Quantitative Evaluation of xAI Methods for Multivariate Time Series - A Case Study for a CNN-Based MI Detection Model

This paper presents an evaluation framework for xAI methods that is tailored for multivariate time series data. The framework
includes three evaluation approaches encompassing a stability analysis, consistency analysis, and truthfulness analysis. The stability analysis investigates the consistency of explanations provided by a single xAI method for similar inputs. In the truthfulness analysis, the meaningfulness of explanations provided by an xAI method is examined.