fatigue Prediction","authors":"N. Baumgartner, C. Kranzinger, S. Kranzinger, C. Snyder, T. Stöggl, B. Resch","doi":"10.2478/ijcss-2023-0005","DOIUrl":"https://doi.org/10.2478/ijcss-2023-0005","url":null,"abstract":"Abstract 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.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43148107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract NBA teams rely heavily on their star players, though an ever-increasing tendency shows that proper ball movement is key for building a successful offense. According to experts, one of the most crucial individual contributions for this aspect is ‘making the extra pass’ – meaning to pass on a decent shooting opportunity to create an even better one. However, judging this ability is subjective, even a precise definition is missing. In this analysis, we conceptualize the event and design a method to measure this skill on an individual player level. Using this model, we analyze directly assisted shots – whether they could have been turned down to make the extra pass. In-season statistics are used to calculate the scoring efficiency of the player from the particular zone given the distance of the closest defender. Our method helps to automatically find individual situations where the extra pass could have been played to gain a margin in Expected Points and scaled up to a whole season, we are able to identify which areas of the court are the most often overlooked. By detecting these missed opportunities of extra passes, experts can easily point out situations where better teamwork can lead to better scoring opportunities.
{"title":"Modeling the extra pass in basketball – an assessment of one of the most crucial skills for creating great ball movement","authors":"Bence Supola, T. Hoch, A. Baca","doi":"10.2478/ijcss-2023-0002","DOIUrl":"https://doi.org/10.2478/ijcss-2023-0002","url":null,"abstract":"Abstract NBA teams rely heavily on their star players, though an ever-increasing tendency shows that proper ball movement is key for building a successful offense. According to experts, one of the most crucial individual contributions for this aspect is ‘making the extra pass’ – meaning to pass on a decent shooting opportunity to create an even better one. However, judging this ability is subjective, even a precise definition is missing. In this analysis, we conceptualize the event and design a method to measure this skill on an individual player level. Using this model, we analyze directly assisted shots – whether they could have been turned down to make the extra pass. In-season statistics are used to calculate the scoring efficiency of the player from the particular zone given the distance of the closest defender. Our method helps to automatically find individual situations where the extra pass could have been played to gain a margin in Expected Points and scaled up to a whole season, we are able to identify which areas of the court are the most often overlooked. By detecting these missed opportunities of extra passes, experts can easily point out situations where better teamwork can lead to better scoring opportunities.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42352407","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Justus Schlenger, Fabian Wunderlich, Dominik Raabe, D. Memmert
Abstract 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. 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. 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.
{"title":"Systematic Analysis of Position-Data-based Key Performance Indicators","authors":"Justus Schlenger, Fabian Wunderlich, Dominik Raabe, D. Memmert","doi":"10.2478/ijcss-2023-0006","DOIUrl":"https://doi.org/10.2478/ijcss-2023-0006","url":null,"abstract":"Abstract 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. 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. 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.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43012743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ruzelan Khalid, M. M. Yusof, Nurzahidah Che Rosli, M. Nawawi
Abstract 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.
{"title":"A Decision Support System for Simulating and Predicting the Impacts of Various Tournament Structures on Tournament Outcomes","authors":"Ruzelan Khalid, M. M. Yusof, Nurzahidah Che Rosli, M. Nawawi","doi":"10.2478/ijcss-2023-0004","DOIUrl":"https://doi.org/10.2478/ijcss-2023-0004","url":null,"abstract":"Abstract 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.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43748331","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract 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.
{"title":"Estimating the effect of hitting strategies in baseball using counterfactual virtual simulation with deep learning","authors":"Hiroshi Nakahara, K. Takeda, Keisuke Fujii","doi":"10.2478/ijcss-2023-0001","DOIUrl":"https://doi.org/10.2478/ijcss-2023-0001","url":null,"abstract":"Abstract 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.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41587130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rumena Komitova, Dominik Raabe, R. Rein, D. Memmert
Abstract Time series data mining deals with extracting useful and meaningful information from time series data. Recently, the increasing use of temporal data, in particular time series data, has received much attention in the literature. Since most of sports data contain time information, it is natural to consider the temporal dimension in form of time series. However, in sports, the effective use of time series data mining techniques is still under development. The main goal of this paper is therefore to serve as an introduction to time series data mining and a glossary for interested researchers from the sports community. The paper gives an overview about current data mining tasks and tries to identify their potential research direction for further investigation. Furthermore, we want to draw more attention with respect to the importance of mining approaches with sport data and their particular challenges beyond usual time series data mining tasks.
{"title":"Time Series Data Mining for Sport Data: a Review","authors":"Rumena Komitova, Dominik Raabe, R. Rein, D. Memmert","doi":"10.2478/ijcss-2022-0008","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0008","url":null,"abstract":"Abstract Time series data mining deals with extracting useful and meaningful information from time series data. Recently, the increasing use of temporal data, in particular time series data, has received much attention in the literature. Since most of sports data contain time information, it is natural to consider the temporal dimension in form of time series. However, in sports, the effective use of time series data mining techniques is still under development. The main goal of this paper is therefore to serve as an introduction to time series data mining and a glossary for interested researchers from the sports community. The paper gives an overview about current data mining tasks and tries to identify their potential research direction for further investigation. Furthermore, we want to draw more attention with respect to the importance of mining approaches with sport data and their particular challenges beyond usual time series data mining tasks.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45527607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Georgios Kyriakidis, V. Panoutsakopoulos, I. Paraschos, D. Chatzopoulos, A. Yiannakos, Georgios I. Papaiakovou
Abstract The purpose of this study was to evaluate three distinct methods of teaching the three-step ball throw simulating the javelin throw technique to primary school students. The sample consisted of 131 primary school students of 5th and 6th grade (Mage = 11.4, SD = 0.47 years) randomly divided into three groups. The control group (CON) received typical instruction, the first experimental group (EXP) followed a blended learning intervention which included an interactive learning activity software and the second experimental group (EXPVF) followed the same blended learning method with an additional direct video feedback system. A pre/post-test design was implemented to evaluate students’ technique, using as criteria five selected technique elements of the three-step ball throw. Wilcoxon signed-rank test analysis showed that all three groups performed significantly better after the intervention in all five criteria. However, Kruskal-Wallis H test analysis with post-hoc test revealed that the results for EXPVF group were significantly better than the other two groups in all elements, while the EXP group showed significantly better results in three of the five elements compared with the CON group. In conclusion, students appeared to benefit more in their three-step ball throw technique through blended learning and direct video feedback.
{"title":"The Impact of Blended Learning and Direct Video Feedback on Primary School Students’ Three-Step Ball Throwing Technique","authors":"Georgios Kyriakidis, V. Panoutsakopoulos, I. Paraschos, D. Chatzopoulos, A. Yiannakos, Georgios I. Papaiakovou","doi":"10.2478/ijcss-2022-0010","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0010","url":null,"abstract":"Abstract The purpose of this study was to evaluate three distinct methods of teaching the three-step ball throw simulating the javelin throw technique to primary school students. The sample consisted of 131 primary school students of 5th and 6th grade (Mage = 11.4, SD = 0.47 years) randomly divided into three groups. The control group (CON) received typical instruction, the first experimental group (EXP) followed a blended learning intervention which included an interactive learning activity software and the second experimental group (EXPVF) followed the same blended learning method with an additional direct video feedback system. A pre/post-test design was implemented to evaluate students’ technique, using as criteria five selected technique elements of the three-step ball throw. Wilcoxon signed-rank test analysis showed that all three groups performed significantly better after the intervention in all five criteria. However, Kruskal-Wallis H test analysis with post-hoc test revealed that the results for EXPVF group were significantly better than the other two groups in all elements, while the EXP group showed significantly better results in three of the five elements compared with the CON group. In conclusion, students appeared to benefit more in their three-step ball throw technique through blended learning and direct video feedback.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46223779","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Mandorino, A. Figueiredo, Gianluca Cima, A. Tessitore
Abstract Periods of intensified training may increase athletes’ fatigue and impair their recovery status. Therefore, understanding internal and external load markers-related to fatigue is crucial to optimize their weekly training loads. The current investigation aimed to adopt machine learning (ML) techniques to understand the impact of training load parameters on the recovery status of athletes. Twenty-six adult soccer players were monitored for six months, during which internal and external load parameters were daily collected. Players’ recovery status was assessed through the 10-point total quality recovery (TQR) scale. Then, different ML algorithms were employed to predict players’ recovery status in the subsequent training session (S-TQR). The goodness of the models was evaluated through the root mean squared error (RMSE), mean absolute error (MAE), and Pearson’s Correlation Coefficient (r). Random forest regression model produced the best performance (RMSE=1.32, MAE=1.04, r = 0.52). TQR, age of players, total decelerations, average speed, and S-RPE recorded in the previous training were recognized by the model as the most relevant features. Thus, ML techniques may help coaches and physical trainers to identify those factors connected to players’ recovery status and, consequently, driving them toward a correct management of the weekly training loads.
长时间的高强度训练会增加运动员的疲劳，影响其恢复状态。因此，了解与疲劳相关的内部和外部负荷标志对于优化他们的每周训练负荷至关重要。本研究旨在采用机器学习(ML)技术来了解训练负荷参数对运动员恢复状态的影响。对26名成年足球运动员进行了为期6个月的监测，在此期间每天收集内外负荷参数。采用10分制TQR (total quality recovery)量表评估球员的康复状态。然后，采用不同的ML算法预测球员在后续训练阶段的恢复状态(S-TQR)。通过均方根误差(RMSE)、平均绝对误差(MAE)和Pearson相关系数(r)来评价模型的优劣，其中随机森林回归模型表现最佳(RMSE=1.32, MAE=1.04, r = 0.52)。TQR、球员年龄、总减速度、平均速度和S-RPE在之前的训练中被模型识别为最相关的特征。因此，机器学习技术可以帮助教练和体能训练师识别与球员恢复状态相关的因素，从而推动他们正确管理每周的训练负荷。
{"title":"Analysis of Relationship between Training Load and Recovery Status in Adult Soccer Players: a Machine Learning Approach","authors":"M. Mandorino, A. Figueiredo, Gianluca Cima, A. Tessitore","doi":"10.2478/ijcss-2022-0007","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0007","url":null,"abstract":"Abstract Periods of intensified training may increase athletes’ fatigue and impair their recovery status. Therefore, understanding internal and external load markers-related to fatigue is crucial to optimize their weekly training loads. The current investigation aimed to adopt machine learning (ML) techniques to understand the impact of training load parameters on the recovery status of athletes. Twenty-six adult soccer players were monitored for six months, during which internal and external load parameters were daily collected. Players’ recovery status was assessed through the 10-point total quality recovery (TQR) scale. Then, different ML algorithms were employed to predict players’ recovery status in the subsequent training session (S-TQR). The goodness of the models was evaluated through the root mean squared error (RMSE), mean absolute error (MAE), and Pearson’s Correlation Coefficient (r). Random forest regression model produced the best performance (RMSE=1.32, MAE=1.04, r = 0.52). TQR, age of players, total decelerations, average speed, and S-RPE recorded in the previous training were recognized by the model as the most relevant features. Thus, ML techniques may help coaches and physical trainers to identify those factors connected to players’ recovery status and, consequently, driving them toward a correct management of the weekly training loads.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45516704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
David Brinkjans, D. Memmert, Jonas Imkamp, J. Perl
Abstract Typical performance indicators in professional quantitative soccer analysis simplify complex matters, resulting in loss of information. Hence, a novel approach to characterize the performance of soccer teams was investigated: Success-Scores, combining space control with ball control and the correlation between the two. Success-Score Profiles were calculated for 14 games from the German Bundesliga. The dataset was split into two groups: all data points above resp. below the 80th percentile of Success-Scores. Subsequently, the relative goalscoring frequency in those two groups was compared. All data points were sorted according to their Success-Score and split into equally sized eighths. These groups were tested for a rank order correlation with the number of scored goals. Finally, the Success-Scores of two teams with different success levels as well as their opponents’ Success-Scores were compared. Results indicated significantly higher goalscoring frequencies above the 80th percentile for Success-Scores and a statistically significant rank order correlation between the Success-Scores and the number of scored goals, rs(6) = 0.73, p = .04. The more successful team showed significantly higher Success-Scores. This novel performance indicator shows significant connections to success defined as scoring goals and final ranking in elite soccer and therefore shows potential in reconizing underlying performance.
