Non‐imaging Passive Infrared Matrix Bed Occupancy Sensor for Persons with Dementia
Bibliographic record
Abstract
BACKGROUND: 65% of persons with dementia (PWD) experience disturbed sleep, often exiting their beds up to 14 times per night, impacting caregivers' well-being. The unpredictability is a leading cause of institutionalization in Taiwan. Reliable sleep monitoring can help caregivers rest better, reducing their stress. Current sensors include mechanical pressure sensors and cameras. Pressure sensors offer privacy but require mattress contact. Since PWDs sleep may sleep in unusual postures, comprehensive coverage while necessary, is costly and may be uncomfortable. Cameras, while contact-free, raise privacy issues and don't work well with heavy blankets. We developed a bed occupancy sensor using a passive infrared matrix sensor that maintains privacy, costs less than $100/unit, and works with blankets, quilts, and unusual sleeping positions of PWD. METHOD: An Infrared matrix and a motion sensor on the ceiling monitor the room. Standard deviations of bed, floor and motion data is processed by a microcontroller, which determines if the PWD is in bed (sleeping soundly or fitfully), sitting on the side, beside the bed, or has left the room. RESULTS: The system was tested in the lab, detecting bed entries and exits under various conditions with < 5s response time, using a commercial bed pressure sensor as a benchmark. It was also deployed for 136 days in a real-life setting in Taiwan, where temperatures ranged from 8°C to 35°C. CONCLUSION: An ambient temperature insensitive, low-cost cost, privacy-preserving, non-imaging remote bed occupancy sensor, and algorithm has been developed with < 5s response time.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".