An Automated Framework for Lane Closure Detection on Highway Using Connected Vehicle Data and Machine Learning Models
Bibliographic record
Abstract
Lane closures on highways present significant challenges, including traffic disruptions, increased crash risks, and economic losses. The traditional methods, which use primarily manual reporting or sensor‐based methods, can be error‐prone, inefficient, and costly. This study introduces an innovative real‐time lane closure detection approach using connected vehicle (CV) data and machine learning techniques. Our methodology analyzes CV data metrics such as speed variations and lateral waypoint positioning relative to road reference lines, comparing these across road segments with and without closures. We employ two machine learning models—support vector machines (SVMs) and k‐nearest neighbors (K‐NN)—trained on features extracted from these metrics to detect lane closures and provide insights into location and time of start and end. This research was extended to encompass the entire state of Iowa, utilizing annual data to comprehensively assess lane closure detection capabilities across diverse geographical and traffic conditions, demonstrating its potential for scalability and broader implementation. Challenges encountered during state‐wide implementation were addressed, proposing practical solutions to mitigate them. A visual dashboard was also developed to validate the models’ accuracy in detecting lane closures, aiding informed decision‐making by DOT officials and other stakeholders. Our research highlights potential applications, including scalable solutions for accurate lane closure detection, driver alerts in connected cars, crash risk analysis, and support for naturalistic driving studies in lane closures. This data‐driven method offers a cost‐effective, real‐time alternative to conventional detection methods. By advancing lane closure detection methods, this paper contributes to enhancing road safety and optimizing traffic management and catalyzes the evolution of autonomous vehicle technologies within modern 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 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".