Authors :

Alhassan Adamu

Address :

Department of Computer Science, Aliko Dangole University of Science and Technology, Wudil

Abstract :

The knowledge of group tactical behavior has grown into a crucial component in the field of athletic data analysis and visualization at this point in time. In order to make effective use of the ever-increasing volumes of complex information, collaborative and automated information analysis is of critical importance. One of the most common methods utilized in professional team sports is the collection and examination of data pertaining to the monitoring of athletes. The purpose of this exercise is to investigate tiredness and the following adaptive reactions, as well as to conduct an analysis of performance potential and to reduce the likelihood that damage and disease will really occur. For the purpose of the continued development of fitness goods that are based on artificial intelligence (AI), the data visualization software that was developed during the era of big data analytics provides a solid framework for the development of these products. Consequently, the objective of this study was to offer an effective video visualization framework based on artificial intelligence and big data analytics. This framework is called the HybridAI Sports Visualization Framework (HybridAISVF), and it was designed to improve the visualization of sports data. For the purpose of this study, the technology of machine learning is utilized to classify the sports video. This is accomplished by extracting both the temporal and spatial properties of the films. Our approach is built on a foundation that is comprised of a combination of temporal pooling layers and convolutional neural networks. The findings of the trials indicate that the Hybrid AISVF model, which is recommended, significantly enhances accuracy, recall, precision and F1-score in comparison with the other models that are currently being utilized.

Keywords :

Sports Visualization; Big Data; Sports Data Analysis; Artificial Intelligence; Video-Based Visualization; Risk Reduction.