Applied Sciences

Editorial

Jump to: Research, Review

2 pages, 159 KiB

Open AccessEditorial

Computational Intelligence and Data Mining in Sports

by Iztok Fister and Iztok Fister, Jr.

Appl. Sci. 2021, 11(6), 2637; https://doi.org/10.3390/app11062637 - 16 Mar 2021

Cited by 1 | Viewed by 1521

Abstract

Sport can be viewed from two standpoints: professional and recreational [...] Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

Research

Jump to: Editorial, Review

24 pages, 987 KiB

Open AccessArticle

Classification of Similar Sports Images Using Convolutional Neural Network with Hyper-Parameter Optimization

by Vili Podgorelec, Špela Pečnik and Grega Vrbančič

Appl. Sci. 2020, 10(23), 8494; https://doi.org/10.3390/app10238494 - 27 Nov 2020

Cited by 17 | Viewed by 3852

Abstract

With the exponential growth of the presence of sport in the media, the need for effective classification of sports images has become crucial. The traditional approaches require carefully hand-crafted features, which make them impractical for massive-scale data and less accurate in distinguishing images [...] Read more.

With the exponential growth of the presence of sport in the media, the need for effective classification of sports images has become crucial. The traditional approaches require carefully hand-crafted features, which make them impractical for massive-scale data and less accurate in distinguishing images that are very similar in appearance. As the deep learning methods can automatically extract deep representation of training data and have achieved impressive performance in image classification, our goal was to apply them to automatic classification of very similar sports disciplines. For this purpose, we developed a CNN-TL-DE method for image classification using the fine-tuning of transfer learning for training a convolutional neural network model with the use of hyper-parameter optimization based on differential evolution. Through the automatic optimization of neural network topology and essential training parameters, we significantly improved the classification performance evaluated on a dataset composed from images of four similar sports—American football, rugby, soccer, and field hockey. The analysis of interpretable representation of the trained model additionally revealed interesting insights into how our model perceives images which contributed to a greater confidence in the model prediction. The performed experiments showed our proposed method to be a very competitive image classification method for distinguishing very similar sports and sport situations. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

22 pages, 331 KiB

Open AccessArticle

Offensive and Defensive Plus–Minus Player Ratings for Soccer

by Lars Magnus Hvattum

Appl. Sci. 2020, 10(20), 7345; https://doi.org/10.3390/app10207345 - 20 Oct 2020

Cited by 4 | Viewed by 3125

Abstract

Rating systems play an important part in professional sports, for example, as a source of entertainment for fans, by influencing decisions regarding tournament seedings, by acting as qualification criteria, or as decision support for bookmakers and gamblers. Creating good ratings at a team [...] Read more.

Rating systems play an important part in professional sports, for example, as a source of entertainment for fans, by influencing decisions regarding tournament seedings, by acting as qualification criteria, or as decision support for bookmakers and gamblers. Creating good ratings at a team level is challenging, but even more so is the task of creating ratings for individual players of a team. This paper considers a plus–minus rating for individual players in soccer, where a mathematical model is used to distribute credit for the performance of a team as a whole onto the individual players appearing for the team. The main aim of the work is to examine whether the individual ratings obtained can be split into offensive and defensive contributions, thereby addressing the lack of defensive metrics for soccer players. As a result, insights are gained into how elements such as the effect of player age, the effect of player dismissals, and the home field advantage can be broken down into offensive and defensive consequences. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

9 pages, 1507 KiB

Open AccessArticle

The Performance Evolution of Match Play Styles in the Spanish Professional Basketball League

by Miguel-Ángel Gómez, Ramón Medina, Anthony S. Leicht, Shaoliang Zhang and Alejandro Vaquera

Appl. Sci. 2020, 10(20), 7056; https://doi.org/10.3390/app10207056 - 11 Oct 2020

Cited by 4 | Viewed by 2119

Abstract

The aim of this study is to analyse the performance evolution of all, and the dominant, team’s performances throughout an eight-season period within the Spanish professional basketball league. Match-related statistics were gathered from all regular season matches (n = 2426) played during the [...] Read more.

