AI system analyzes multi-modal data for railway crossing safety

Researchers have developed an AI system to assess the safety of railway crossings by analyzing multi-modal data. The system combines visual cues from images with structured data, such as accident history, to provide safety scores. In a proof-of-concept, the pipeline achieved a macro F1 score of 0.757 for identifying high-risk and low-risk crossings and an RMSE of 0.078 for estimating Federal Railroad Administration (FRA)-based safety scores. AI

IMPACT Could improve public safety by enabling more accurate risk assessment of railway crossings.

RANK_REASON Academic paper detailing a new AI system and its performance metrics. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• CORE Recommender
• DagsHub
• Federal Railroad Administration
• Gotit.pub
• Hugging Face
• IArxiv Recommender
• Influence Flower
• Nícolas Roque dos Santos
• ScienceCast

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →