Development of Motion Detection Algorithm Using 3d Sensors for Patient Monitoring Support Service System
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
With the aging of the overall patient population, the incidence of patients developing delirium during hospitalization is increasing. This study aims to improve post-operative safety management and reduce the workload of nurses related to patient care. We have developed a monitoring system that uses 3D sensors to detect specific behaviors and motions that require attention in cases where patients exhibit abnormal behaviors, such as falls and self-removal of IV lines, and trigger alerts. In this paper, we present an algorithm for detecting dangerous motions. We use the point cloud data generated by the 3D sensors that collect 3D information. We analyze the motions of subjects based on changes in the point cloud data and tag specific human body motions and behaviors. When there are no obstacles in the imaging direction of the 3D sensors, we detect human body movements (supine position on the bed, half sitting up, and separated from the bed) with an F-measure of 98.33% and motions (thrashing limbs, touching mouth/neck/arms, no action) with an F-measure of 98.23%. We detect the basic motions that trigger alert notifications. However, the detection accuracy decreases depending on the imaging conditions and subject movements. We use invisible and safe near-infrared light for motion detection and recognition to perform imaging even after lights are turned off, without disturbing patients' sleep. Motion recognition using point cloud data is a privacy-friendly monitoring method with a low risk of acquiring personally identifiable information. In the future, we plan to verify the algorithm using actual patients and investigate the detection of motions in addition to those considered in this study.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 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