MotionPI ← Back to project overview

Wearable biosignals · Free-living activity

Reading real-world movement from a wristband

A free-living recording from one participant in an NIH field study — 104 hours of ENMO across 11 days — raw wrist acceleration reduced to ENMO on-device, then screened in real time for moderate-to-vigorous physical activity.

104 h
ENMO recorded across 11 days, day and night
6 s
uniform grid the 15-s ENMO stream is resampled onto
100.6 mg
MVPA threshold · 70% of a 7-min window
~7.7 M
records / day sustained across the study

ENMO across two weeks of daily life

The wristband streams 15-second ENMO averages; they are plotted here on a uniform 6-second grid, so each point is a resampled value rather than a new measurement. Activity concentrates in waking hours and collapses overnight — the exact free-living structure health-sensing models need, and where signal quality usually breaks.

ENMO (15-s average, 6-s grid) 7-min moving average 100.6 mg MVPA threshold night Hover a point for its value · drag left-to-right across the chart to zoom into a window · double-click to zoom back out · click any legend entry to show or hide that layer
De-identified data from one consented participant, shown for demonstration. The full study is stored on the University of Utah CHPC and keyed by pseudonymous IDs.

What it takes to make this signal trustworthy

Clean free-living biosignals don't happen by accident — they are an engineering result.

ENMO computed on the wristband

The wristband derives gravity-adjusted acceleration (ENMO) on-device and streams compact 15-second summaries over BLE — so the phone stores motion-relevant features instead of gigabytes of raw high-rate waveform.

Real-time MVPA detection → survey

When 70% of ENMO in a 7-minute window exceeds 100.6 mg, the device flags moderate-to-vigorous activity and fires an in-the-moment survey — capturing context at the moment the behavior happens, not hours later from recall.

Clean in the wild, by design

Offline-first buffering, schema-validated writes, and automatic BLE reconnection keep the record intact when phones die, networks vanish, or the OS kills the app — the platform sustains ~7.7M records a day across the deployment.

Privacy engineered in

Records are keyed by a pseudonymous device ID, GPS is AES-256 encrypted on-device, and everything lives on university HPC — the research team never has access to participant identities.