arXiv subjects

Saeid Habibi

Publications and source records attributed to Saeid Habibi.

3 recordsLinked to original sources

arXiv2025

Evaluating Anomaly Detectors for Simulated Highly Imbalanced Industrial Classification Problems

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 industrial applications. An ongoing challenge is extreme class imbalance, primarily due to the limited availability of faulty data during training. This paper presents a comprehensive evaluation of anomaly detection algorithms using a problem-agnostic simulated dataset that reflects real-world engineering constraints. Using a synthetic dataset with a hyper-spherical based anomaly distribution in 2D and 10D, we benchmark 14 detectors across training datasets with anomaly rates between 0.05% and 20% and training sizes between 1 000 and 10 000 (with a testing dataset size of 40 000) to assess performance and generalization error. Our findings reveal that the best detector is highly dependant on the total number of faulty examples in the training dataset, with additional healthy examples offering insignificant benefits in most cases. With less than 20 faulty examples, unsupervised methods (kNN/LOF) dominate; but around 30-50 faulty examples, semi-supervised (XGBOD) and supervised (SVM/CatBoost) detectors, we see large performance increases. While semi-supervised methods do not show significant benefits with only two features, the improvements are evident at ten features. The study highlights the performance drop on generalization of anomaly detection methods on smaller datasets, and provides practical insights for deploying anomaly detection in industrial environments.

cs.LG↗

arXiv2025

Bayes Error Rate Estimation in Difficult Situations

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 data. BER estimators offer insight into the difficulty of any classification problem and set expectations for optimal classification performance. In order to be useful, the estimators must also be accurate with a limited number of samples on multivariate problems with unknown class distributions. To determine which estimators meet the minimum requirements for "usefulness", an in-depth examination of their accuracy is conducted using Monte Carlo simulations with synthetic data in order to obtain their confidence bounds for binary classification. To examine the usability of the estimators for real-world applications, new non-linear multi-modal test scenarios are introduced. In each scenario, 2500 Monte Carlo simulations per scenario are run over a wide range of BER values. In a comparison of k-Nearest Neighbor (kNN), Generalized Henze-Penrose (GHP) divergence and Kernel Density Estimation (KDE) techniques, results show that kNN is overwhelmingly the more accurate non-parametric estimator. In order to reach the target of an under 5% range for the 95% confidence bounds, the minimum number of required samples per class is 1000. As more features are added, more samples are needed, so that 2500 samples per class are required at only 4 features. Other estimators do become more accurate than kNN as more features are added, but continuously fail to meet the target range.

cs.LG↗

arXiv2025

Correcting Domain Shifts in Electric Motor Vibration Data for Unseen Operating Conditions

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 diagnosis (FDD). The proposed method combines the Harmonic Feature Space (HFS) with regression to correct for frequency and energy differentials in steady-state data, enabling accurate FDD on unseen operating conditions within the range of the training conditions. The HFS aligns harmonics across different operating frequencies, while regression compensates for energy variations, preserving the relative magnitude of vibrations critical for fault detection. The proposed approach is evaluated on a detection problem using experimental data from a Belt-Starter Generator (BSG) electric motor, with test conditions having a minimum 1000 RPM and 5 Nm difference from training conditions. Results demonstrate that the method outperforms traditional analysis techniques, achieving high classification accuracy at a 94% detection rate and effectively reducing domain shifts. The approach is computationally efficient, requires only healthy data for training, and is well-suited for real-world applications where the exact application operating conditions cannot be predetermined.

eess.SP↗