Assessing Individual Route-Level Distress from Collective Distress by Applying Multitask Learning to Promote Older Adults’ Daily Walking
Bibliographic record
Abstract
Older adults’ walking is significantly limited by the distress they experience from environmental stressors in the current pedestrian infrastructure. To alleviate their stressful experience, a routing system that recommends less stressful routes has great potential for just-in-time intervention to promote their daily walking. In the routing system, a means for assessing individual route-level distress (i.e., the overall distress an individual experiences on a route) is required to compare the route-level distress among candidate routes and select the optimal one. However, existing assessment methods require pre-evaluation of all possible routes in a pedestrian network, making their adoption in a routing system infeasible. To overcome this, the authors propose a collective distress and multitask learning (MTL)–based method that does not rely on pre-evaluation of every route. Instead, the proposed method predicts route-level distress through collective distress, given that an individual’s overall distress is typically influenced by stressors along a route, and collective distress serves as a proxy for stressors. Specifically, the authors first examined the explanatory power of collective distress on individual route-level distress to determine its potential as a predictive input through regression analysis using 1,012 walking trips from 64 older adults. Then, an MTL model with a deep belief network (DBN) structure was developed and tested to predict individual route-level distress from collective distress. Results showed that metrics quantifying the frequency and intensity of collective distress have significant explanatory power for individual route-level distress (McFadden R2: 0.227). Also, the MTL with DBNs presented promising performance (mean absolute error of 0.389 on a 1–5 scale) in predicting a new user’s perceived route-level distress with only seven self-reported route samples. These findings indicate that incorporating collective distress with the proposed MTL-based model can be used in routing systems to provide the least stressful route, thereby enhancing older adults’ walking in pedestrian infrastructure.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".