P2‐387: Daily Routine Monitoring in Older Adults through a Lightweight Sensor, Non‐Intrusive Infrastructure
Bibliographic record
Abstract
The avoidance of institutionalization in older adults with or without cognitive decline is of paramount importance from a public health perspective (Piau, Campo et al. 2014). One of the challenges of assistive technology is to effectively monitor Activities of Daily Living (ADLs) in order to ensure that they are performed adequately. This is an important step toward preventing incidents (e.g. fall or intrusion) and detecting eventual functional decline through longitudinal observations. Twenty community-dwelling older adults were recruited. Participants were all aged 70 over (m=81 yo), with a score over 25 on the Mini-Mental Examination State, and were moderate to fully autonomous (GIR 4-6: an autonomy scale used in France). Participants were asked to sketch their daily ADLs routine (time at which they wake up, eat, shower, etc.). A set of 11 sensors (motion, contact, and electric) were installed, for 5 to 12 months in each participant’s home (see Caroux, Consel, Dupuy, Sauzéon, 2014 for details). Then, we calculated the most probabilistic routine for each selected ADLs based solely on the data collected, with minimal a priori on time frames or durations for each ADL. Reported routine was compared to the observed routine to validate formulas. For all ADLs mixed together, reported and observed routines strongly correlated, r(113) = .978, p < .001. Moreover, significant correlations were observed for each respective ADLs, despite moderate inter-subject variability (waking up: r(19)=.652, breakfast: r(18)=.652, dressing/showering: r(19)=.819, lunch: r(20)=.534, dinner: r(20) = .550, going to sleep: r(20)=.485).
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 | 0.003 |
| 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 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.008 | 0.002 |
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".