Machine Learning approaches for freight train safety monitoring

• Forschungsstelle: INNOSUISSE
• Projektnummer: 14586.2 PFES-ES
• Projekttitel Englisch: Machine Learning approaches for freight train safety monitoring

Kurzbeschreibung (Deutsch)

Machine Learning approaches for freight train safety monitoring

Kurzbeschreibung (Englisch)

Machine Learning approaches for freight train safety monitoring

Abstract (Deutsch)

The proposed project aims to provide a method for safety monitoring of trains in the SBB network. It focuses on automatically identifying wheel defects on freight trains based on the existing SBB infrastructure.|The method is expected to provide within-class and overall wheel defect rankings. This goal involves adapting and extending current machine learning methods such as multiple instance learning, semi-supervised classification and simultaneous regression and ranking.

Abstract (Englisch)

The proposed project aims to provide a method for safety monitoring of trains in the SBB network. It focuses on automatically identifying wheel defects on freight trains based on the existing SBB infrastructure.|The method is expected to provide within-class and overall wheel defect rankings. This goal involves adapting and extending current machine learning methods such as multiple instance learning, semi-supervised classification and simultaneous regression and ranking.