Heartlyf fuses TinyML edge intelligence, ESP32 wearable hardware and real-time Firebase cloud to continuously monitor ECG, detect arrhythmias and dispatch GPS-enabled emergency alerts in under one second.
8 cutting-edge features that make Heartlyf the most advanced IoT cardiac monitoring platform available.
TinyML model detects 5 types of cardiac arrhythmias with >95% accuracy in real-time.
On-device inference using ESP32 with quantized TensorFlow Lite — no cloud latency.
NEO-6M GPS sends precise coordinates with every emergency alert via Telegram.
AD8232 sensor captures 250Hz ECG signals with 12-bit ADC precision continuously.
Monitor vitals from any device via responsive PWA with full support.
Auto-generated PDF medical reports with ECG strips, HRV analysis and AI notes.
Instant Telegram, SMS and push notifications to family during cardiac events.
End-to-end pipeline from IoT sensor to emergency response.
Quantized INT8 model for ESP32 edge inference
Sub-second cloud sync for ECG vitals and alerts
Live ECG visualization and patient dashboards
Instant emergency notifications with GPS coordinates
MIT-BIH training pipeline and model evaluation
Main controller with dual-core 240MHz CPU, WiFi & Bluetooth. Runs TinyML edge AI model locally.
Dedicated cardiac monitor IC with low-power op-amp. Captures clean ECG waveforms at 250Hz.
Optical heart-rate and SpO2 sensor using PPG technology. Accuracy ±2% SpO2.
2000mAh rechargeable LiPo with USB-C charging. Up to 48h continuous monitoring.
AD8232 ECG + MAX30105 SpO2 capture physiological signals at 250Hz sampling rate
Bandpass filter (0.5–40Hz), baseline wander removal, noise reduction on ESP32
TensorFlow Lite model classifies ECG rhythm in <100ms on ESP32 edge device
Data synced to Firebase Realtime DB. Deep learning model on cloud runs secondary analysis
Telegram + SMS alerts with GPS coordinates sent instantly to emergency contacts
Cardiac analysis engine trained using the MIT-BIH Arrhythmia Database — gold-standard ECG dataset provided by PhysioNet.
AI-Powered Cardiac Monitoring System — Senior Capstone Project, GNIOT 2025-26