基于混合专家的场景自适应持续学习用于基于信道状态信息的人体活动识别
Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts
AI总结：
本文提出了一种基于混合专家的场景自适应持续学习方法，通过注意力机制的语义路由器实现场景特定适应，降低推理成本，实现在多场景下的高效人体活动识别。
摘要：
基于信道状态信息（CSI）的人体活动识别（HAR）在不同物理环境中面临性能退化的问题。持续学习（CL）提供了一种系统的方法，在学习新领域的同时保持过去的知识，但现有的CL解决方案在积累领域时扩展性差，依赖于大型回放缓冲区或导致线性增长的推理成本。在本文中，我们提出了一种场景自适应混合专家（SAMoE-C），将跨域CSI-based HAR建模为混合专家系统，通过注意力机制的语义路由器激活选定的专家。此外，我们开发了一种新的训练协议，仅需要极小的回放缓冲区以稳定路由器的领域辨别能力。实验结果表明，SAMoE-C在四个场景的CSI数据集上实现了接近最先进的准确性，同时保持显著较低的推理成本。通过结合模块化专家、选择性激活与路由器和轻量级训练协议，SAMoE-C实现了在现实世界中可扩展的跨域CSI-based HAR部署，具有低训练开销和高计算效率。
英文摘要：
Channel state information (CSI)-based human activity recognition (HAR) is vulnerable to performance degradation under domain shifts across varying physical environments. Continual learning (CL) offers a principled way to learn new domains sequentially while preserving past knowledge, but existing CL solutions for CSI-based HAR scale poorly with accumulating domains, rely on a large replay buffer, or incur linearly growing inference cost. In this letter, we propose Scene-Adaptive Mixture of Experts with Clustered Specialists (SAMoE-C), which formulates cross-domain CSI-based HAR as a mixture-of-experts system that enables scene-specific adaptation, via an attention-based semantic router that activates only selected experts for each input. Moreover, we develop a novel training protocol, which requires only a tiny replay buffer for stabilizing domain discrimination of the router. Experimental results on a four-scene CSI dataset demonstrate that SAMoE-C approaches the state-of-the-art accuracy, while maintaining a significantly lower inference cost. By jointly combining modular experts, selective activation with router and a lightweight training protocol, SAMoE-C enables scalable cross-domain CSI-based HAR deployment with low training overhead and high computational efficiency in real-world settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