The aim of this study is to analyse the performance evolution of all, and the dominant, team’s performances throughout an eight-season period within the Spanish professional basketball league. Match-related statistics were gathered from all regular season matches (n = 2426) played during the period 2009–2010 to 2016–2017. The non-metric multidimensional scaling model was used to examine the team’s profiles across seasons and for the most successful (playoff) teams. The main results showed that: 3-point field goals made (effect size, d = 0.61; 90% confidence interval, CI = 0.23; 1.37) and missed (d = 0.72; 90% CI = 0.35; 1.46), and assists (d = 1.27; 90% CI = 0.82; 1.86) presented a positive trend with an increased number of actions across the seasons; 2-point field goals made (d = 0.21; 90% CI = −1.25; 2.02) and missed (d = 0.27; 90% CI = −0.52; 0.92) were decreased; free throws made and missed, rebounds, fouls, blocks, steals and turnovers showed a relatively stable performance. The matrix solution (stress = 0.22, rmse (root mean squared error) = 7.9 × 10⁴, maximum residual = 5.8 × 10³) indicated minimal season-to-season evolution with the ordination plot and convex hulls overlapping. The two most dominant teams exhibited unique match patterns with the most successful team’s pattern, a potential benchmark for others who exhibited more dynamic evolutions (and less success). The current findings identified the different performances of teams within the Spanish professional basketball league over eight seasons with further statistical modelling of match play performances useful to identify temporal trends and support coaches with training and competition preparations. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

14 pages, 602 KiB

Open AccessArticle

The Effect of Weather in Soccer Results: An Approach Using Machine Learning Techniques

by Ditsuhi Iskandaryan, Francisco Ramos, Denny Asarias Palinggi and Sergio Trilles

Appl. Sci. 2020, 10(19), 6750; https://doi.org/10.3390/app10196750 - 26 Sep 2020

Cited by 4 | Viewed by 3861

Abstract

The growing popularity of soccer has led to the prediction of match results becoming of interest to the research community. The aim of this research is to detect the effects of weather on the result of matches by implementing Random Forest, Support Vector [...] Read more.

The growing popularity of soccer has led to the prediction of match results becoming of interest to the research community. The aim of this research is to detect the effects of weather on the result of matches by implementing Random Forest, Support Vector Machine, K-Nearest Neighbors Algorithm, and Extremely Randomized Trees Classifier. The analysis was executed using the Spanish La Liga and Segunda division from the seasons 2013–2014 to 2017–2018 in combination with weather data. Two tasks were proposed as part of this study: the first was to find out whether the game will end in a draw, a win by the hosts or a victory by the guests, and the second was to determine whether the match will end in a draw or if one of the teams will win. The results show that, for the first task, Extremely Randomized Trees Classifier is a better method, with an accuracy of 65.9%, and, for the second task, Support Vector Machine yielded better results with an accuracy of 79.3%. Moreover, it is possible to predict whether the game will end in a draw or not with 0.85 AUC-ROC. Additionally, for comparative purposes, the analysis was also performed without weather data. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

10 pages, 988 KiB

Open AccessArticle

Learning to Rank Sports Teams on a Graph

by Jian Shi and Xin-Yu Tian

Appl. Sci. 2020, 10(17), 5833; https://doi.org/10.3390/app10175833 - 23 Aug 2020

Cited by 7 | Viewed by 3313

Abstract

To improve the prediction ability of ranking models in sports, a generalized PageRank model is introduced. In the model, a game graph is constructed from the perspective of Bayesian correction with game results. In the graph, nodes represent teams, and a link function [...] Read more.

To improve the prediction ability of ranking models in sports, a generalized PageRank model is introduced. In the model, a game graph is constructed from the perspective of Bayesian correction with game results. In the graph, nodes represent teams, and a link function is used to synthesize the information of each game to calculate the weight on the graph’s edge. The parameters of the model are estimated by minimizing the loss function, which measures the gap between the predicted rank obtained by the model and the actual rank. The application to the National Basketball Association (NBA) data shows that the proposed model can achieve better prediction performance than the existing ranking models. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

13 pages, 1487 KiB

Open AccessArticle

Analyse Success Model of Split Time and Cut-Off Point Values of Physical Demands to Keep Category in Semi-Professional Football Players

by Jesus Vicente Gimenez, Luis Jimenez-Linares, Jorge Garcia-Unanue, Javier Sanchez-Sanchez, Leonor Gallardo and Jose Luis Felipe

Appl. Sci. 2020, 10(15), 5299; https://doi.org/10.3390/app10155299 - 31 Jul 2020

Cited by 3 | Viewed by 2275

Abstract

The aim of this study was to analyse different success models and split time on cut-off point values on physical demands to keep category in semi-professional football players. An ad hoc observational controlled study was carried out with a total of ten (840 [...] Read more.

