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
The aim of this study was to propose a set of network methods to measure the specific properties of a team. These metrics were organised at macro-analysis levels. The interactions between teammates were collected and then processed following the analysis levels herein announced. Overall, 577 offensive plays were analysed from five matches. The network density showed an ambiguous relationship among the team, mainly during the 2nd half. The mean values of density for all matches were 0.48 in the 1st half, 0.32 in the 2nd half and 0.34 for the whole match. The heterogeneity coefficient for the overall matches rounded to 0.47 and it was also observed that this increased in all matches in the 2nd half. The centralisation values showed that there was no 'star topology'. The results suggest that each node (i.e., each player) had nearly the same connectivity, mainly in the 1st half. Nevertheless, the values increased in the 2nd half, showing a decreasing participation of all players at the same level. Briefly, these metrics showed that it is possible to identify how players connect with each other and the kind and strength of the connections between them. In summary, it may be concluded that network metrics can be a powerful tool to help coaches understand team's specific properties and support decision-making to improve the sports training process based on match analysis.
RESUMO
The main objective of this study was to analyse the distance covered and the activity profile that players presented at the FIFA World Cup in 2010. Complementarily, the distance covered by each team within the same competition was analysed. For the purposes of this study 443 players were analysed, of which 35 were goalkeepers, 84 were external defenders, 77 were central defenders, 182 were midfielders, and 65 were forwards. Afterwards, a thorough analysis was performed on 16 teams that reached the group stage, 8 teams that achieved the round of 16, 4 teams that reached the quarter-finals, and 4 teams that qualified for the semi-finals and finals. A comparison of the mean distance covered per minute among the playing positions showed statistically significant differences (F(4,438) = 559.283; p < 0.001; 2 = 0.836; Power = 1.00). A comparison of the activity time among tactical positions also resulted in statistically significant differences, specifically, low activity (F(4,183.371) = 1476.844; p < 0.001; 2 = 0.742; Power = 1.00), medium activity (F(4,183.370) = 1408.106; p < 0.001; 2 = 0.731; Power = 1.00), and high activity (F(4,182.861) = 1152.508; p < 0.001; 2 = 0.703; Power = 1.00). Comparing the mean distance covered by teams, differences that are not statistically significant were observed (F(3,9.651) = 4.337; p < 0.035; 2 = 0.206; Power = 0.541). In conclusion, the tactical positions of the players and their specific tasks influence the activity profile and physical demands during a match.
RESUMO
The performance of football players within game context can be analyzed based on their ability to break or (re)balance the attacker-defender dyad. In this context, the analysis of each sub-phase (e.g., 1v1, 2v2) presents a feature that needs to be taken into account in sports analysis. This study aims to investigate the interpersonal dynamics dyad formed by the attacker and the defender in 1v1 situations with a goalkeeper. A sample of 11 football male players (age: 17.91 ± 1.04 years) with 8.6 ± 1.52 years of practice experience participated in the study. Analyzing the 1v1 sub-phase, results show that the distance, speed and angular amplitude between the attacker and the defender increases, especially when the attacker attempts to overtake the defender (i.e., score a goal). We conclude that decision-making emerges from the perception that players draw from the action, actively and consistently interacting to find solutions to emerging problems within the game context.
RESUMO
The aim of this pilot study was propose a set of network methods to measure the specific properties of football teams. These metrics were organized on "meso" and "micro" analysis levels. Five official matches of the same team on the First Portuguese Football League were analyzed. An overall of 577 offensive plays were analyzed from the five matches. From the adjacency matrices developed per each offensive play it were computed the scaled connectivity, the clustering coefficient and the centroid significance and centroid conformity. Results showed that the highest values of scaled connectivity were found in lateral defenders and central and midfielder players and the lowest values were found in the striker and goalkeeper. The highest values of clustering coefficient were generally found in midfielders and forwards. In addition, the centroid results showed that lateral and central defenders tend to be the centroid players in the attacking process. In sum, this study showed that network metrics can be a powerful tool to help coaches to understanding the specific team's properties, thus supporting decision-making and improving sports training based on match analysis...
"Avaliando as conexões entre jogadores de futebol utilizando métricas de network: Um estudo piloto." O presente estudo piloto teve como objetivo do piloto propor um conjunto de métodos de network para avaliar as propriedades de equipes de futebol. Essas métricas foram organizadas em função dos níveis de análise "meso" e "micro." Foram analisados cinco jogos oficiais da mesma equipa participante na Primeira Liga Profissional de Futebol Português. Um conjunto de 577 jogadas atacantes foram analisadas ao longo desses cinco jogos. As interações entre companheiros de equipa foram recolhidas e processadas seguindo os níveis de análise anteriormente referidos. Os resultados evidenciaram que os maiores valores de escala de conetividade foram encontrados nos defensores laterais e zagueiros, bem como, nos meio-campistas e os menores valores encontraram-se no atacante e goleiro. Os maiores valores de coeficiente de agrupamento foram geralmente encontrados nos meio-campistas e atacantes. No caso dos resultados relativos ao centroid verificou-se que os defensores laterais e zagueiros tendem a ser os jogadores centroids no processo atacante. Em resumo, este estudo destacou que as métricas de network podem ser um instrumento poderoso para auxiliar os treinadores a compreenderem as propriedades específicas das equipes, suportando a tomada de decisão e melhorando o treinamento tendo como base a análise de jogo...
