GNN-XAR: A Graph Neural Network for Explainable Activity Recognition in Smart Homes

2025-02-25

AI Summary

Sensor-based human activity recognition (HAR) in smart homes faces a critical challenge: while graph neural networks (GNNs) achieve high accuracy, their lack of interpretability hinders deployment in high-stakes, trust-critical domains such as healthcare. Method: This paper proposes the first explainable GNN architecture for HAR, modeling sensor time-series data as dynamic heterogeneous graphs and integrating GNNs with causality-driven eXplainable AI (XAI) mechanisms to jointly deliver accurate predictions and human-understandable decision rationales. Contribution/Results: Evaluated on two benchmark public HAR datasets, our method achieves marginal gains in classification accuracy while significantly outperforming state-of-the-art approaches in explanation quality—specifically in fidelity, consistency, and readability. By bridging performance and transparency, it establishes a novel paradigm for trustworthy intelligent home health monitoring.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Reasoning under Uncertainty: Graphical Models
• Knowledge Representation and Reasoning: Common-Sense Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Sensor-based Human Activity Recognition (HAR) in smart home environments is crucial for several applications, especially in the healthcare domain. The majority of the existing approaches leverage deep learning models. While these approaches are effective, the rationale behind their outputs is opaque. Recently, eXplainable Artificial Intelligence (XAI) approaches emerged to provide intuitive explanations to the output of HAR models. To the best of our knowledge, these approaches leverage classic deep models like CNNs or RNNs. Recently, Graph Neural Networks (GNNs) proved to be effective for sensor-based HAR. However, existing approaches are not designed with explainability in mind. In this work, we propose the first explainable Graph Neural Network explicitly designed for smart home HAR. Our results on two public datasets show that this approach provides better explanations than state-of-the-art methods while also slightly improving the recognition rate.

Problem

• Explainable Graph Neural Network
• Smart Home Activity Recognition
• Improved Recognition and Explanation

Innovation

• Explainable Graph Neural Network
• Smart Home Activity Recognition
• Improved Explanation and Accuracy