Predicting Accident Severity on Taiwan Highways Using Machine Learning and Electronic Toll Collection (ETC) Data
Bibliographic record
Abstract
This study aims to develop a machine learning‐based framework for predicting the severity of highway traffic accidents by leveraging high‐resolution data from Taiwan’s Electronic Toll Collection (ETC) system. Unlike traditional accident‐reporting systems, the ETC infrastructure provides a uniquely comprehensive and precise dataset that captures spatiotemporal traffic patterns and environmental conditions across the national highway network. This rich dataset enabled the integration of data mining and data visualization techniques to uncover nontypical contributing factors to accident severity. Feature engineering was conducted using random forest and LASSO regression, while extreme gradient boosting and the Apriori algorithm were employed to identify key associations between accident severity and contextual variables. Based on human factor and traffic psychology theory, influential factors include poor lighting at night, adverse weather conditions, late‐night hours (20:00–06:00), specific geographic regions (e.g., Yilan County), speed limits of 100 km/h, and vehicle types such as taxis and large trucks. The findings not only enhance the understanding of environmental influences on accident outcomes but also offer actionable insights for improving highway safety. Moreover, Taiwan’s ETC system serves as a model for countries seeking to integrate tolling infrastructure with traffic safety analytics.
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) | 0.000 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 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".