"La evaluación de las conexiones entre los jugadores de fútbol utilizando métricas de red: un estudio piloto." El objetivo de este estudio piloto fue el de proponer un conjunto de métodos para evaluar las propiedades de la red los equipos de fútbol. Estas métricas se organizaron de acuerdo con el nivel de análisis "meso" y "micro." Se analizaron cinco partidos oficiales en el mismo equipo que participan en la Liga Premier de Fútbol Profesional de Portugal. Se analizó una serie de 577 atacantes mueve en estos cinco partidos. Las interacciones entre los compañeros de equipo fueron recolectados y procesados siguiendo los niveles de análisis mencionados. Los resultados mostraron que los valores más altos de conectividad de la escala se encuentran en los defensores laterales y centrales, así como los mediocampistas centrales y los valores más bajos se encontraron en-punta delantera y el portero. Los valores más altos del coeficiente de agrupamiento se encuentran generalmente en el medio y los atacantes. En los resultados para el jugador centroid, se encontró que los defensores laterales y centrales tienden a ser actores centrales en el proceso de ataque. En resumen, este estudio pone de relieve que las métricas de la red puede ser una herramienta poderosa para ayudar a los entrenadores a comprender las propiedades específicas de los equipos, el apoyo a la toma de decisiones y la mejora de lo entrenamiento basada en el análisis del juego...
Assuntos
Humanos , Masculino , Desempenho Acadêmico , FutebolRESUMO
A tendência evolutiva do futebol determina as necessidades de produzir ferramentas inovadoras que aumentem substancialmente a eficiência da análise de jogo. Considerando os métodos tradicionais notacionais como limitados para a interpretação dos processos de jogo, a investigação carece de novos métodos nos quais prevaleça a análise do processo. Dessa forma, o presente trabalho propõe-se a analisar novas métricas quantitativas e automáticas de avaliação tática no futebol, nomeadamente o centroid de equipe e o índice de dispersão.
The evolutionary tendency of the football game determines the conception of the new tools that increase the efficiency of the match analysis. The traditional notational analysis, actually, are limited to understand the true dynamic of the football match, thus the investigation lacks by new methods to understand the process and not just the product. Therefore, this work aims analyze new automatically tactical metrics, specifically the centroid and the stretch index method.
RESUMO
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.
RESUMO
O presente estudo objetivou analisar as amplitudes angulares do atacante em relação ao defensor ao longo da série temporal de prática, tentando verificar se tal parâmetro contribui para a quebra da estabilidade da díade atacante-defensor. Participaram 11 futebolistas (17,91 ± 1,04 anos de idade) com 8,6 ± 1,52 de anos de prática. De forma a entender a relação da posição entre o atacante e o defensor, procedeu-se ao cálculo do posicionamento angular entre ambos. Para o efeito, considerou-se o ângulo 0º como sendo o ângulo entre o atacante e o defensor quando estes formam uma linha perpendicular à aresta do campo onde se encontra a baliza estando o defensor mais próximo da mesma. Os resultados indicam uma oscilação regular por parte do atacante no sentido de procurar desequilibrar o oponente sendo que, através dessa ação-reação o atacante procura encontrar novas soluções que resultem da exploração do meio e do adversário.
The aim of this study was to analyze the angular amplitudes of the attacker over the defender along the series of practice, trying to see if this parameter contributes to the breakdown of the stability of the attacker-defender dyad. In the study participated 11 players (17.91 ± 1.04 years old) with 8.6 ± 1.52 years of practice. In order to understand the position relationship between the attacker and defender, we calculate the angular positioning between them. For this purpose we considered the 0º angle as the angle between the striker and the defender when they form a perpendicular line to the edge of the field where staying the goal. The results show a regular oscillation by the attacker to seek to unbalance the opponent and that through this action-reaction the attacker tries to find new solutions resulting from the exploitation of the environment and the opponent.
El presente estudio tuvo como objetivo analizar las amplitudes angulares del atacante contra el defensor, tratando de ver si este parámetro contribuye a la ruptura de la estabilidad de la pareja atacante-defensor. Participaron 11 jugadores (17,91 ± 1,04 años), con 8,6 ± 1,52 años de práctica. Con el fin de entender la relación de posición entre el atacante y el defensor, procedió al cálculo de la posición angular entre los dos. Con este fin, hemos considerado el ángulo de 0º como el ángulo entre el delantero y el defensor cuando forman una línea perpendicular a la arista del campo donde se encuentra la portería, estando el defensor está más cerca de la misma. Los resultados muestran una oscilación regular del atacante para tratar de desequilibrar al oponente siendo que a través de esta acción-reacción, el atacante trata de encontrar nuevas soluciones que resultan de la exploración del ambiente y del adversario.