Using Multi-agent Geo-simulation Techniques for the Detection of Risky Areas for Trains
Bibliographic record
Abstract
A transportation system is spatially and functionally distributed; its subsystems have a high degree of autonomy and are in constant interaction with each other and with the surrounding geographic environment. Modeling and simulating such systems in large-scale geographic spaces is a complex process. In this paper we address the domain of railway systems, and more particularly the problem of detecting risky areas along railroads. This requires that we consider a variety of static and dynamic variables, including train characteristics, hazardous events (e.g. rock-falls), and the properties of the large-scale geographic environment, as well as weather conditions. This simulation enables us to recommend speed limits in risky areas while taking into account all of the aforementioned factors. Since statistical and analytical models are not appropriate to represent such a complex process in which spatial constraints are of high importance, we adopted a multi-agent geo-simulation (MAGS) approach that facilitates the simulation of complex systems in large-scale geo-referenced environments. In this paper, we present Train-MAGS, an agent-based geo-simulation tool that simulates train behaviors in risky areas in large-scale virtual geographic environments. We also demonstrate how risky areas can be detected in real time using an agent-based approach. This work also illustrates how the application of artificial intelligence techniques, such as the MAGS approach, provides interesting perspectives of realistic and plausible simulations aimed at improving the functioning, the efficiency, and the safety of the transportation systems.
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 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".