Open access
2026
Low-Data Cross-Environment Transfer Learning for Wi-Fi CSI-Based Human Activity Recognition: An Inductive Bias Perspective
A cross-environment transfer learning framework for CSI-based HAR that integrates CSI preprocessing, adaptive amplitude-phase fusion via TinyGate, an R(2+1)D backbone, and two temporal modeling strategies, namely Bidirectional Long Short-Term Memory (Bi-LSTM) and Transformer is proposed.
Parma Hadi Rantelinggi, Mondher Bouazizi, Tomoaki Ohtsuki
· IEEE Access · 0 citations