Decoding pedestrian severity at crosswalks using hybrid clustering and random parameter models
Swastika Barua, Michael Starewich, Tausif Islam Chowdhury, Amir Rafe, Subasish Das · 2026
Read Decoding pedestrian severity at crosswalks using hybrid clustering and random parameter models by Swastika Barua, Michael Starewich, Tausif Islam Chowdhury, Amir Rafe, Subasish Das (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/pmc-13473592.txt.
Description
Swastika Barua and four colleagues analysed in 2026 why some pedestrian crashes at crosswalks turn severe, using Texas crash records from 2017 to 2022. Crosswalk crashes cause a disproportionate share of serious injuries and deaths, yet a single model for all crashes may hide how risk works. The team first used cluster correspondence analysis to sort crashes into three environments, then fitted separate severity models within each cluster.
The three settings were intersection crashes tied to turning drivers violating right of way, and low-speed yield-phase crashes at intersections that damaged property only. Distraction-related crashes saw vehicles leave driveways away from intersections. Weather, lighting, road type, speed limits, and inattentive driving all shaped severity, but their effects shifted across clusters, with daylight and undivided roads showing wide unexplained variation. The authors argue for context-specific countermeasures, since one uniform fix cannot fit three different crash worlds.
Catalog record
| CREATOR | Swastika Barua, Michael Starewich, Tausif Islam Chowdhury, Amir Rafe, Subasish Das |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 96 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |