scholarly journals Team Sports for Game AI Benchmarking Revisited

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Maxim Mozgovoy ◽  
Mike Preuss ◽  
Rafael Bidarra

Sport games are among the oldest and best established genres of computer games. Sport-inspired environments, such as RoboCup, have been used for AI benchmarking for years. We argue that, in spite of the rise of increasingly more sophisticated game genres, team sport games will remain an important testbed for AI benchmarking due to two primary factors. First, there are several genre-specific challenges for AI systems that are neither present nor emphasized in other types of games, such as team AI and frequent replanning. Second, there are unmistakable nonskill-related goals of AI systems, contributing to player enjoyment, that are most easily observed and addressed within a context of a team sport, such as showing creative and emotional traits. We analyze these factors in detail and outline promising directions for future research for game AI benchmarking, within a team sport context.

2016 ◽  
Vol 30 (1) ◽  
pp. 55-67 ◽  
Author(s):  
Sebastian Harenberg ◽  
Harold A. Riemer ◽  
Erwin Karreman ◽  
Kim Dorsch

The study explored the competition between teammates for playing time (i.e., positional competition) within university team sports from the athletes’ perspective. Sixteen Canadian interuniversity team sport athletes (11 women, 5 men) participated in semistructured interviews. Results revealed that positional competition (a) occurs between players in the same position, (b) is necessary to determine playing time, (c) is an ongoing, omni-present process, and (d) happens under the awareness of the coach. Furthermore, various inputs (by the individual athlete, team, coach), processes (performance-related, information-related), and outcomes (individual, collective) became apparent. Positional competition is a group process that occurs across multiple competitive situations (e.g., practices, games). Future research is needed to clearly define and operationalize it as its own construct.


2020 ◽  
Author(s):  
Rory Bunker ◽  
Teo Sunsjak

Over the past two decades, Machine Learning (ML) techniques have been increasingly utilized for the purpose of predicting outcomes in sport. In this paper, we provide a review of studies that have used ML for predicting results in team sport, covering studies from 1996 to 2019. We sought to answer five key research questions while extensively surveying papers in this field. This paper offers insights into which ML algorithms have tended to be used in this field, as well as those that are beginning to emerge with successful outcomes. Our research highlights defining characteristics of successful studies and identifies robust strategies for evaluating accuracy results in this application domain. Our study considers accuracies that have been achieved across different sports and explores the notion that outcomes of some team sports could be inherently more difficult to predict than others. Finally, our study uncovers common themes of future research directions across all surveyed papers, looking for gaps and opportunities, while proposing recommendations for future researchers in this domain.


2017 ◽  
Vol 12 (s2) ◽  
pp. S2-27-S2-34 ◽  
Author(s):  
Robin T. Thorpe ◽  
Greg Atkinson ◽  
Barry Drust ◽  
Warren Gregson

The increase in competition demands in elite team sports over recent years has prompted much attention from researchers and practitioners to the monitoring of adaptation and fatigue in athletes. Monitoring fatigue and gaining an understanding of athlete status may also provide insights and beneficial information pertaining to player availability, injury, and illness risk. Traditional methods used to quantify recovery and fatigue in team sports, such as maximal physical-performance assessments, may not be feasible to detect variations in fatigue status throughout competitive periods. Faster, simpler, and nonexhaustive tests such as athlete self-report measures, autonomic nervous system response via heart-rate-derived indices, and to a lesser extent, jump protocols may serve as promising tools to quantify and establish fatigue status in elite team-sport athletes. The robust rationalization and precise detection of a meaningful fluctuation in these measures are of paramount importance for practitioners working alongside athletes and coaches on a daily basis. There are various methods for arriving at a minimal clinically important difference, but these have been rarely adopted by sport scientists and practitioners. The implementation of appropriate, reliable, and sensitive measures of fatigue can provide important information to key stakeholders in team-sport environments. Future research is required to investigate the sensitivity of these tools to fundamental indicators such as performance, injury, and illness.


