The HealthFusion system achieved 92.59% accuracy for human activity recognition and a mean absolute error of 2.97 BPM for heart rate estimation, outperforming commercial devices.
Does the HealthFusion system accurately recognize human activity and estimate heart rate using smartphone sensors compared to commercial devices?
The HealthFusion smartphone-based system demonstrates high accuracy for human activity recognition and heart rate estimation, potentially offering a reliable tool for telemedicine and preventive healthcare.
This paper presents HealthFusion, a real-time health monitoring system integrating Human Activity Recognition (HAR) and heart rate estimation using deep learning optimized for smartphones. The HAR component uses a four-layer MLP achieving 92.59% accuracy on the UCI HAR dataset. The heart rate module achieves 2.97 BPM MAE and R² of 0.9629, outperforming commercial devices (4–7 BPM). Both models run in a React Native and FastAPI application with user authentication, dashboards, history, and SQLite storage. Comprehensive testing validates reliability for telemedicine and preventive healthcare.
M Umair Anwar (Wed,) reported a other. HealthFusion system vs. Commercial devices was evaluated on Human Activity Recognition accuracy and heart rate estimation mean absolute error (MAE). The HealthFusion system achieved 92.59% accuracy for human activity recognition and a mean absolute error of 2.97 BPM for heart rate estimation, outperforming commercial devices.