Fusion Sense Integrates Environmental Data With Health
Fusion Sense is a project that builds a context-aware health monitor using three Arduino UNO Q edge nodes, integrating ECG, SpO₂, PPG and environmental sensors. It trains TinyML models with Edge Impulse on MIT-BIH (109,446 samples) and PTB (14,552 samples), uses GANs to balance classes, and deploys optimized classifiers for millisecond, on-device inference. The system targets real-time, privacy-preserving health monitoring at the edge.
Key Points
- 1Integrates ECG, SpO₂, PPG and environmental sensors into a unified, edge-based health monitoring cluster.
- 2Uses Arduino UNO Q cluster and TinyML via Edge Impulse for low-latency, on-device inference.
- 3Applies GAN-augmented MIT-BIH and PTB datasets to mitigate class imbalance and improve cardiac classification.
Scoring Rationale
Notable technical integration and actionable Edge ML implementation, limited by project-level validation and lack of peer-reviewed results.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