1984 ◽  
Vol 1 (3) ◽  
pp. 263-279 ◽  
Author(s):  
Klaus V. Meier

Television is the most immediate and compelling medium for sports coverage. Consequently, the sports presentations that it delivers, particularly championship series, attract a vast and devoted audience. This study provided a detailed, descriptive content analysis of the television broadcast packaging of the 1982-83 championship games, both professional and university, of the four most popular North American team sports—baseball, football, hockey, and basketball. Videotape recordings of the entire broadcast packages centered upon these games were analyzed. The program content was divided into four specific and distinct components: advertisements, pre- and postgame programs, between-play time, and live-play time. The ensuing discussion addressed the basic structure of each broadcast package, the absolute and relative data for each of the four components of the various games and, finally, the intriguing relationship between the derived data (particularly the live-play time component) and concomitant levels of viewer ratings. Concluding comments reflected on the significance of the findings and also provided considerations for future research based upon materials presented within the study.


2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Robert I. M. Delves ◽  
Robert J. Aughey ◽  
Kevin Ball ◽  
Grant M. Duthie

Abstract Background Wearable tracking devices are commonly utilised to quantify the external acceleration load of team sport athletes during training and competition. The ability to accelerate is an important attribute for athletes in many team sports. However, there are many different acceleration metrics that exist in team sport research. This review aimed to provide researchers and practitioners with a clear reporting framework on acceleration variables by outlining the different metrics and calculation processes that have been adopted to quantify acceleration loads in team sport research. Methods A systematic review of three electronic databases (CINAHL, MEDLINE, SPORTDiscus), was performed to identify peer-reviewed studies that published external acceleration load in elite team sports during training and/or competition. Articles published between January 2010 and April 2020 were identified using Boolean search phrases in relation to team sports (population), acceleration/deceleration (comparators), and competition and/or training (outcome). The included studies were required to present external acceleration and/or deceleration load (of any magnitude) from able-bodied athletes (mean age ≥ 18 years) via wearable technologies. Results A total of 124 research articles qualified for inclusion. In total, 113/124 studies utilised GPS/GNSS technology to outline the external acceleration load of athletes. Count-based metrics of acceleration were predominant of all metrics in this review (72%). There was a lack of information surrounding the calculation process of acceleration with 13% of studies specifying the filter used in the processing of athlete data, whilst 32% outlined the minimum effort duration (MED). Markers of GPS/GNSS data quality, including horizontal dilution of precision (HDOP) and the average number of satellites connected, were outlined in 24% and 27% of studies respectively. Conclusions Team sport research has predominantly quantified external acceleration load in training and competition with count-based metrics. Despite the influence of data filtering processes and MEDs upon acceleration, this information is largely omitted from team sport research. Future research that outlines acceleration load should present filtering processes, MEDs, HDOP, and the number of connected satellites. For GPS/GNSS systems, satellite planning tools should document evidence of available satellites for data collection to analyse tracking device performance. The development of a consistent acceleration filtering method should be established to promote consistency in the research of external athlete acceleration loads.


Nutrients ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 1235
Author(s):  
Michèle Renard ◽  
David T. Kelly ◽  
Niamh Ní Chéilleachair ◽  
Ciarán Ó Catháin

Field-based team sports present large energetic demands given their intermittent high-intensity nature. Current evidence suggests that the dietary intake of female athletes may be insufficient to meet such demands, resulting in negative consequences for athletic performance and health. The primary aim of this review was to therefore assess the adequacy of dietary intake of female field-based team sport athletes when compared to dietary recommendations. A systematic search of databases, including PubMed, Web of Science, SPORTDiscus, and OpenGrey, was performed from the earliest record available until July 2020, obtaining an initial total of 2588 articles. To be included within the final review, articles were required to provide a quantitative assessment of baseline dietary intake specific to the target population. A total of 20 studies (n = 462) met the full eligibility criteria. A majority reported that the dietary intake of female field-based team sport athletes was insufficient in overall energy (2064 ± 309 kcal·day−1), carbohydrate (4.3 ± 1.2 g·kg·day−1), and iron intake (13.6 ± 6.2 mg·day−1) when compared to recommendations. Future research is required to establish why female team sport athletes consistently demonstrate deficient dietary practices, and to explore the potential negative consequences of this.


