Deep learning creates realistic wireless signals for better model training
A Deep Generative Model for Synthesizing Labeled Wireless Signals
Artificial Intelligence
Summary
It is hard and expensive to collect real wireless signals for use in teaching computers to understand wireless environments. The authors created a new AI method called IIns-GAN that can make fake wireless signals that still behave like real ones. These generated signals change depending on the environment, making them useful for training systems that estimate distance or identify places. Tests show the new method makes signals that closely match real measurements and help improve wireless sensing tasks.
wireless signalsgenerative adversarial networksdeep learningUltra-Wideband (UWB)signal synthesismodel trainingdistance estimationenvironment identificationdata labelingwireless sensing
Authors
Yuxiao Li, Keke Hu, Santiago Mazuelas, Yuan Shen
Abstract
Wireless signals with position-related labels are pivotal for both performance evaluation and model training in the realm of wireless sensing. However, acquiring real-world datasets is often challenged by significant measurement and labeling costs. Traditional methods for synthesizing labeled wireless signals typically rely on environmental models, leading to extensive hyper-parameter tuning and inadequate realism for comprehensive model training purposes. To address these limitations, we introduce a novel deep learning (DL)-based method, namely Inter-Instance Generative Adversarial Networks (IIns-GAN), to generate realistic labeled wireless signals. The generated signals are particularly adaptive to different environment scenarios and well-suited for various model training tasks, including distance estimation and environment identification. We have conducted extensive experiments on public Ultra-Wideband (UWB) datasets to evaluate the realism and utility of the generated signals. The results demonstrate that the signals generated by IIns-GAN mirror the physical characteristics of real-world measurements, and significantly contribute to the improvement of model training in diverse wireless sensing tasks.