Cameron Ross, P. Lamb, P. McAlpine, G. Kennedy, C. Button
Abstract Wearable sensors that can be used to measure human performance outcomes are becoming increasingly popular within sport science research. Validation of these sensors is vital to ensure accuracy of extracted data. The aim of this study was to establish the validity and reliability of gyroscope sensors contained within three different inertial measurement units (IMU). Three IMUs (OptimEye, I Measure U and Logger A) were fixed to a mechanical calibration device that rotates through known angular velocities and positions. RMS scores for angular displacement, which were calculated from the integrated angular velocity vectors, were 3.85° ± 2.21° and 4.34° ± 2.57° for the OptimEye and IMesU devices, respectively. The RMS error score for the Logger A was 22.76° ± 23.22°, which was attributed to a large baseline shift of the angular velocity vector. After a baseline correction of all three devices, RMS error scores were all below 3.90°. Test re-test reliability of the three gyroscope sensors were high with coefficient of variation (CV%) scores below 2.5%. Overall, the three tested IMUs are suitable for measuring angular displacement of snow sports manoeuvres after baseline corrections have been made. Future studies should investigate the accuracy and reliability of accelerometer and magnetometer sensors contained in each of the IMUs to be used to identify take-off and landing events and the orientation of the athlete at those events.
可穿戴式传感器可用于测量人类表现结果，在体育科学研究中越来越受欢迎。这些传感器的验证对于确保提取数据的准确性至关重要。本研究的目的是建立陀螺仪传感器包含在三个不同的惯性测量单元(IMU)的有效性和可靠性。三个imu (OptimEye, I Measure U和Logger A)固定在一个机械校准装置上，该装置通过已知的角速度和位置旋转。根据综合角速度矢量计算的角位移RMS评分，OptimEye和IMesU装置的角位移RMS评分分别为3.85°±2.21°和4.34°±2.57°。记录器A的RMS误差评分为22.76°±23.22°，这是由于角速度矢量的基线偏移较大。在对所有三种设备进行基线校正后，RMS误差评分均低于3.90°。三种陀螺仪传感器的重测信度较高，变异系数(CV%)得分均在2.5%以下。总的来说，三个测试imu适合测量基线修正后的雪上运动动作的角位移。未来的研究应调查每个imu中包含的加速度计和磁力计传感器的准确性和可靠性，用于识别起降事件以及运动员在这些事件中的方向。
{"title":"Validation of gyroscope sensors for snow sports performance monitoring","authors":"Cameron Ross, P. Lamb, P. McAlpine, G. Kennedy, C. Button","doi":"10.2478/ijcss-2020-0004","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0004","url":null,"abstract":"Abstract Wearable sensors that can be used to measure human performance outcomes are becoming increasingly popular within sport science research. Validation of these sensors is vital to ensure accuracy of extracted data. The aim of this study was to establish the validity and reliability of gyroscope sensors contained within three different inertial measurement units (IMU). Three IMUs (OptimEye, I Measure U and Logger A) were fixed to a mechanical calibration device that rotates through known angular velocities and positions. RMS scores for angular displacement, which were calculated from the integrated angular velocity vectors, were 3.85° ± 2.21° and 4.34° ± 2.57° for the OptimEye and IMesU devices, respectively. The RMS error score for the Logger A was 22.76° ± 23.22°, which was attributed to a large baseline shift of the angular velocity vector. After a baseline correction of all three devices, RMS error scores were all below 3.90°. Test re-test reliability of the three gyroscope sensors were high with coefficient of variation (CV%) scores below 2.5%. Overall, the three tested IMUs are suitable for measuring angular displacement of snow sports manoeuvres after baseline corrections have been made. Future studies should investigate the accuracy and reliability of accelerometer and magnetometer sensors contained in each of the IMUs to be used to identify take-off and landing events and the orientation of the athlete at those events.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45639758","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. Makino, Tomohiro Odaka, J. Kuroiwa, Izumi Suwa, Hideyuki Shirai
Abstract In tennis, the accumulation of data has progressed and research on tactical analysis has been conducted. Estimating strategically important factors would have the benefit of providing players with useful advice and helping audience members understand what tennis players are good at. Previous research has been conducted into ways of predicting Association of Tennis Professionals (ATP) tennis match outcomes as well as estimating factors that are important for victories using machine learning models. The challenge of previous research is that the victory factor lacks concreteness. Since we thought the root of the abovementioned problem was that previous researchers used game summary as a feature and did not consider the process of rallies between points, this research focused on calculating the frequency of single shots, two-shot patterns, and specific effective shot patterns from each point rally of ATP singles matches. We then used those data to predict point winners and useful features using L1-regularized logistic regression. The highest accuracy obtained was 66.5%, and the area under the curve (AUC) was 0.689. The most prominent feature we found was the ratio of specific shots by specific players. From these results, our method could reveal more concretely tactical factors than previous studies.
{"title":"Feature Selection to Win the Point of ATP Tennis Players Using Rally Information","authors":"M. Makino, Tomohiro Odaka, J. Kuroiwa, Izumi Suwa, Hideyuki Shirai","doi":"10.2478/ijcss-2020-0003","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0003","url":null,"abstract":"Abstract In tennis, the accumulation of data has progressed and research on tactical analysis has been conducted. Estimating strategically important factors would have the benefit of providing players with useful advice and helping audience members understand what tennis players are good at. Previous research has been conducted into ways of predicting Association of Tennis Professionals (ATP) tennis match outcomes as well as estimating factors that are important for victories using machine learning models. The challenge of previous research is that the victory factor lacks concreteness. Since we thought the root of the abovementioned problem was that previous researchers used game summary as a feature and did not consider the process of rallies between points, this research focused on calculating the frequency of single shots, two-shot patterns, and specific effective shot patterns from each point rally of ATP singles matches. We then used those data to predict point winners and useful features using L1-regularized logistic regression. The highest accuracy obtained was 66.5%, and the area under the curve (AUC) was 0.689. The most prominent feature we found was the ratio of specific shots by specific players. From these results, our method could reveal more concretely tactical factors than previous studies.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44347456","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 Many factors are considered when making a hiring decision in the National Football League (NFL). One difficult decision that executives must make is who they will select in the offseason. Mathematical models can be developed to aid humans in their decision-making processes because these models are able to find hidden relationships within numeric data. This research proposes the Heuristic Evaluation of Artificially Replaced Teammates (HEART) methodology, which is a mathematical model that utilizes machine learning and statistical-based methodologies to aid managers with their hiring decisions. The goal of HEART is to determine expected and theoretical contribution values for a potential candidate, which represents a player’s ability to increase or decrease a team’s forecasted winning percentage. In order to validate the usefulness of the methodology, the results of a 2007 case study were presented to subject matter experts. After analyzing the survey results statistically, five of the eight decision-making categories were found to be “very useful” in terms of the information that the methodology provided.
{"title":"A Team-Compatibility Decision Support System for the National Football League","authors":"William A. Young, G. Weckman","doi":"10.2478/ijcss-2020-0005","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0005","url":null,"abstract":"Abstract Many factors are considered when making a hiring decision in the National Football League (NFL). One difficult decision that executives must make is who they will select in the offseason. Mathematical models can be developed to aid humans in their decision-making processes because these models are able to find hidden relationships within numeric data. This research proposes the Heuristic Evaluation of Artificially Replaced Teammates (HEART) methodology, which is a mathematical model that utilizes machine learning and statistical-based methodologies to aid managers with their hiring decisions. The goal of HEART is to determine expected and theoretical contribution values for a potential candidate, which represents a player’s ability to increase or decrease a team’s forecasted winning percentage. In order to validate the usefulness of the methodology, the results of a 2007 case study were presented to subject matter experts. After analyzing the survey results statistically, five of the eight decision-making categories were found to be “very useful” in terms of the information that the methodology provided.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69212441","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 Driven by the increased availability of position and performance data, automated analyses are becoming the daily routine in many top-level sports. Methods from the domains of data mining and machine learning are more frequently used to generate new insights from massive amounts of data. This study evaluates the performance of four current models (multi-layer perceptron, convolutional network, recurrent network, gradient boosted tree) in classifying tactical behaviors on a beach volleyball dataset consisting of 1,356 top-level games. A three-way between-subjects analysis of variance was conducted to determine the effects of model, input features and target behavior on classification accuracy. Results show significant differences in classification accuracy between models as well as significant interaction effects between factors. Our models achieve classification performance similar to previous work in other sports. Nonetheless, they are not yet at the level to warrant practical application in day to day performance analysis in beach volleyball.
{"title":"Performance of machine learning models in application to beach volleyball data.","authors":"S. Wenninger, D. Link, M. Lames","doi":"10.2478/ijcss-2020-0002","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0002","url":null,"abstract":"Abstract Driven by the increased availability of position and performance data, automated analyses are becoming the daily routine in many top-level sports. Methods from the domains of data mining and machine learning are more frequently used to generate new insights from massive amounts of data. This study evaluates the performance of four current models (multi-layer perceptron, convolutional network, recurrent network, gradient boosted tree) in classifying tactical behaviors on a beach volleyball dataset consisting of 1,356 top-level games. A three-way between-subjects analysis of variance was conducted to determine the effects of model, input features and target behavior on classification accuracy. Results show significant differences in classification accuracy between models as well as significant interaction effects between factors. Our models achieve classification performance similar to previous work in other sports. Nonetheless, they are not yet at the level to warrant practical application in day to day performance analysis in beach volleyball.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44865188","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 Decision making in sport involves forecasting and selecting choices from different options of action, care, or management. These processes are conditioned by the available information (sometimes limited, fallible, or excessive), the cognitive limitations of the decision-maker (heuristics and biases), the finite amount of available time to make the decision, and the levels of risk and reward. Decision support systems have become increasingly common in sporting contexts such as scheduling optimization, skills evaluation and classification, decision-making assessment, talent identification and team selection, or injury risk assessment. However no specific, formalised framework exists to help guide either the development or evaluation of these systems. Drawing on a variety of literature, this paper proposes a decision support system development framework for specific use in high-performance sport. It proposes three separate criteria for this purpose: 1) Context Satisfaction, 2) Output Quality, and 3) Process Efficiency. Underpinning these criteria there are six specific components: Feasibility, Delivered knowledge, Decisional guidance, Data quality, System error, and System complexity. The proposed framework offers a systematic approach for users to ensure that each of the six components are considered and optimised before, during, and after developing the system. A DSS development framework for high-performance sport should help to improve both short and long term decision-making in a variety of sporting contexts.
{"title":"A development framework for decision support systems in high-performance sport","authors":"Xavi Schelling, S. Robertson","doi":"10.2478/ijcss-2020-0001","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0001","url":null,"abstract":"Abstract Decision making in sport involves forecasting and selecting choices from different options of action, care, or management. These processes are conditioned by the available information (sometimes limited, fallible, or excessive), the cognitive limitations of the decision-maker (heuristics and biases), the finite amount of available time to make the decision, and the levels of risk and reward. Decision support systems have become increasingly common in sporting contexts such as scheduling optimization, skills evaluation and classification, decision-making assessment, talent identification and team selection, or injury risk assessment. However no specific, formalised framework exists to help guide either the development or evaluation of these systems. Drawing on a variety of literature, this paper proposes a decision support system development framework for specific use in high-performance sport. It proposes three separate criteria for this purpose: 1) Context Satisfaction, 2) Output Quality, and 3) Process Efficiency. Underpinning these criteria there are six specific components: Feasibility, Delivered knowledge, Decisional guidance, Data quality, System error, and System complexity. The proposed framework offers a systematic approach for users to ensure that each of the six components are considered and optimised before, during, and after developing the system. A DSS development framework for high-performance sport should help to improve both short and long term decision-making in a variety of sporting contexts.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45062012","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 professional sports clubs, the growing number of individual IT-systems increases the need for central information systems. Various solutions from different suppliers lead to a fragmented situation in sports. Therefore, a standardized and independent general concept for a club information systems (CIS) is necessary. Due to the different areas involved, an interdisciplinary approach is required, which can be provided by sports informatics. The purpose of this paper is the development of a general and sports informatics driven concept for a CIS, using methods and models of existing areas, especially business intelligence (BI). Software engineering provides general methods and models. Business intelligence addresses similar problems in industry. Therefore, existing best practice models are examined and adapted for sport. From sports science, especially training systems and information systems in sports are considered. Practical relevance is illustrated by an example of Liverpool FC. Based on these areas, the requirements for a CIS are derived, and an architectural concept with its different components is designed and explained. To better understand the practical challenges, a participatory observation was conducted during years of working in sports clubs. This paper provides a new sports informatics approach to the general design and architecture of a CIS using best practice models from BI. It illustrates the complexity of this interdisciplinary topic and the relevance of a sports informatics approach. This paper is meant as a conceptional starting point and shows the need for further work in this field.
{"title":"A Concept for Club Information Systems (CIS) - An Example for Applied Sports Informatics","authors":"Thomas Blobel, M. Lames","doi":"10.2478/ijcss-2020-0006","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0006","url":null,"abstract":"Abstract In professional sports clubs, the growing number of individual IT-systems increases the need for central information systems. Various solutions from different suppliers lead to a fragmented situation in sports. Therefore, a standardized and independent general concept for a club information systems (CIS) is necessary. Due to the different areas involved, an interdisciplinary approach is required, which can be provided by sports informatics. The purpose of this paper is the development of a general and sports informatics driven concept for a CIS, using methods and models of existing areas, especially business intelligence (BI). Software engineering provides general methods and models. Business intelligence addresses similar problems in industry. Therefore, existing best practice models are examined and adapted for sport. From sports science, especially training systems and information systems in sports are considered. Practical relevance is illustrated by an example of Liverpool FC. Based on these areas, the requirements for a CIS are derived, and an architectural concept with its different components is designed and explained. To better understand the practical challenges, a participatory observation was conducted during years of working in sports clubs. This paper provides a new sports informatics approach to the general design and architecture of a CIS using best practice models from BI. It illustrates the complexity of this interdisciplinary topic and the relevance of a sports informatics approach. This paper is meant as a conceptional starting point and shows the need for further work in this field.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49521264","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}
{"title":"Diachronic analysis application for the detection of soccer performance standards: a case study","authors":"R. M. Dios, M. A. Jiménez, M. Anguera-Argilaga","doi":"10.2478/ijcss-2020-0011","DOIUrl":"https://doi.org/10.2478/ijcss-2020-0011","url":null,"abstract":"","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"69212688","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 As a up and coming sport, powerlifting is gathering more and more attetion. Powerlifters vary in their strength levels and performances at different ages as well as differing in height and weight. Hence the questions arises on how to establish the relationship between age and weight. It is difficult to judge the performance of athletes by artificial expertise, as subjective factors affecting the performance of powerlifters often fail to achieve the desired results. In recent years, artificial intelligence has made groundbreaking strides. Therefore, using artificial intelligence to predict the performance of athletes is among one of many interesting topics in sports competitions. Based on the artificial intelligence algorithm, this research proposes an analysis model of powerlifters’ performance. The results show that the method proposed in this paper can predict the best performance of powerlifters. Coefficient of determination-R2=0.86 and root-mean-square error of prediction-RMSEP=20.98 demonstrate the effectiveness of our method.
{"title":"The effects of age and body weight on powerlifters: An analysis model of powerlifting performance based on machine learning","authors":"Vinh Huy Chau, Anh Thu Vo, Ba Tuan Le","doi":"10.2478/ijcss-2019-0019","DOIUrl":"https://doi.org/10.2478/ijcss-2019-0019","url":null,"abstract":"Abstract As a up and coming sport, powerlifting is gathering more and more attetion. Powerlifters vary in their strength levels and performances at different ages as well as differing in height and weight. Hence the questions arises on how to establish the relationship between age and weight. It is difficult to judge the performance of athletes by artificial expertise, as subjective factors affecting the performance of powerlifters often fail to achieve the desired results. In recent years, artificial intelligence has made groundbreaking strides. Therefore, using artificial intelligence to predict the performance of athletes is among one of many interesting topics in sports competitions. Based on the artificial intelligence algorithm, this research proposes an analysis model of powerlifters’ performance. The results show that the method proposed in this paper can predict the best performance of powerlifters. Coefficient of determination-R2=0.86 and root-mean-square error of prediction-RMSEP=20.98 demonstrate the effectiveness of our method.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44249793","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 Competitive balance is a key concept in sport because it creates an uncertainty on the outcome that leads to increased interest and demand for these events. The Spanish Professional Football League (LaLiga) has been one of the top European leagues in the last decade, and it has given rise to a particular research interest regarding its characteristics and structure. Since season 1995/96, LaLiga changed the number of points given to the winning teams, by awarding three points per victory instead of two. In this paper, we assess the impact of such a change on the competitive balance of LaLiga. Our analysis focuses on teams with varying levels of performance and follows a three-step approach. First, we cluster the teams according to their historical performance using an adjusted measure based on their credible intervals of winning ratios. Second, we calculate Kendall’s tau coefficient (according to our adjusted measure) in order to obtain the overall ranking turnover of teams between consecutive seasons. Third, we assess the causal impact of the adoption of the new scoring system, based on Kendall’s tau coefficients, for each cluster of teams. Our results show that the overall competitive balance decreased after the adoption of the new scoring system. However, the impact was not the same for all teams, being more significant for top teams and less significant for bottom teams. Moreover, our predictions using adjusted ARIMA models indicate that this difference in the competitive balance will persist for future seasons.
{"title":"Assessing the causal impact of the 3-point per victory scoring system in the competitive balance of LaLiga","authors":"César Soto-Valero, M. Pic","doi":"10.2478/ijcss-2019-0018","DOIUrl":"https://doi.org/10.2478/ijcss-2019-0018","url":null,"abstract":"Abstract Competitive balance is a key concept in sport because it creates an uncertainty on the outcome that leads to increased interest and demand for these events. The Spanish Professional Football League (LaLiga) has been one of the top European leagues in the last decade, and it has given rise to a particular research interest regarding its characteristics and structure. Since season 1995/96, LaLiga changed the number of points given to the winning teams, by awarding three points per victory instead of two. In this paper, we assess the impact of such a change on the competitive balance of LaLiga. Our analysis focuses on teams with varying levels of performance and follows a three-step approach. First, we cluster the teams according to their historical performance using an adjusted measure based on their credible intervals of winning ratios. Second, we calculate Kendall’s tau coefficient (according to our adjusted measure) in order to obtain the overall ranking turnover of teams between consecutive seasons. Third, we assess the causal impact of the adoption of the new scoring system, based on Kendall’s tau coefficients, for each cluster of teams. Our results show that the overall competitive balance decreased after the adoption of the new scoring system. However, the impact was not the same for all teams, being more significant for top teams and less significant for bottom teams. Moreover, our predictions using adjusted ARIMA models indicate that this difference in the competitive balance will persist for future seasons.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44665242","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}
S. Jauhiainen, S. Äyrämö, H. Forsman, Jukka-Pekka Kauppi
Abstract Identifying potential future elite athletes is important in many sporting events. The successful identification of potential future elite athletes at an early age would help to provide high-quality coaching and training environments in which to optimize their development. However, a large variety of different skills and qualities are needed to succeed in elite sports, making talent identification generally a complex and multifaceted problem. Due to the rarity of elite athletes, datasets are inherently imbalanced, making classical statistical inference difficult. Therefore, we approach talent identification as an anomaly detection problem. We trained a nonlinear one-class support vector machine (one-class SVM) on a dataset (N=951) collected from 14-year-old junior soccer players to detect potential future elite players. The mean area under the receiver operating characteristic curve (AUC-ROC) over the tested hyperparameter combinations was 0.763 (std 0.007). The most accurate model was obtained when physical tests, measuring, for example, technical skills, speed, and agility, were used. According to our results, the proposed approach could be useful to support decision-makers in the process of talent identification.
{"title":"Talent identification in soccer using a one-class support vector machine","authors":"S. Jauhiainen, S. Äyrämö, H. Forsman, Jukka-Pekka Kauppi","doi":"10.2478/ijcss-2019-0021","DOIUrl":"https://doi.org/10.2478/ijcss-2019-0021","url":null,"abstract":"Abstract Identifying potential future elite athletes is important in many sporting events. The successful identification of potential future elite athletes at an early age would help to provide high-quality coaching and training environments in which to optimize their development. However, a large variety of different skills and qualities are needed to succeed in elite sports, making talent identification generally a complex and multifaceted problem. Due to the rarity of elite athletes, datasets are inherently imbalanced, making classical statistical inference difficult. Therefore, we approach talent identification as an anomaly detection problem. We trained a nonlinear one-class support vector machine (one-class SVM) on a dataset (N=951) collected from 14-year-old junior soccer players to detect potential future elite players. The mean area under the receiver operating characteristic curve (AUC-ROC) over the tested hyperparameter combinations was 0.763 (std 0.007). The most accurate model was obtained when physical tests, measuring, for example, technical skills, speed, and agility, were used. According to our results, the proposed approach could be useful to support decision-makers in the process of talent identification.","PeriodicalId":38466,"journal":{"name":"International Journal of Computer Science in Sport","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48643188","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：