Daily Routine Recognition from Longitudinal, Real-Life Wearable Sensor Data for the Elderly
Bibliographic record
Abstract
As our population continues to age, there is a growing need for tailored healthcare solutions for the elderly. Despite the promise of current wearable devices, the effectiveness of these devices in addressing complex healthcare needs, especially in identifying cognitive decline still requires extensive refinement. Analyzing Routines can be a potential solution as it can provide insights into cognitive health, potentially serving as an early indicator of cognitive decline or impairment. This paper presents a framework to identify routine and non-routine behaviors using the CASAS smartwatch dataset, a public real-life longitudinal dataset. This is of particular significance in health monitoring and understanding long-term behavior patterns among the elderly. Our work addresses challenges throughout the entire Routine recognition process, including noisy and incomplete data, class imbalance, reliance on accurate activity labeling, and the preprocessing overhead typically encountered in wearable sensor datasets. The findings of our study suggest that labeling the dataset based on cosine similarity and label propagation results in improved activity recognition accuracy compared to kNN for classes with fewer samples. However, kNN demonstrates the best overall performance, particularly for classes such as Work, Other, Hygiene, where it excels due to its abundance in the dataset. Moreover, our findings emphasize the importance of identifying the most occurring activity sequences, which influences routine identification. This underscores the importance of recognizing and modeling recurring activity patterns, highlighting their significance in the routine identification process. Understanding these patterns can have an impact on the healthcare of the elderly, enabling tailored interventions to support healthy aging at home. In the future, this research aims to contribute to improved monitoring, timely interventions, and ultimately, enhanced quality of life for older adults living independently.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".