Machine Learning approaches for freight train safety monitoring

• Research unit: INNOSUISSE
• Project number: 14586.2 PFES-ES

Short description (German)

Machine Learning approaches for freight train safety monitoring

Short description (English)

Machine Learning approaches for freight train safety monitoring

Abstract (German)

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 (English)

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.