IoT Based Health Monitoring with Diet, Exercise and Calories recommendation Using Machine Learning
Abstract With the increasing awareness of health and fitness, the demand for more efficient and personalized fitness solutions is on the rise. This research proposes an innovative system that integrates innovative technologies to streamline gym operations, enhance member experiences, and promote per...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer Nature
2025-04-01
|
| Series: | Human-Centric Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s44230-025-00096-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract With the increasing awareness of health and fitness, the demand for more efficient and personalized fitness solutions is on the rise. This research proposes an innovative system that integrates innovative technologies to streamline gym operations, enhance member experiences, and promote personalized health strategies. The system comprises a website for administration and member registration, coupled with an RFID-based hardware device for member authentication and BMI measurement. Member data, including BMI, is securely stored, and visualized on personalized profiles through line charts. Additionally, machine learning algorithms recommend tailored exercise, diet type, Basal Metabolic Rate (BMR), and daily caloric intake based on individual member data. The study’s method ology includes utilizing a comprehensive dataset from Kaggle, separated into sets for testing and training, to develop and evaluate machine learning models. The Random Forest model demonstrated superior performance in precision, recall, F1-score, and R2 score metrics, making it the optimal choice for the recommender system. In Pakistan, both the fitness and healthcare sectors still rely heavily on manual methods for health assessment and monitoring. In most gyms, trainers manually evaluate members’ fitness levels without leveraging data-driven insights, while in hospitals, BMI calculations are often performed manually by doctors, leading to inefficiencies and potential inaccuracies. Existing automated systems, where available, are either too costly or lack personalization, making them impractical for widespread adoption. Our proposed system addresses these gaps by providing a cost-effective, IoT-integrated solution that automates BMI measurement, gym member authentication, and personalized fitness and dietary recommendations. Our system ensures precision, security, and accessibility, making intelligent health tracking feasible for both gym-goers and healthcare professionals. This research not only enhances automation and efficiency in fitness management but also introduces an affordable technological solution to improve health monitoring in hospitals. |
|---|---|
| ISSN: | 2667-1336 |