Author(s):  
Yuval Paldi ◽  
Daniel S. Moran ◽  
Orna Baron-Epel ◽  
Shiran Bord ◽  
Riki Tesler

The Israeli Mamanet Cachibol League (MCL) serves as a community model that incorporates physical activity and amateur team sports among women. Team sports have been shown to bridge gaps and build positive relationships between communities. There is a paucity of data regarding the advantages of team sports to promote the health and well-being of women from different ethnic backgrounds. The purpose of this study was to examine the association of participation in MCL with social capital, health, and well-being across two ethnic groups: Jewish and Arab women. A cross-sectional survey was conducted among women aged 25–64: 102 Jewish and 96 Arab MCL participants, and 102 Jewish and 81 Arab non-MCL participants. Data regarding social capital (trust, social support and social involvement) and well-being (self-reported health and psychosomatic and depressive symptoms) were analyzed using two-way analyses of covariance and multiple regression models with sequential entry of the variables. MCL participants from both ethnic groups reported higher social capital (p < 0.001), better self-reported health (p < 0.001), and lower psychosomatic symptoms (p < 0.001) compared to non-participants. Jewish MCL participants reported lower depressive symptoms (p < 0.001) than non-participants, however no difference was found between Arab MCL participants and non-participants (p < 0.160). Amateur team sports such as MCL are related with higher levels of well-being and social capital. Future research should focus on longitudinal studies that examine the change in social capital and well-being over time.


Sports ◽  
2018 ◽  
Vol 6 (4) ◽  
pp. 174 ◽  
Author(s):  
Thomas Dos’Santos Christopher Thomas ◽  
Paul Comfort ◽  
Paul A. Jones

The purpose of this study was twofold: (1) to examine differences in change of direction (COD) performance and asymmetries between team-sports while considering the effects of sex and sport; (2) to evaluate the relationship between linear speed, COD completion time, and COD deficit. A total of 115 (56 males, 59 females) athletes active in cricket, soccer, netball, and basketball performed the 505 for both left and right limbs and a 10-m sprint test. All team-sports displayed directional dominance (i.e., faster turning performance/shorter COD deficits towards a direction) (p ≤ 0.001, g = −0.62 to −0.96, −11.0% to −28.4%) with, male cricketers tending to demonstrate the greatest COD deficit asymmetries between directions compared to other team-sports (28.4 ± 26.5%, g = 0.19–0.85), while female netballers displayed the lowest asymmetries (11.0 ± 10.1%, g = 0.14–0.86). Differences in sprint and COD performance were observed between sexes and sports, with males demonstrating faster 10-m sprint times, and 505 times compared to females of the same sport. Male soccer and male cricketers displayed shorter COD deficits compared to females of the same sport; however, female court athletes demonstrated shorter COD deficits compared to male court athletes. Large significant associations (ρ = 0.631–0.643, p < 0.001) between 505 time and COD deficit were revealed, while trivial, non-significant associations (ρ ≤ −0.094, p ≥ 0.320) between COD deficit and 10-m sprint times were observed. In conclusion, male and female team-sport athletes display significant asymmetries and directional dominance during a high approach velocity 180° turning task. Coaches and practitioners are advised to apply the COD deficit for a more isolated measure of COD ability (i.e., not biased towards athletes with superior acceleration and linear speed) and perform COD speed assessments from both directions to establish directional dominance and create a COD symmetry profile.


