Hardware-Aware Edge Deep Learning for Multimodal Biomedical Monitoring
Multi-task CNN–SE–Transformer running entirely on an ESP32-S3 for real-time ECG arrhythmia, stress, and activity classification — with on-device adaptive learning and motion-aware alerting. No cloud required.
- 297 ms inference on 10-second multi-sensor windows (ECG, PPG, IMU, GSR)
- 715× reduction in activation storage via head-only backpropagation
- Patent-pending EdgeGuard on-device adaptation framework