Abstract
Device-free localization (DFL) locates targets without equipping with wireless devices or tag under the Internet-of-Things (IoT) architectures. As an emerging technology, DFL has spawned extensive applications in the IoT environment, such as intrusion detection, mobile robot localization, and location-based services. Current DFL-related machine learning (ML) algorithms still suffer from low localization accuracy and weak dependability/robustness because the group structure has not been considered in their location estimation, which leads to an undependable process. To overcome these challenges, we propose in this work a dependable block-sparse scheme by particularly considering the group structure of signals. An accurate and robust ML algorithm named block-sparse coding with the proximal operator (BSCPO) is proposed for DFL. In addition, a severe Gaussian noise is added in the original sensing signals for preserving network-related privacy as well as improving the dependability of the model. The real-world data-driven experimental results show that the proposed BSCPO achieves robust localization and signal-recovery performance even under severely noisy conditions and outperforms state-of-the-art DFL methods. For single-target localization, BSCPO retains high accuracy when the signal-to-noise ratio exceeds −10 dB. BSCPO is also able to localize accurately under most multitarget localization test cases.
Highlights
W ITH the continuous deployment of wireless networks [1], e.g., WiFi, fifth-generation communications (5G), and satellite communications, people will inevitably be covered by wireless signals wherever they are located
In practical cases, one can assume that the number of locations of targets is far fewer than the number of all the grids of a detection area, the localization problem can be further transformed into a classical sparse representation classification (SRC) problem, which can be well solved by the machine-learning algorithm, sparse coding
Through a review of the recent literature, we find that, to accurately locate targets, the previous studies have proposed many schemes, such as deep neural networks (DNNs) [18], KNN [11], radio tomographic imaging (RTI) [19], etc., using the received signal strength (RSS) or the channel state information (CSI) signal [20]– [22]
Summary
W ITH the continuous deployment of wireless networks [1], e.g., WiFi, fifth-generation communications (5G), and satellite communications, people will inevitably be covered by wireless signals wherever they are located. Because sensor nodes generate data with a specific pattern that is associated with a specific target’s position and that differs from others, the pattern information can be used for localization. From this perspective, previous studies transformed the localization problem into the classification problem [8]–[10]. In practical cases, one can assume that the number of locations of targets is far fewer than the number of all the grids of a detection area, the localization problem can be further transformed into a classical sparse representation classification (SRC) problem, which can be well solved by the machine-learning algorithm, sparse coding.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
