AINeutralarXiv – CS AI · 10h ago5/10
🧠
Practical Wi-Fi-based Motion Recognition Under Variable Traffic Patterns
Researchers propose a transformer-based neural network (SRV-NN) that enables Wi-Fi sensing systems to recognize human motions and gestures despite variable transmission traffic patterns and sampling rates. The approach uses dynamic sampling rate augmentation to improve generalization, demonstrating enhanced accuracy and stability across inconsistent data conditions compared to traditional fixed-rate methods.