{"title":"Success-Score in Professional Soccer – Validation of a Dynamic Key Performance Indicator Combining Space Control and Ball Control within Goalscoring Opportunities","authors":"David Brinkjans, D. Memmert, Jonas Imkamp, J. Perl","doi":"10.2478/ijcss-2022-0009","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0009","url":null,"abstract":"Abstract Typical performance indicators in professional quantitative soccer analysis simplify complex matters, resulting in loss of information. Hence, a novel approach to characterize the performance of soccer teams was investigated: Success-Scores, combining space control with ball control and the correlation between the two. Success-Score Profiles were calculated for 14 games from the German Bundesliga. The dataset was split into two groups: all data points above resp. below the 80th percentile of Success-Scores. Subsequently, the relative goalscoring frequency in those two groups was compared. All data points were sorted according to their Success-Score and split into equally sized eighths. These groups were tested for a rank order correlation with the number of scored goals. Finally, the Success-Scores of two teams with different success levels as well as their opponents’ Success-Scores were compared. Results indicated significantly higher goalscoring frequencies above the 80th percentile for Success-Scores and a statistically significant rank order correlation between the Success-Scores and the number of scored goals, rs(6) = 0.73, p = .04. The more successful team showed significantly higher Success-Scores. This novel performance indicator shows significant connections to success defined as scoring goals and final ranking in elite soccer and therefore shows potential in reconizing underlying performance.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47276866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Abstract This review explores the avenues for the application of meta-heuristics in sports. The necessity of sophisticated algorithms to investigate different NP hard problems encountered in sports analytics was established in the recent past. Meta-heuristics have been applied as a promising approach to such problems. We identified team selection, optimal lineups, sports equipment optimization, scheduling and ranking, performance analysis, predictions in sports, and player tracking as seven major categories where meta-heuristics were implemented in research in sports. Some of our findings include (a) genetic algorithm and particle swarm optimization have been extensively used in the literature, (b) meta-heuristics have been widely applied in the sports of cricket and soccer, (c) the limitations and challenges of using meta-heuristics in sports. Through awareness and discussion on implementation of meta-heuristics, sports analytics research can be rich in the future.
{"title":"Meta-heuristics meet sports: a systematic review from the viewpoint of nature inspired algorithms","authors":"M.K.A. Ariyaratne, R.M. Silva","doi":"10.2478/ijcss-2022-0003","DOIUrl":"https://doi.org/10.2478/ijcss-2022-0003","url":null,"abstract":"Abstract This review explores the avenues for the application of meta-heuristics in sports. The necessity of sophisticated algorithms to investigate different NP hard problems encountered in sports analytics was established in the recent past. Meta-heuristics have been applied as a promising approach to such problems. We identified team selection, optimal lineups, sports equipment optimization, scheduling and ranking, performance analysis, predictions in sports, and player tracking as seven major categories where meta-heuristics were implemented in research in sports. Some of our findings include (a) genetic algorithm and particle swarm optimization have been extensively used in the literature, (b) meta-heuristics have been widely applied in the sports of cricket and soccer, (c) the limitations and challenges of using meta-heuristics in sports. Through awareness and discussion on implementation of meta-heuristics, sports analytics research can be rich in the future.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48653003","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：