Published Paper Details:

Understanding human action patterns is essential for many things, like keeping an eye on your health or figuring out how to get better at sports. This paper presents a novel approach to a human action pattern recognition system using physical training for children's activities. In this approach, children do exercises. The recognition system is developed by using a varied dataset of physical training attendees performing different exercises. With the use of computer vision and machine learning to implement logistic regression to track and categorize these actions, with consideration given to both spatial and temporal aspects. This real-time recognition system doesn't just accurately identify actions; it also provides physical training for children with personalized feedback and recommendations enhances the fitness experience and promotes proper exercise form to prevent injury. Through this approach, the aim is to broaden the accessibility of action pattern recognition, making it available to a larger group of individuals. The impact is felt in fitness, healthcare, and sports performance analysis, nurturing improved exercise habits and overall well-being.