Understanding Incident Effects on Subway Operations: Clustering Analysis of Severity Patterns
Bibliographic record
Abstract
Incidents pose challenges to the reliable operation of urban rail transit systems. Given the high frequency of subway services, even minor incidents can cause cascading delays across multiple trains. Understanding incident effects is crucial for improving response time and enabling efficient recovery strategies. This study uses operational records from the Montreal subway system to quantify the overall impact of incidents including the number of affected trains and total delay time. The proposed approach involves integrating operational records with incident data to identify the source of delays and subsequent knock-on effects. To recognize distinct propagation patterns among various incident types, K-means clustering is applied to categorize incidents into three clusters. Cluster 1 represents incidents with the lowest impacts, affecting only one direction of a subway line and imposing an average total delay time of 16 min. Cluster 2, which comprises most incidents, causing moderate operational impacts with an average total delay time of 52 min. Cluster 3 includes severe incidents, affecting an average of 26 trains and causing a total delay time of 273 min. Peak hour analysis indicates that morning and evening peak hours have the highest average number of affected trains, emphasizing the impact of peak hours on incident severity. Investigation into the causes of incidents highlights that the most frequent incidents fall into Cluster 2, implying moderate impacts on subway operations. This research provides valuable insights into subway incident management, laying the groundwork for further studies aimed at enhancing the performance of urban rail transit systems during service disruptions.
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 | 0.004 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".