The aim of this study was to analyse different success models and split time on cut-off point values on physical demands to keep category in semi-professional football players. An ad hoc observational controlled study was carried out with a total of ten (840 match data) outfield main players (25.2 ± 6.3 years, 1.79 ± 0.75 m, 74.9 ± 5.8 kg and 16.5 ± 6 years of football experience) and monitored using 15 Hz GPS devices. During 14 official matches from the Spanish division B in the 2016/2017 season, match data were coded considering the situational variable (score) and classified by match results (winning, losing or drawing). The results show significant differences between high-intensity attributes criteria that considered split time in velocity zones of 0–15 min (p = 0.043, ηp² = 0.065, medium), 30–45 min (p = 0.010, ηp² = 0.094, medium) and 60–75 min (p = 0.015, ηp² = 0.086, medium), as well as sprint 60–75 min (p = 0.042, ηp² = 0.066, medium) and 75–90 min (p = 0.002, ηp² = 0.129, medium). Decision tree induction was applied to reduce the disparity range of data according to six 15-min intervals and to determine the cut-off point values for every parameter combination. It was possible to establish multivariate models for the main high-intensity actions criteria, allowing the establishment of all rules with their attributes and enabling the detection and visualisation of relationships and the pattern sets of variables for determining success. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

20 pages, 678 KiB

Open AccessArticle

Combining Internal- and External-Training-Loads to Predict Non-Contact Injuries in Soccer

by Emmanuel Vallance, Nicolas Sutton-Charani, Abdelhak Imoussaten, Jacky Montmain and Stéphane Perrey

Appl. Sci. 2020, 10(15), 5261; https://doi.org/10.3390/app10155261 - 30 Jul 2020

Cited by 32 | Viewed by 5602

Abstract

The large amount of features recorded from GPS and inertial sensors (external load) and well-being questionnaires (internal load) can be used together in a multi-dimensional non-linear machine learning based model for a better prediction of non-contact injuries. In this study we put forward [...] Read more.

The large amount of features recorded from GPS and inertial sensors (external load) and well-being questionnaires (internal load) can be used together in a multi-dimensional non-linear machine learning based model for a better prediction of non-contact injuries. In this study we put forward the main hypothesis that the use of such models would be able to inform better about injury risks by considering the evolution of both internal and external loads over two horizons (one week and one month). Predictive models were trained with data collected by both GPS and subjective questionnaires and injury data from 40 elite male soccer players over one season. Various classification machine-learning algorithms that performed best on external and internal loads features were compared using standard performance metrics such as accuracy, precision, recall and the area under the receiver operator characteristic curve. In particular, tree-based algorithms based on non-linear models with an important interpretation aspect were privileged as they can help to understand internal and external load features impact on injury risk. For 1-week injury prediction, internal load features data were more accurate than external load features while for 1-month injury prediction, the best performances of classifiers were reached by combining internal and external load features. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

18 pages, 2402 KiB

Open AccessArticle

Using Machine Learning and Candlestick Patterns to Predict the Outcomes of American Football Games

by Yu-Chia Hsu

Appl. Sci. 2020, 10(13), 4484; https://doi.org/10.3390/app10134484 - 29 Jun 2020

Cited by 6 | Viewed by 10301

Abstract

Match outcome prediction is a challenging problem that has led to the recent rise in machine learning being adopted and receiving significant interest from researchers in data science and sports. This study explores predictability in match outcomes using machine learning and candlestick charts, [...] Read more.

