WiDFF-ID: Device-Free Fast Person Identification Using Commodity WiFi

WiFi-based person identification has been made possible by the widespread deployment of WiFi devices. However, most existing methods rely on the person's gait characters, which need several minutes of walking to extract the wireless signature of an individual for training and testing, and thus limit the speed and size of the identification of people. In this work, to address the aforementioned challenges, we propose a novel WiFi-based Device-Free Fast Identification (WiDFF-ID) approach. In particular, we first use RF-based biometrics to derive the personal Channel State Information (CSI) fingerprint. Using such posture information instead of original gait action could effectively enable quick identification for more people. Then a set of methods including data augmentation are employed to process the fused RF-biometric signals to greatly reduce training time and storage resources. In the following, a novel multi-layer deep convolutional neural network is proposed for reusing prior calculated features and uniquely identifying individuals. Finally, we implement WiDFF-ID on commodity off-the-shelf WiFi devices. Experimental results show that the proposed scheme can reach 98% of average identification accuracy with a total of 42 volunteers, implying that the proposed WiDFF-ID can be used in scenarios involving a larger group of people for access authentication.