Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a Bayesian XAI framework for power quality disturbance (PQD) classification that quantifies explanation uncertainty by generating a distribution of relevance attributions for each instance. This allows users to select explanations based on confidence levels, improving the reliability of interpretations in safety-critical applications. Experiments on synthetic and real-world PQD datasets demonstrate the framework's ability to enhance transparency and reliability by providing uncertainty-aware explanations.
Quantifying uncertainty in XAI explanations lets you choose interpretations with a desired confidence level, making AI more reliable in high-stakes power grid applications.
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.