Match outcome prediction is a challenging problem that has led to the recent rise in machine learning being adopted and receiving significant interest from researchers in data science and sports. This study explores predictability in match outcomes using machine learning and candlestick charts, which have been used for stock market technical analysis. We compile candlestick charts based on betting market data and consider the character of the candlestick charts as features in our predictive model rather than the performance indicators used in the technical and tactical analysis in most studies. The predictions are investigated as two types of problems, namely, the classification of wins and losses and the regression of the winning/losing margin. Both are examined using various methods of machine learning, such as ensemble learning, support vector machines and neural networks. The effectiveness of our proposed approach is evaluated with a dataset of 13261 instances over 32 seasons in the National Football League. The results reveal that the random subspace method for regression achieves the best accuracy rate of 68.4%. The candlestick charts of betting market data can enable promising results of match outcome prediction based on pattern recognition by machine learning, without limitations regarding the specific knowledge required for various kinds of sports. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

18 pages, 839 KiB

Open AccessArticle

A Bayesian In-Play Prediction Model for Association Football Outcomes

by Qingrong Zou, Kai Song and Jian Shi

Appl. Sci. 2020, 10(8), 2904; https://doi.org/10.3390/app10082904 - 22 Apr 2020

Cited by 6 | Viewed by 5311

Abstract

Point process models have made a significant contribution to the prediction of football association outcomes. It is conventionally the case that defence and attack capabilities have been assumed to be constant during a match and estimated against the average performance of all other [...] Read more.

Point process models have made a significant contribution to the prediction of football association outcomes. It is conventionally the case that defence and attack capabilities have been assumed to be constant during a match and estimated against the average performance of all other teams in history. Drawing upon a Bayesian method, this paper proposes a dynamic strength model which relaxes assumption of the constant teams’ strengths and permits applying in-match performance information to calibrate them. An empirical study demonstrates that although the Bayesian model fails to achieve improvement in goal difference prediction, it registers clear achievements with regard to the prediction of the total number of goals and Win/Draw/Loss outcome prediction. When the Bayesian model bets against the SBOBet bookmaker, one of the most popular gaming companies among Asian handicaps fans, whose odds data were obtained from both the Win/Draw/Loss market and over–under market, it may obtain positive returns; this clearly contrasts with the process model with constant strengths, which fails to win money from the bookmaker. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

24 pages, 3949 KiB

Open AccessArticle

Design and Validation of Rule-Based Expert System by Using Kinect V2 for Real-Time Athlete Support

by Serkan Örücü and Murat Selek

Appl. Sci. 2020, 10(2), 611; https://doi.org/10.3390/app10020611 - 15 Jan 2020

Cited by 18 | Viewed by 4788

Abstract

In sports and rehabilitation processes where isotonic movements such as bodybuilding are performed, it is vital for individuals to be able to correct the wrong movements instantly by monitoring the trainings simultaneously, and to be able to train healthily and away from the [...] Read more.

In sports and rehabilitation processes where isotonic movements such as bodybuilding are performed, it is vital for individuals to be able to correct the wrong movements instantly by monitoring the trainings simultaneously, and to be able to train healthily and away from the risks of injury. For this purpose, we designed a new real-time athlete support system using Kinect V2 and Expert System. Lateral raise (LR) and dumbbell shoulder press (DSP) movements were selected as examples to be modeled in the system. Kinect V2 was used to obtain angle and distance changes in the shoulder, elbow, wrist, hip, knee, and ankle during movements in these movement models designed. For the rule base of Expert System developed according to these models, a 2⁸-state rule table was designed, and 12 main rules were determined that could be used for both actions. In the sample trainings, it was observed that the decisions made by the system had 89% accuracy in DSP training and 82% accuracy in LR training. In addition, the developed system has been tested by 10 participants (25.8 ± 5.47 years; 74.69 ± 14.81 kg; 173.5 ± 9.52 cm) in DSP and LR training for four weeks. At the end of this period and according to the results of paired t-test analysis (p < 0.05) starting from the first week, it was observed that the participants trained more accurately and that they enhanced their motions by 58.08 ± 11.32% in LR training and 54.84 ± 12.72% in DSP training. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

17 pages, 2300 KiB

Open AccessCommunication

Use of Machine Learning to Automate the Identification of Basketball Strategies Using Whole Team Player Tracking Data

by Changjia Tian, Varuna De Silva, Michael Caine and Steve Swanson

Appl. Sci. 2020, 10(1), 24; https://doi.org/10.3390/app10010024 - 18 Dec 2019

Cited by 38 | Viewed by 9670

Abstract

The use of machine learning to identify and classify offensive and defensive strategies in team sports through spatio-temporal tracking data has received significant interest recently in the literature and the global sport industry. This paper focuses on data-driven defensive strategy learning in basketball. [...] Read more.

