Design of Advanced Technologies for Performance Tracking and Analysis in Fitness and Nutrition

Abstract

The article's focus was on evaluating the design of a mobile platform using the Mobile-D methodology, which uses machine learning to enhance users' physical performance and well-being by analyzing data from their devices and providing personalized recommendations. The main objective of the application is to improve health and well-being by offering personalized exercise plans and nutritional recommendations, reducing diseases related to lifestyle choices. Regarding the methodological aspects, a preliminary evaluation was conducted of a weight prediction algorithm, a collaborative filtering algorithm, and an assessment of the training level for new users. In terms of the findings, these have been significant regarding the algorithm designed to predict weight and recommend appropriate exercise and nutrition plans according to the user's experience, successfully evaluating the algorithm's ability to adjust the distribution based on the user's experience levels. Additionally, the ability to assess the satisfaction of gym clients and workers (n =225) who use a mobile application for tracking physical and nutritional performance. The results showed that 88% of users were satisfied or very satisfied with the application, indicating its relevance, ease of use, and effectiveness in meeting users' needs. The majority of users considered that the application was in line with their fitness goals, and a small percentage expressed dissatisfaction or negative aspects. The study concludes that the application is a valuable tool for improving health outcomes.