Smartwatch PPG + accelerometer signals reframed to detect hypertension signs
CurieuxExplorer · x · 2026-11-12
A Google-related study detects hypertension signs using two sensors already on modern smartwatches: PPG for wrist blood-volume pulse waveforms and accelerometry for stillness detection and ballistocardiogram signals. Instead of estimating noisy point-in-time blood pressure, it reframes the task: multimodal self-supervised learning encodes waveform embeddings, person-level aggregation follows, and a supervised classifier outputs a hypertension score.
More from Embodied
- CoRL Poster: Extending Open-Universe Assistance Games and Dialog Goal Inference to Robots — dhadfieldmenell · 2026-11-13
- Fable 5.2 authors every part of a Rube Goldberg machine, simulated in MuJoCo — jakedahn · 2026-11-13
- Standard Bots CEO Evan Beard aims to build the world's largest robot maker in the US — Rewkang · 2026-11-13
- Spotlight paper EqC: Equilibrium Energy Control for introspective lifelong robot learning — chris_j_paxton · 2026-11-13
- Ex-Tesla Autopilot simulation leads exit stealth at $1.1B valuation with $160M raised — heyshrutimishra · 2026-11-12
- MIMIC and BMW train video-action model hitting up to 100% success on industrial tasks — pess_r · 2026-11-12