PulseAugur
LIVE 10:53:43
research · [2 sources] ·
0
research

New SAMoE-C method improves CSI-based HAR with scene-adaptive experts

Researchers have developed a new method called Scene-Adaptive Mixture of Experts with Clustered Specialists (SAMoE-C) to improve human activity recognition using channel state information (CSI). This approach addresses performance degradation when CSI-based systems encounter different physical environments by enabling scene-specific adaptation through an attention-based semantic router that activates only relevant experts. The system also utilizes a minimal replay buffer for training stability and significantly reduces inference costs compared to existing continual learning solutions. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Introduces a more scalable and efficient approach for real-world deployment of CSI-based activity recognition systems.

RANK_REASON Academic paper detailing a new method for CSI-based human activity recognition.

Read on arXiv cs.LG →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 · Wenhan Zheng, Yuyi Mao, Ivan Wang-Hei Ho ·

    Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts

    arXiv:2605.06447v1 Announce Type: new Abstract: 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 d…

  2. arXiv cs.LG TIER_1 · Ivan Wang-Hei Ho ·

    Scene-Adaptive Continual Learning for CSI-based Human Activity Recognition with Mixture of Experts

    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 knowle…