Loading...
4 results
Search Results
Now showing 1 - 4 of 4
- Using artificial intelligence for pattern recognition in a sports contextPublication . Rodrigues, Ana Cristina; Pereira, Alexandre Santos; Mendes, Rui; Araújo, André Gonçalves; Couceiro, Micael; Figueiredo, António J.Optimizing athlete’s performance is one of the most important and challenging aspects of coaching. Physiological and positional data, often acquired using wearable devices, have been useful to identify patterns, thus leading to a better understanding of the game and, consequently, providing the opportunity to improve the athletic performance. Even though there is a panoply of research in pattern recognition, there is a gap when it comes to non-controlled environments, as during sports training and competition. This research paper combines the use of physiological and positional data as sequential features of different artificial intelligence approaches for action recognition in a real match context, adopting futsal as its case study. The traditional artificial neural networks (ANN) is compared with a deep learning method, Long Short-Term Memory Network, and also with the Dynamic Bayesian Mixture Model, which is an ensemble classification method. The methods were used to process all data sequences, which allowed to determine, based on the balance between precision and recall, that Dynamic Bayesian Mixture Model presents a superior performance, with an F1 score of 80.54% against the 33.31% achieved by the Long Short-Term Memory Network and 14.74% achieved by ANN.
- Developing a tactical metric to estimate the defensive area of soccer teams : the defensive play areaPublication . Manuel Clemente, Filipe; M. L. Martins, Fernando; Couceiro, Micael; Mendes, Rui; Figueiredo, António J.This study proposes a computational method to inspect the tactical position of players during the match and a new metric to analyse the defensive pressure made by a soccer team. These metrics only require Cartesian information about the players’ positions on the field. As a case study, three matches played by the same professional soccer team were considered, including variables computed for the half of the match (first half vs second half) and the final score of the game for an analysis of variance of tactical performance, trying to identify the influence of such variables on the collective organisation. The data were collected at 1 Hz and from this process, 9218 instances of useful time were collected. The results revealed that the different kinds of final scores had significant effects on the tactical performance. The comparison between two halves of the match revealed significant differences with a small effect size on tactical performance. In summary, this study showed that these new tactical metrics can be a computational option to increase a coaches’ knowledge about the defensive organisation of soccer teams, giving them the possibility to augment their own perception with metrics that can provide specific information.
- A educação física e desporto em Portugal como parte do processo educativo : a ESEC e a sua oferta formativaPublication . Figueiredo, António J.; Mendes, Rui; M. L. Martins, Fernando; Melo, Ricardo; Gomes, Ricardo; Rebelo Leandro, Cristina
- Análise de jogo no futebol : métricas de avaliação do comportamento coletivoPublication . Manuel Clemente, Filipe; Couceiro, Micael; M. L. Martins, Fernando; Figueiredo, António J.; Mendes, RuiO jogo de futebol, como realidade complexa, necessita de uma interpretação do comportamento coletivo da equipa. Assim, o presente trabalho objetivou apresentar 4 métricas de avaliação coletiva baseadas na relação espácio-temporal, procurando identificar diferenças nos comportamentos coletivos nos momentos com e sem posse de bola. Para o efeito, analisou-se um jogo de futebol de sete do escalão de formação sub-14. Os resultados evidenciaram diferenças significativas entre os momentos com e sem posse de bola no que se refere ao espaço ocupado pelas equipas A (F(1, 1506)= 8.31, p= 0.004, η²= 0.005, Power= 0.82) e B (F(1, 1506)= 37.66, p= 0.001, η²= 0.024, Power= 1.00), às triangulações efetivas entre jogadores nas equipas A (F(1, 1506)= 1343.89, p= 0.001, η²= 0.472, Power= 1.000) e B (F(1, 1506)= 968.50, p= 0.001, η²= 0.391; Power= 1.00) e à progressão do centroid nas equipas A (F(1. 1506)= 11.79, p= 0.001, η²= 0.008, Power= 0.93) e B (F(1, 1506)= 9.43, p= 0.001, η²= 0.006, Power= 0.87). Conclui-se com o presente trabalho que as métricas de avaliação coletiva possibilitam uma identificação de relações espácio-temporais entre jogadores, identificando uma expansão maior das equipas na situação com posse de bola, bem como, o avanço do ponto médio da equipa.