The use of machine learning to identify and classify offensive and defensive strategies in team sports through spatio-temporal tracking data has received significant interest recently in the literature and the global sport industry. This paper focuses on data-driven defensive strategy learning in basketball. Most research to date on basketball strategy learning has focused on offensive effectiveness and is based on the interaction between the on-ball player and principle on-ball defender, thereby ignoring the contribution of the remaining players. Furthermore, most sports analytical systems that provide play-by-play data is heavily biased towards offensive metrics such as passes, dribbles, and shots. The aim of the current study was to use machine learning to classify the different defensive strategies basketball players adopt when deviating from their initial defensive action. An analytical model was developed to recognise the one-on-one (matched) relationships of the players, which is utilised to automatically identify any change of defensive strategy. A classification model is developed based on a player and ball tracking dataset from National Basketball Association (NBA) game play to classify the adopted defensive strategy against pick-and-roll play. The methodology described is the first to analyse the defensive strategy of all in-game players (both on-ball players and off-ball players). The cross-validation results indicate that the proposed technique for automatic defensive strategy identification can achieve up to 69% accuracy of classification. Machine learning techniques, such as the one adopted here, have the potential to enable a deeper understanding of player decision making and defensive game strategies in basketball and other sports, by leveraging the player and ball tracking data. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

11 pages, 1384 KiB

Open AccessArticle

Relationship between External and Internal Workloads in Elite Soccer Players: Comparison between Rate of Perceived Exertion and Training Load

by Alessio Rossi, Enrico Perri, Luca Pappalardo, Paolo Cintia and F. Marcello Iaia

Appl. Sci. 2019, 9(23), 5174; https://doi.org/10.3390/app9235174 - 28 Nov 2019

Cited by 24 | Viewed by 5132

Abstract

The use of machine learning (ML) in soccer allows for the management of a large amount of data deriving from the monitoring of sessions and matches. Although the rate of perceived exertion (RPE), training load (S-RPE), and global position system (GPS) are standard [...] Read more.

The use of machine learning (ML) in soccer allows for the management of a large amount of data deriving from the monitoring of sessions and matches. Although the rate of perceived exertion (RPE), training load (S-RPE), and global position system (GPS) are standard methodologies used in team sports to assess the internal and external workload; how the external workload affects RPE and S-RPE remains still unclear. This study explores the relationship between both RPE and S-RPE and the training workload through ML. Data were recorded from 22 elite soccer players, in 160 training sessions and 35 matches during the 2015/2016 season, by using GPS tracking technology. A feature selection process was applied to understand which workload features influence RPE and S-RPE the most. Our results show that the training workloads performed in the previous week have a strong effect on perceived exertion and training load. On the other hand, the analysis of our predictions shows higher accuracy for medium RPE and S-RPE values compared with the extremes. These results provide further evidence of the usefulness of ML as a support to athletic trainers and coaches in understanding the relationship between training load and individual-response in team sports. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research

31 pages, 579 KiB

Open AccessFeature PaperReview

A Systematic Literature Review of Intelligent Data Analysis Methods for Smart Sport Training

by Alen Rajšp and Iztok Fister, Jr.

Appl. Sci. 2020, 10(9), 3013; https://doi.org/10.3390/app10093013 - 26 Apr 2020

Cited by 70 | Viewed by 13790

Abstract

The rapid transformation of our communities and our way of life due to modern technologies has impacted sports as well. Artificial intelligence, computational intelligence, data mining, the Internet of Things (IoT), and machine learning have had a profound effect on the way we [...] Read more.

The rapid transformation of our communities and our way of life due to modern technologies has impacted sports as well. Artificial intelligence, computational intelligence, data mining, the Internet of Things (IoT), and machine learning have had a profound effect on the way we do things. These technologies have brought changes to the way we watch, play, compete, and also train sports. What was once simply training is now a combination of smart IoT sensors, cameras, algorithms, and systems just to achieve a new peak: The optimum one. This paper provides a systematic literature review of smart sport training, presenting 109 identified studies. Intelligent data analysis methods are presented, which are currently used in the field of Smart Sport Training (SST). Sport domains in which SST is already used are presented, and phases of training are identified, together with the maturity of SST methods. Finally, future directions of research are proposed in the emerging field of SST. Full article

(This article belongs to the Special Issue Computational Intelligence and Data Mining in Sports)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Computational Intelligence and Data Mining in Sports

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (14 papers)

Editorial

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI