Two-dimensional ETTC–labeled longitudinal and lateral conflicts for interpretable real-time crash risk prediction in freeway interchange diverging areas

Feng Tang, Rui Wu, Zhizhen Liu, Shiyu Zhong · 2026

Read Two-dimensional ETTC–labeled longitudinal and lateral conflicts for interpretable real-time crash risk prediction in freeway interchange diverging areas by Feng Tang, Rui Wu, Zhizhen Liu, Shiyu Zhong (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0344623.txt.

Description

Feng Tang and colleagues predict crash risk at freeway exits. Their traffic safety study appeared in PLOS ONE in 2026. They studied twelve exit zones on two Chinese freeways. Cameras and image software pulled dozens of motion measures from video. The team tagged near-conflicts between cars, both behind and beside each other. Warnings were built in thirty-second blocks.

Four learning models were tested. The boosted-tree model did best. A tool that explains each warning ranked the top risk factors. Side conflicts lasted longer than rear ones. They also carried higher risk. Bad conflicts clustered within two hundred meters of the exit. Designers now know the exact stretch to fix first.

Catalog record

CREATORFeng Tang, Rui Wu, Zhizhen Liu, Shiyu Zhong
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE93999
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0344623

Browse the full library · About the Tower of Babel