<![CDATA[Adopting a healthy lifestyle necessitates a well-balanced nutritional plan and personalized exercise routines aligned with an individual's health status. The healthcare system often lacks personalized care, leading to weak prevention and generic diets. This study presents an IoT-based framework for easy health monitoring without frequent doctor visits. The system integrates sensors to measure vital indicators like pulse rate, body temperature, SpO?, and BMI, with minimal assistance from healthcare personnel. Utilizing data gathered from individuals aged 16–25, ML algorithms like Logistic Regression, Random Forest, and KNN analyze the parameters to deliver personalized dietary and fitness recommendations. The dataset includes BMI, body temperature, pulse rate, and SpO2 measurements gathered via an integrated IoT unit. Before analysis, the data was refined and optimized through ML algorithms. This comprehensive approach moves beyond traditional diagnostic methods by incorporating personalized recommendations, including dietary plans and exercise routines, tailored based on the evaluated data. Among the evaluated algorithms, Random Forest demonstrated the highest accuracy (99%) in a 60:40 training-to-testing ratio. To improve accessibility, a user-friendly web platform is designed, facilitating seamless interaction and engagement. The framework unifies real-time monitoring, cardiovascular risk detection, and adaptive guidance, bridging fragmented digital health solutions for early intervention and better health outcomes.]]>
Copyrights © 2025
