4 papers
Evaluating Anomaly Detectors for Simulated Highly Imbalanced Industrial Classification Problems
Lesley Wheat, Martin v. Mohrenschildt, Saeid Habibi
Machine learning offers potential solutions to current issues in industrial systems in areas such as quality control and predictive maintenance, but also faces unique barriers in i…
Rethinking Gaussian-Windowed Wavelets for Damping Identification
Hadi M. Daniali, Martin v. Mohrenschildt
In modal analysis, the prevalent use of Gaussian-based wavelets (such as Morlet and Gabor) for damping estimation is rarely questioned. In this study, we challenge this conventiona…
Bayes Error Rate Estimation in Difficult Situations
Lesley Wheat, Martin v. Mohrenschildt, Saeid Habibi
The Bayes Error Rate (BER) is the fundamental limit on the achievable generalizable classification accuracy of any machine learning model due to inherent uncertainty within the dat…
Correcting Domain Shifts in Electric Motor Vibration Data for Unseen Operating Conditions
Lesley Wheat, Martin v. Mohrenschildt, Saeid Habibi +1
This paper addresses the problem of domain shifts in electric motor vibration data created by new operating conditions in testing scenarios, focusing on bearing fault detection and…