Learning-Based Model for Evaluating the Impact of Neighborhood Design on Travel Behavior
Bibliographic record
Abstract
This research developed an agent-based model that evaluates the impact of neighborhood design on travel behavior while accounting for habit formation, social interactions, various levels of information provision, and awareness of transport and land use system changes. The developed model employs a framework that integrates random utility maximization theory with reinforcement learning concepts to account for the bounded rationality and knowledge learning process. Moreover, the model utilizes the diffusions of innovations theory to simulate how agents propagate information across family members and co-workers. It also adds a time dimension to the modal shift process, which could be used to indicate the relative duration to reap the full benefits of proposed scenarios. The model was applied to a neighborhood in Kelowna, British Columbia, Canada, to assess the impact on travel behavior of the SMARTer growth principles. The results showed that retrofitting non-motorized networks has more impact on modal shift than retrofitting road networks. This implies that infrastructure investments related to providing more accessibility for non-motorized users may be more socially and sustainably profitable than investments in policies targeting auto users. In addition, the results revealed that land use policies led to higher modal shift to non-motorized modes compared to retrofitting the transportation network, which highlights the importance of integrating land use and transportation planning. Similarly, the results demonstrated that transportation demand management policies can provide a positive stimulus to commuters to maintain familiarity with active transportation (AT) modes, which led in the presented case study to an increase in AT modal share.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".