RESUMO
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.
Assuntos
Desempenho Atlético , Aprendizado Profundo , Reconhecimento Automatizado de Padrão , Dispositivos Eletrônicos Vestíveis , Teorema de Bayes , Humanos , Redes Neurais de Computação , EsportesRESUMO
Este trabalho teve como objetivo desenvolver um dispositivo de produção de um Escoamento Aerodinâmico Induzido (EAI) capaz de simular a constrição ambiental e vento lateral, em contexto experimental de análise ao primeiro serviço de tênis. Para tal, estudou-se o comportamento da bola de tênis sob o efeito de um EAI no túnel de vento e analisou-se (3D) o lançamento da bola no primeiro serviço plano de 12 jogadores de tênis experientes. Concebeu-se um dispositivo composto por um ventilador industrial ajustável em altura e em profundidade às caraterísticas morfológicas e técnicas do tenista. O caudal de EAI é estável e monitorizável através de um variador de velocidade. Conclui-se que as três "velocidades de vento" selecionadas, constrangem o lançamento da bola (simulado por uma máquina) no eixo dos x (lateral), tornando o dispositivo capaz de perturbar a execução motora do serviço de tênis, recriando uma constrição ambiental relevante para a modalidade.
The present work developed a device for producing an induced aerodynamic flow (EAI) to simulate the environmental constraint, side wind, in the experimental context of analysis on the first tennis serve. For this, we studied the tennis ball behavior under the influence of an EAI in a wind tunnel, and 3D analyzed the ball toss in the first flat serve of 12 experienced tennis players. We designed a device composed of an industrial ventilator with adjustable height and depth to the morphological and technical features of each player. The EAI flow generated by the device is stable and monitorable through a speed variator. The three selected wind speed have constrained the ball toss (simulated by the device) on the x axis (lateral), making the device able to disturb the performance of the tennis serve, recreating therefore in an experimental context a relevant environmental constraint to tennis.