A system for the monitoring of sleep-related parameters based on inertial measurement units
Bibliographic record
Abstract
Sleep is an essential process needed by the body; as a result, the effects of sleep deprivation are severe and include increased risk of heart diseases and dementia. It is estimated that 40% of Canadians suffer from sleep disorders; nevertheless, most of them are unaware of their condition. Approximately 75–80% of cases of sleep apnea (SA), the most common sleep disorder, are still undiagnosed and thus lacking treatment. However, demand for sleep studies is unmet by the available spaces—high operating costs and expensive equipment limits their availability and the access to diagnosis. Thus, the necessity of inexpensive, yet adequate alternatives for the monitoring of sleep parameters is evident. We present the development of a respiratory effort (RE), body position (BP), and heart rate (HR) monitoring systems for sleep using inertial measurement units (IMU) comprising a 3D accelerometer, gyroscope, and magnetometer. These parameters are required by the American Academy of Sleep Medicine (AASM), and necessary for diagnosis of SA. The chest’s angle variations due to breathing are tracked using all three sensors in the IMU and an extended Kalman filter (EKF) as a data fusion method, thus obtaining the RE in supine and lateral recumbent positions, as well as monitoring BP by tracking gravity vector orientation relative to the body. The system is self-contained, wireless, battery operated and real time. Thus, we improve over previous works that only measure RE limited to a supine position of the body. The HR is estimated by detecting cardiac induced vibrations from a single axis angular rate measuring channel. Using a simple algorithm with an adaptive threshold for peak detection, we obtain good instantaneous HR readings. Although its simplicity sacrifices some accuracy, it is amenable for real-time implementation in a low cost, wireless microcontroller, such as the one utilized for RE/BP. Both tests show promising results, with a high correlation value for RE (e.g. 96.26%) and low error values for HR (e.g. mean 0.35bpm) with respect the reference signals. Furthermore, preliminary tests show the possibility of obtaining all three signals using a single IMU device, suggesting a viable alternative to current technologies.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.008 |
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".