Development of a Sensor-Based Behavioral Monitoring Solution to Support Dementia Care
Bibliographic record
Abstract
BACKGROUND: Mobile and wearable technology presents exciting opportunities for monitoring behavior using widely available sensor data. This could support clinical research and practice aimed at improving quality of life among the growing number of people with dementia. However, it requires suitable tools for measuring behavior in a natural real-life setting that can be easily implemented by others. OBJECTIVE: The objectives of this study were to develop and test a set of algorithms for measuring mobility and activity and to describe a technical setup for collecting the sensor data that these algorithms require using off-the-shelf devices. METHODS: A mobility measurement module was developed to extract travel trajectories and home location from raw GPS (global positioning system) data and to use this information to calculate a set of spatial, temporal, and count-based mobility metrics. Activity measurement comprises activity bout extraction from recognized activity data and daily step counts. Location, activity, and step count data were collected using smartwatches and mobile phones, relying on open-source resources as far as possible for accessing data from device sensors. The behavioral monitoring solution was evaluated among 5 healthy subjects who simultaneously logged their movements for 1 week. RESULTS: The evaluation showed that the behavioral monitoring solution successfully measures travel trajectories and mobility metrics from location data and extracts multimodal activity bouts during travel between locations. While step count could be used to indicate overall daily activity level, a concern was raised regarding device validity for step count measurement, which was substantially higher from the smartwatches than the mobile phones. CONCLUSIONS: This study contributes to clinical research and practice by providing a comprehensive behavioral monitoring solution for use in a real-life setting that can be replicated for a range of applications where knowledge about individual mobility and activity is relevant.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".