Explaining Human Activity Recognition with SHAP: Validating Insights with Perturbation and Quantitative Measures
arXiv:2411.03714 · doi:10.1016/j.compbiomed.2025.109838
Abstract
In Human Activity Recognition (HAR), understanding the intricacy of body movements within high-risk applications is essential. This study uses SHapley Additive exPlanations (SHAP) to explain the decision-making process of Graph Convolution Networks (GCNs) when classifying activities with skeleton data. We employ SHAP to explain two real-world datasets: one for cerebral palsy (CP) classification and the widely used NTU RGB+D 60 action recognition dataset. To test the explanation, we introduce a novel perturbation approach that modifies the model's edge importance matrix, allowing us to evaluate the impact of specific body key points on prediction outcomes. To assess the fidelity of our explanations, we employ informed perturbation, targeting body key points identified as important by SHAP and comparing them against random perturbation as a control condition. This perturbation enables a judgment on whether the body key points are truly influential or non-influential based on the SHAP values. Results on both datasets show that body key points identified as important through SHAP have the largest influence on the accuracy, specificity, and sensitivity metrics. Our findings highlight that SHAP can provide granular insights into the input feature contribution to the prediction outcome of GCNs in HAR tasks. This demonstrates the potential for more interpretable and trustworthy models in high-stakes applications like healthcare or rehabilitation.
Published in Computers in Biology and Medicine
References in corpus (13)
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- Towards A Rigorous Science of Interpretable Machine Learning
- The Kinetics Human Action Video Dataset
- A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
- All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
- From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
- A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?
- OpenXAI: Towards a Transparent Evaluation of Model Explanations
- Towards falsifiable interpretability research
- AutoGCN -- Towards Generic Human Activity Recognition with Neural Architecture Search
- Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective
- A Survey on Human Action Recognition