Decision support system for effective action recognition of track and field sports using ant colony optimization

Different Decision Support Systems (DSS) are being used for the revolution in the sports sector, based on cutting-edge technology like artificial intelligence, machine learning, the Internet of Things, and virtual reality. The coach can now make very precise and unbiased decisions related to the players' skills and selection. It is now very convenient to improve the skills and performance of the players through the implementation of various computer-grounded methodologies. Professionals can recognize the unwanted behavior of players in time during sports and hence can ensure a peaceful atmosphere during sports. The recognition of non-standard actions by the players can help in the avoidance of serious injuries or illness. The DSS can predict the nature of the weather, and the sports personnel can take decisions regarding the carrying out of games. The players can do their training without any restrictions on space or time. The real-time analysis of already-existing videos of games can help newcomers learn and improve their skills and performances. The trainers can check the physical fitness of the athletes very efficiently and provide them with useful and valuable recommendations related to their fitness level. The proposed study employed ant colony optimization to identify and track the optimal features of athletes in order to improve individual and team performance in sports competitions. The ant colony optimization technique is a probabilistic approach to solving computing problems that can be reduced to identifying suitable paths via graphs. The results of the study show the effectiveness of the proposed study.