A Data Augmentation-Based Method for Robust Device-Free Localization in Changing Environments of Passive Radio Frequency Identification System

Abstract

Device-free localization (DFL) is playing a critical role in many applications which do not require any device attached to the target. Because of environmental changes, the fingerprint database established in the original environments is unable to remain effective when used in the changing environments. Looking at dropout as a prior-knowledge-free data augmentation operation, we propose a convolutional denoising autoencoder (DAE)-based DFL architecture AugRF. Our method combines the merits of the convolutional neural network and the DAE in which convolutional operation is beneficial to feature extraction and dropout operation is equivalent to generating augmented versions of the training data. It is noted that our method can improve the localization performance in changed environments without resampling and retraining processes. Simulations and real-world experiments verify the superiority of the proposed architecture. Our localization system can be implemented with a commercial ultrahigh-frequency radio frequency identification system. When the signal-to-noise ratio of the fingerprint data drops significantly due to environmental changes, AugRF contributes to improving localization accuracy. In addition, the time cost for one positioning meets the requirement of real-time indoor localization.