Abstract:
We compare model-centric and data-centric machine learning (ML) approaches to address the issue of insufficient training data for ML-based failure identification. The res...Show MoreMetadata
Abstract:
We compare model-centric and data-centric machine learning (ML) approaches to address the issue of insufficient training data for ML-based failure identification. The results suggest that a datacentric approach can improve classification accuracy by up to 7.1% on under-represented failures, albeit at a higher computational cost.
Date of Conference: 01-05 October 2023
Date Added to IEEE Xplore: 28 March 2024
Electronic ISBN:978-1-83953-926-8