Poster abstract: Implications of target diversity for organic device-free localization

Abstract

Device-free localization (DFL) plays an important role in many applications, such as the intrusion detection. Most traditional DFL systems assume a fixed distribution of the received signal strength (RSS) changes even they are distorted by different types of targets. It inevitably causes the localization to fail if the targets for modeling and testing belong to different categories. We propose a transferring scheme for DFL, which employs a rigorously designed transferring function to transfer the distorted RSS changes across different categories of targets into a latent feature space, where the distributions of the distorted RSS changes from different categories of targets are unified. A benefit of this approach is that the same transferred localization models can be shared by different categories of targets, leading to a substantial reduction of the human efforts. The results of experiments illustrate the efficacy of our transferring scheme.