Tunnel crash severity and congestion duration joint evaluation based on cross-stitch networks

Apr 1, 2025·

Chenzhu Wang

Mohamed Abdel-Aty

Lei Han

· 1 min read

Project DOI DOI

Type

Journal article

Publication

Accident Analysis and Prevention, 213, 107942

This paper sits at the intersection of safety and operations: the model learns shared and task-specific information for injury severity and congestion duration.

Last updated on Apr 26, 2026

Tunnel Safety Multi-Task Learning Congestion Duration

Authors

Chenzhu Wang

Postdoctoral Researcher

← Grouped random parameters Poisson-Lindley model with spatial effects addressing crashes at intersections Jul 1, 2025

LSTM + Transformer real-time crash risk evaluation using traffic flow and risky driving behavior data Nov 1, 2024 →