projects

Four projects connecting safe reinforcement learning, generative personalization, contrastive physiological modeling, scientific computing, and biomedical uncertainty quantification.

health-ai

24H Cuffless Blood Pressure Monitoring

Wearable PPG blood pressure monitoring with personalization, calibration, and product-level robustness.

Deceleration Capacity Screening from Wearable Signals

Wearable heart-risk screening using deceleration capacity theory, ECG/PPG representation learning, and long-horizon aggregation.

reinforcement-learning

SafeRunRL: PPO for Target-Heart-Rate Treadmill Control

Research prototype for target-heart-rate treadmill control using wearable PPG/ACC states, a learned heart-rate response environment, and PPO.

research

Orthogonal Polynomials and Biomedical Uncertainty Quantification

Ph.D. research on recurrence algorithms, polynomial chaos expansion, UncertainSCI, and reliable biomedical simulation.