Activity Classification in Independent Living Environment with JINS MEME Eyewear
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
The population of older adults relative to the total population is rising rapidly worldwide, and this contributes to an increased burden on healthcare systems. Older adults with complex needs are often limited in their ability to perform basic daily activities, and they may require task-specific supports. With continuous health-monitoring systems, the ability to recognize people's activities in their homes can enable automated assisted living systems, caregivers and clinicians to provide suitable adaptive care. With the advent of miniaturized sensing technology, which can be wearable, it is now possible to collect and store data on different aspects of human movement under realistic independent living conditions.In our most recent Smart Condo™ study, twenty-six participants spent one two-hour session in the one-bedroom living environment, either alone or in pairs, and performed a scripted protocol of activities of daily living. Twelve of these participants wore the commercial smart eyewear device JINS MEME, which collected electrooculography, accelerometer and gyroscope data throughout their sessions. In this paper, we describe our method for offline classification of the participants' activities. We show that this method yields equal or better results with a variety of activities compared to approaches that involve more restrictive wearable device setups. The results demonstrate the suitability of JINS MEME for recognition of activities of daily living and identify limitations associated with the current model.
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 | 0.000 | 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 | 0.000 | 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