发表机构
University of Bologna; University of Napoli Federico II; University of Verona（博洛尼亚大学; 那不勒斯费德里科二世大学; 维罗纳大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
XAI2CSI框架利用XAI的SAGE方法分析DL型CSI感知系统，揭示其过度依赖上下文特定CSI模式导致跨场景泛化差的问题，为开发鲁棒Wi-Fi感知系统提供参考。
AI 中文摘要
Wi-Fi信道状态信息（CSI）已成为实现无设备人体活动识别（HAR）的关键支撑技术，可利用现有通信基础设施实现低成本、非侵入式感知。然而，基于CSI数据训练的深度学习（DL）模型由于无线传播的上下文敏感性，往往难以在不同用户、环境和设备设置间实现泛化。尽管存在这一挑战，针对模型决策及泛化失败的理解却未得到足够关注。本文提出XAI2CSI框架，该框架利用可解释人工智能（XAI）分析基于DL的CSI感知系统。XAI2CSI采用模型不可知的可解释性方法SAGE，量化在IEEE 802.11ax数据的标称及跨上下文评估下，CSI的时域、频域和空间分量对HAR决策的贡献。分析表明，所考虑的DL模型因过度依赖上下文特定的CSI模式，对未知条件的鲁棒性有限，当部署条件变化时，会导致模型误判底层信号动态。所提出的方法及发现为探索替代解决方案、指导开发鲁棒且透明的Wi-Fi感知系统提供了参考框架。
英文摘要
Wi-Fi Channel State Information (CSI) has emerged as a key enabler for device-free Human Activity Recognition (HAR), enabling low-cost, unobtrusive sensing using existing communication infrastructure. However, Deep Learning (DL) models trained on CSI data often struggle to generalize across users, environments, and device setups due to the context sensitivity of wireless propagation. Despite this challenge, limited attention has been devoted to understanding model decisions and generalization failures. This paper introduces XAI2CSI, a framework that leverages eXplainable Artificial Intelligence (XAI) to analyze DL-based CSI sensing systems. XAI2CSI employs SAGE, a model-agnostic explainability method, to quantify temporal, spectral, and spatial CSI contributions to HAR decisions under nominal and cross-context evaluations on IEEE 802.11ax data. Our analysis reveals that the considered DL model exhibits limited robustness to unseen conditions due to an over-reliance on context-specific CSI patterns, causing models to misinterpret the underlying signal dynamics when deployment conditions change. The proposed methodology and findings provide a reference framework to explore alternative solutions and guide the development of robust, transparent Wi-Fi sensing systems.
Commentsaccepted at 22nd International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob 26)
