Developing Models to Evaluate Pedestrian-Cyclist Interaction Satisfaction on Pedestrian Streets
Bibliographic record
Abstract
RÉSUMÉ: «RÉSUMÉ: Les modes de transport actifs (la marche et le vélo) sont essentiels au développement de systèmes de transport accessibles, sécuritaires et durables. Pour promouvoir le transport actif, les villes aménagent des rues piétonnes et améliorent les espaces de marche et de vélo tout en priorisant les préoccupations de sécurité. De nombreuses études ont été menées pour évaluer la satisfaction des personnes à l'égard de divers lieux et espaces, et il est largement reconnu que la satisfaction est influencée par un large éventail de facteurs. Les études sur la satisfaction intègrent de nombreuses variables, ce qui peut rendre le modèle trop complexe. De plus, les méthodes d'analyse simples peuvent ne pas fournir suffisamment d'informations lorsqu'il s'agit de problèmes tels que l'identification des facteurs qui affectent la satisfaction des utilisateurs. Pendant ce temps, les méthodes d'apprentissage automatique (Machine Learning/ML) sont généralement plus aptes à gérer et à étudier la relation entre plusieurs variables, en particulier dans les situations où des interactions complexes entre les facteurs peuvent exister. Lors de la pandémie de Covid-19 à l'été 2021, la Ville de Montréal et ses arrondissements ont mis en place 12 projets de rues piétonnes. Le projet pilote « Cohabitation Cyclistes et Pietons (CCP) » a été lancé sur l'avenue du Mont-Royal et la rue Wellington. Dans le cadre de ce projet, la Ville de Mont-Royal souhaitait créer de multiples lieux de promenade et de vélo. Non seulement la Ville de Mont-Royal permet aux gens de rester actifs, mais elle réduit également le risque de propagation de la maladie. La présente recherche visait à évaluer le niveau de satisfaction des piétons et des cyclistes avec leur coexistence mutuelle par les données obtenues à partir de l'enquête CCP. S'appuyant sur la littérature existante, dans la présente étude, des techniques d'apprentissage automatique comprenant à la fois des méthodes de régression et de classification ont été proposées et appliquées pour identifier les facteurs clés influençant les niveaux de satisfaction des utilisateurs.» ABSTRACT: «ABSTRACT: Active transportation modes (walking and cycling) are vital for developing transportation systems that are accessible, safe, and sustainable. To promote active transportation, cities are developing pedestrianized streets and improving walking and cycling environments while prioritizing safety concerns. Numerous studies have been conducted to assess people's satisfaction with various locations, and it is widely recognized that satisfaction is influenced by a broad range of factors. Studies on satisfaction incorporate many variables, which may make the model overly complex. Furthermore, simple analysis methods may not provide enough insight when it comes to problems such as identifying the factors that affect user satisfaction. Meanwhile, Machine Learning (ML) methods are generally more adept at handling and investigating the relationship between multiple variables, particularly in situations where complex interactions between factors may exist. During the Covid-19 pandemic in the summer 2021, the City of Montreal and its boroughs introduced 12 pedestrian street projects. The pilot project called Cohabitation Cyclists et Pietons (CCP) was launched on Mont-Royal Avenue and Wellington Street. As a part of this project, the City of Mont Royal wanted to create multiple places where people could walk and cycle. Not only does the City of Mont Royal allow people to stay active but it also reduces the risk of spreading the disease. The present research aimed to assess the interaction satisfaction of pedestrians and cyclists with their coexistence on pedestrian streets by the data obtained from the CCP survey. Drawing from the existing literature, in the present study, ML techniques including both regression and classification methods were proposed and applied to identify the key factors influencing user satisfaction levels.»
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 | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".