MILATRAS: MIcrosimulation Learning-based Approach to TRansit ASsignment
Bibliographic record
Abstract
Public transit is considered a cost-effective alternative to mitigate the effects of traffic gridlock through the implementation of innovative service designs, and deploying new smart systems for operations control and traveller information. Public transport planners use transit assignment models to predict passenger loads and levels of service. \n \nExisting transit assignment approaches have limitations in evaluating the effects of information technologies, since they are neither sensitive to the types of information that may be provided to travellers nor to the traveller’s response to that information. Moreover, they are not adequate for evaluating the impacts of Intelligent Transportation Systems (ITS) deployments on service reliability, which in turn affect passengers’ behaviour. \n \nThis dissertation presents an innovative transit assignment framework, namely the MIcrosimulation Learning-based Approach to TRansit ASsignment – MILATRAS. MILATRAS uses learning and adaptation to represent the dynamic feedback of passengers’ trip choices and their adaptation to service performance. Individual passengers adjust their behaviour (i.e. trip choices) according to their experience with the transit system performance. MILATRAS introduces the concept of ‘mental model’ to maintain and distinguish between the individual’s experience with service performance and the information provided about system conditions. \n \nA dynamic transit path choice model is developed using concepts of Markovian Decision Process (MDP) and Reinforcement Learning (RL). It addresses the departure time and path choices with and without information provision. A parameter-calibration procedure using a generic optimization technique (Genetic Algorithms) is also proposed. A proof-of-concept prototype has been implemented; it investigates the impact of different traveller information provision scenarios on departure time and path choices, and network performance. A large-scale application, including parameter calibration, is conducted for the Toronto Transit Commission (TTC) network. \n \nMILATRAS implements a microsimulation, stochastic (nonequilibrium-based) approach for modelling within-day and day-to-day variations in the transit assignment process, where aggregate travel patterns can be extracted from individual choices. MILATRAS addresses many limitations of existing transit assignment models by exploiting methodologies already established in the areas of traffic assignment and travel behaviour modeling. Such approaches include the microsimulation of transportation systems, learning-based algorithms for modelling travel behaviour, agent-based representation for travellers, and the adoption of Geographical Information Systems (GIS). \n \nThis thesis presents a significant step towards the advancement of the modelling for the transit assignment problem by providing a detailed operational specification for an integrated dynamic modelling framework – MILATRAS.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".