Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures

This study uses SHapley Additive exPlanations (SHAP) to explain the decision-making process of Graph Convolution Networks (GCNs) when classifying activities with skeleton data and highlights that SHAP can provide granular insights into the input feature contribution to the prediction outcome of GCNs in HAR tasks.