0746 REVIEW OF A MULTISENSOR, LOW COST, AND UNOBTRUSIVE APPROACH TO DETECT MOVEMENTS IN SIT AND SLEEP
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Movement measurements in the Suggested Immobilization Test (SIT) and sleep recordings are typically measured by polysomnography (PSG) with electromyography (EMG). We investigated the viability of an alternate home-based recording system, SleepSmart, which combines sensing technologies integrated in a bed-sheet and 3D video to detect movements. Pilot study: 19 participants were administered the SIT in the Biomechanics Lab; the subject lay on an angled bed for 30 minutes and slept for up to 90 minutes. We used a combination of the Kinect videography system enabling conventional 2D and novel 3D-technology, a portable EMG device, and a mattress topper sheet fitted with flexible sensors. EMG data was recorded for both tibialis anterior muscles. The goal was to perform pilot testing on the integrated system to fine tune the procedure and equipment. Main findings: The 3-D video recordings enabled the study of movement developments, a novel feature not captured by 2-D video-recordings and/or EMG. Pitfalls in the EMG setup, overall protocol design, and data synchronization were encountered. Several requirements were identified to optimize the test-setup: (1) A millisecond-level time stamping system was needed to sync data between multiple modalities; this mechanism will support identification of movement characteristics (development and peak) for Periodic Limb Movements (PLM). (2) Reflective or light-absorbing artifacts should be removed to maintain video data integrity. (3) With the demonstrated effectiveness of the video-data characterization feature, the mattress-sensor framework should implement machine learning algorithms to automatically identify movement events. Based on findings, the mattress sensors are being replaced with newer sensors to improve performance. The switch from force-sensing resistors (FSRs) to accelerometers incorporates detection of physiological signals (heartbeat and breathing rate). Identification algorithms will include sleep apnea events. More pilot testing will be conducted to validate changes. Kids Brain Health Network (previously NeuroDevNet), AIT Austrian Institute of Technology, BC Children’s Hospital Foundation.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it