2021 ◽  
Vol 6 (2) ◽  
pp. 304-309
Author(s):  
Manzoor Ahmad Bhat

The study aimed to compare the Body Composition in Various Age Groups among Individual and Team Sport. A total of one hundred twenty (120) subjects, comprising 60 Individual and 60 Team sport of district Kulgam J&K, further out of 60 individual sports players 20 players were of the age group between 20-25, ( 20 ) players were of the age group between 25- 30 and 20 players were of the age group between 30-35. the same procedure was followed for 60 team sports players. The Subjects were selected by using purposive sampling. The age of the subjects ranged between 20-25, the second group 25-30, and the third group 30-35. To analyze and compare the Body Composition and fat percentage in three different age groups among individual sports and team sports, the Following equipment and test were used: the data related to Fat Percentage was measured by Skinfold Calipers. BMI: it was estimated by Stadiometer and weighing machine. ).the data that was collected after applying standard testing kits were written in separate columns and was cross-checked for all three different age groups. Individual and team sports of district kulgam. Then the analysis of data was carried out by applying various statistical techniques like average., standard deviation and through the application of formula of t-test to find out the significant difference of all selected physical variables I,e BMI and fat percentage in various age groups among individual and team sports players of kulgam district the level of significance as per norm was kept as (p<0.05). the mean and standard deviation of BMI in 20-25 age group individual game players is ( 22.02 ±2.20) respectively, and the mean and standard deviation of BMI in 20-25 age group of team sports players is (18.01 ±1.81), with an average difference of 4.01. ). Hence individual sports players were found with a higher BMI than team sports players under the 20-25 age group. BMI in the 25-30 age group individual game players is (23.09±1.76) respectively, and the mean and standard deviation of BMI in 25-30 age group of team sports players is (20.07±3.36), with an average difference of 3.02. ). Hence under this age group, the individual sports players were found with a higher BMI than team sports groups. The mean and standard deviation of BMI in 30-35 age group individual game players is (19.30±2.07) respectively, and the mean and standard deviation of BMI in 30-35 age group of team sports players is (22.17 ±3.47), with an average difference of 2.87. Hence, team sports players were found with a higher BMI under the age group than individual sports players. The mean and standard deviation of fat percentage in 20-25 age group individual game players is (11.09±4.83) respectively, and the mean and standard deviation of fat percentage in 20-25 age group of team sports players is (9.02±4.18), with an average difference of 2.17.).Hence under this age group, individual sports players were found fatty as compared to team sports players. The mean and standard deviation of fat percentage in 25-30 age group individual game players is (10.01±3.53) respectively, and the mean and standard deviation of BMI in 25-30 age group of team sports players is (14.04±7.48), with an average difference of 4.13. ). Hence under this age group, team sports players were found fatty as compared to individual sports players. The mean and standard deviation of BMI in 30-35 age group individual game players is (14.08±2.81) respectively, and the mean and standard deviation of fat percentage in 30-35 age group of team sports players is (18.01±5.64), with an average difference of 3.64. Hence under this age group, team sports players were found fatty as compared to individual sports players


2021 ◽  
Vol 79 (1) ◽  
pp. 15-27
Author(s):  
Jordi Arboix-Alió ◽  
Chris Bishop ◽  
Ariadna Benet ◽  
Bernat Buscà ◽  
Joan Aguilera-Castells ◽  
...  

Abstract The direction of inter-limb asymmetries and the change of direction (COD) deficit are two aspects that have increased in recent years. The main objective of the present study was to assess the magnitude of neuromuscular asymmetries in an elite youth female team-sports sample and determine its directionality. Secondary objectives were to evaluate the relationship between COD deficit, linear speed and COD time performance. Elite female youth basketball and handball players (n = 33, age = 16 ± 1.17 y) performed the Single Leg Countermovement Jump in vertical (SLCJ-V), horizontal (SLCJ-H), and lateral (SLCJ-L) directions, the COD and the 10-m sprint. Results showed statistical differences between limbs in all the neuromuscular tests (p < 0.001). The Kappa coefficient showed poor to fair levels of agreement between tasks (K range = -0.087 to 0.233), indicating that asymmetries rarely favoured the same limb between skills. Additionally, small and non-significant correlations were found between the linear sprint capacity and the COD ability. The findings of the present study highlight the independent directionality of asymmetries across tests. The COD deficit does not appear to be much more advantageous than COD total time to measure asymmetry. Practitioners are encouraged to use a fitness testing battery to detect existing side differences and each ability should be specifically trained with functional tasks.


Sign in / Sign up

Export Citation Format

Share Document