New neutrosophic ensemble method enhances bearing fault detection uncertainty

Researchers have developed a novel neutrosophic ensemble classification method to improve uncertainty awareness in bearing fault detection. This approach decomposes a Random Forest, XGBoost, and Logistic Regression ensemble into four indicators: top-class evidence, best-competitor evidence, predictive entropy, and decision disagreement. Experiments on laboratory and industrial benchmarks demonstrated that predictive entropy correlates well with errors, offering better insights than traditional confidence scores. The study also found that fusing time-domain and frequency-domain models and scoring their Jensen-Shannon divergence can outperform individual models, especially under distributional shifts. AI

IMPACT This research offers a more nuanced approach to uncertainty quantification in machine learning for industrial diagnostics, potentially improving reliability in critical systems.

RANK_REASON The cluster contains an academic paper detailing a new machine learning methodology and experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• Case Western Reserve University
• CatalyzeX Code Finder for Papers
• DagsHub
• Gotit.pub
• Hugging Face
• Jensen-Shannon divergence
• Jinan University
• logistic regression model
• random forest
• ScienceCast
• XGBoost

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →