Integrating survival analysis and machine learning for modeling overtaking duration on rural two-lane highways

Chuanhe Shi, Shuai Fu, Yuanchang Zhao, Jing He, Peng Ye, Wenchen Yang · 2026

Read Integrating survival analysis and machine learning for modeling overtaking duration on rural two-lane highways by Chuanhe Shi, Shuai Fu, Yuanchang Zhao, Jing He, Peng Ye, Wenchen Yang (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-0357092.txt.

Description

Chuanhe Shi and colleagues film overtaking on rural mountain two-lane roads with drones, then model how long each pass takes. Long passes mean long exposure to oncoming traffic, a core crash risk, yet mountain data were scarce. From flight videos the team extracted full vehicle paths. Unfinished passes counted as cut-off records. They fit a classic timing model and a forest model that handles such cut-off data.

Passes lasted about ten seconds on average in their footage. The forest model sorted completion times better than the classic model. Readable importance scores named the top factors. They were the passing car's starting speed, its sideways gap, and the speed gap. Speed effects curved rather than running straight. Shi and colleagues offer the results for road design and driver warning systems.

Catalog record

CREATORChuanhe Shi, Shuai Fu, Yuanchang Zhao, Jing He, Peng Ye, Wenchen Yang
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE47152
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0357092

Browse the full library · About the Tower of Babel