Wi-Fi sensing framework WiFuse boosts human activity recognition accuracy

Researchers have developed WiFuse, a novel framework for human activity recognition using Wi-Fi sensing. This dual-stream system fuses denoised time-domain amplitude variations with 2D-FFT-derived Delay-Doppler motion representations. The fused data is processed by a hybrid ResNet-Temporal Convolutional Network (TCN) architecture enhanced with attention mechanisms, achieving up to 95.28% accuracy on the XRF55 dataset and 98.20% on the Wi-MIR dataset. AI

IMPACT This research could lead to more accurate and privacy-preserving human activity recognition systems using readily available Wi-Fi signals.

RANK_REASON The cluster contains a research paper detailing a new technical framework and its experimental results. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Alison Michel Fernandes
• Channel state information
• Human Activity Recognition
• ResNet-Temporal Convolutional Network
• WiFuse
• Wi-MIR
• XRF55

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →