🧪 Test?View on arXiv
Neutrosophic Ensemble Classification for Uncertainty-Aware Bearing Fault Detection: Evidence from Laboratory and Variable-Speed Industrial Benchmarks
Not provided in the abstract
ensemble learningfault detectionuncertainty quantification
2610.06880
Builder Relevance
1h ago70%
Abstract
This paper presents a refined neutrosophic decomposition of an ensemble classifier for bearing fault detection, addressing the conflation of confident errors and ambiguous predictions.
Reality Card
Core Claim
The ensemble classifier achieves 100.00% accuracy on three of four loads in the CWRU benchmark after correcting a mapping error, demonstrating effective fault detection.
Method / Result
Achieved 100.00% accuracy on three of four held-out loads in the CWRU benchmark.
Limitations
The accuracy on the JNU benchmark collapsed to 40.64%, indicating potential generalization issues.
Paper to code
Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.
No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.