A Bayesian Framework for Uncertainty-Aware Explanations in Power Quality Disturbance Classification

TL;DR

This paper introduces a Bayesian explanation framework for power quality disturbance classification that models uncertainty in explanations, improving transparency and reliability in safety-critical applications.

Contribution

It presents a novel Bayesian approach to generate uncertainty-aware explanations, enabling tailored interpretability for different disturbance types.

Findings

Enhances explanation reliability by modeling uncertainty.

Improves transparency of PQD classifiers with confidence-based explanations.

Demonstrates effectiveness on synthetic and real-world datasets.

Abstract

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.