Background The application of artificial intelligence (AI) opens an interesting perspective for predicting injury risk and performance in team sports. A better understanding of the techniques of AI employed and of the sports that are using AI is clearly warranted. The purpose of this study is to identify which AI approaches have been applied to investigate sport performance and injury risk and to find out which AI techniques each sport has been using. Methods Systematic searches through the PubMed, Scopus, and Web of Science online databases were conducted for articles reporting AI techniques or methods applied to team sports athletes. Results Fifty-eight studies were included in the review with 11 AI techniques or methods being applied in 12 team sports. Pooled sample consisted of 6456 participants (97% male, 25 ± 8 years old; 3% female, 21 ± 10 years old) with 76% of them being professional athletes. The AI techniques or methods most frequently used were artificial neural networks, decision tree classifier, support vector machine, and Markov process with good performance metrics for all of them. Soccer, basketball, handball, and volleyball were the team sports with more applications of AI. Conclusions The results of this review suggest a prevalent application of AI methods in team sports based on the number of published studies. The current state of development in the area proposes a promising future with regard to AI use in team sports. Further evaluation research based on prospective methods is warranted to establish the predictive performance of specific AI techniques and methods. Electronic supplementary material The online version of this article (10.1186/s40798-019-0202-3) contains supplementary material, which is available to authorized users.
Knowledge of the possible impacts of climate change on biodiversity in the tropics is especially scarce. We used maximum entropy modeling of species distributions to predict the ranges of endemic and threatened Atlantic Forest birds under a "business as usual" emissions scenario for 2050. Of the 51 species with reliable models, 44 were predicted to lose distribution area, with future ranges averaging 45% of their original size. Range contraction would bring two species to IUCN's threshold for threat under the Extent of Occurrence criterion. We also predict that the size of the regions that currently have the maximum number of endemic and threatened birds would be greatly reduced. Several such regions are currently highly deforested, which might reinforce the future threat to biodiversity.
BackgroundA key strategy in biodiversity conservation is the establishment of protected areas. In the future, however, the redistribution of species in response to ongoing climate change is likely to affect species’ representativeness in those areas. Here we quantify the effectiveness of planning protected areas network to represent 151 birds endemic to the Brazilian Atlantic Forest hotspot, under current and future climate change conditions for 2050.MethodsWe combined environmental niche modeling and systematic conservation planning using both a county and a regional level planning strategy. We recognized the conflict between biodiversity conservation and economic development, including socio-economic targets (as opposed to biological only) and using planning units that are meaningful for policy-makers.ResultsWe estimated an average contraction of 29,500 km2 in environmentally suitable areas for birds, representing 52% of currently suitable areas. Still, the most cost-effective solution represented almost all target species, requiring only ca. 10% of the Atlantic Forest counties to achieve that representativeness, independent of strategy. More than 50% of these counties were selected both in the current and future planned networks, representing >83% of the species.DiscussionOur results indicate that: (i) planning protected areas network currently can be useful to represent species under climate change; (ii) the overlapped planning units in the best solution for both current and future conditions can be considered as “no regret” areas; (iii) priority counties are spread throughout the biome, providing specific guidance wherever the possibility of creating protected area arises; and (iv) decisions can occur at different administrative spheres (Federal, State or County) as we found quite similar numerical solutions using either county or regional level strategies.
"In Brazil, Capoeira is present in the country's history, culture, education and in the schooling process. Today, it is part of the national heritage, integrates the formal Physical Education curriculum of the public network of the State of São Paulo (CEF-SP), of private schools, is an extracurricular activity in several schools and is present at the university as a content of Physical Education courses. School Physical Education was conceived in the treatment of culture related to bodily aspects that manifest themselves in different ways: games and games, gymnastics, dances, sports and fights. In this way, Capoeira was listed as the content of Physical Education classes, acquiring new pedagogical contours and methodological treatments. Thus, this proposal aims to work strategies for dealing with different contents that make up the universe of Capoeira as a content of school Physical Education. In the didactic part, strategies, methods and styles of teaching, playful characteristics, as well as the posture in the teaching process will be addressed. In this sense, we had as a starting point the understanding of Capoeira based on commonly discussed topics, which allowed us to establish the following axes of work: Historicity, Specific Movement, Musicality, Play, Body Language. Once the axes of work were determined, we experienced the organization and systematization of these contents, based on activities and teaching dynamics. Thus, it is expected to promote strategies that make possible the treatment of Capoeira as a content of school Physical Education in the international scenario, thus configuring a rich pedagogical process, based on a plural and liberating education."
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.