A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911595223842816 |
|---|---|
| author | Chen, Yinsong Yu, Samson S. Muttaqi, Kashem M. |
| author_facet | Chen, Yinsong Yu, Samson S. Muttaqi, Kashem M. |
| contents | Advanced deep learning methods have shown remarkable success in power quality disturbance (PQD) classification. To enhance model transparency, explainable AI (XAI) techniques have been developed to provide instance-specific interpretations of classifier decisions. However, conventional XAI methods yield deterministic explanations, overlooking uncertainty and limiting reliability in safety-critical applications. This paper proposes a Bayesian explanation framework that models explanation uncertainty by generating a relevance attribution distribution for each instance. This method allows experts to select explanations based on confidence percentiles, thereby tailoring interpretability according to specific disturbance types. Extensive experiments on synthetic and real-world power quality datasets demonstrate that the proposed framework improves the transparency and reliability of PQD classifiers through uncertainty-aware explanations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13658 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification Chen, Yinsong Yu, Samson S. Muttaqi, Kashem M. Machine Learning Advanced deep learning methods have shown remarkable success in power quality disturbance (PQD) classification. To enhance model transparency, explainable AI (XAI) techniques have been developed to provide instance-specific interpretations of classifier decisions. However, conventional XAI methods yield deterministic explanations, overlooking uncertainty and limiting reliability in safety-critical applications. This paper proposes a Bayesian explanation framework that models explanation uncertainty by generating a relevance attribution distribution for each instance. This method allows experts to select explanations based on confidence percentiles, thereby tailoring interpretability according to specific disturbance types. Extensive experiments on synthetic and real-world power quality datasets demonstrate that the proposed framework improves the transparency and reliability of PQD classifiers through uncertainty-aware explanations. |
| title | A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.13658 |