Abstract
Wireless indoor positioning systems (IPS) are ever-growing as traditional global positioning systems (GPS) are ineffective due to non-line-of-sight (NLoS) signal propagation. In this paper, we present a novel approach to learning three-dimensional (3D) multipath channel characteristics in a probabilistic manner for providing high performance indoor localization of wireless beacons. The proposed system employs a single triad dipole vector sensor (TDVS) for polarization diversity, a deep learning model deemed the denoising autoencoder to extract unique fingerprints from 3D multipath channel information, and a probabilistic k-nearest-neighbor (PkNN) to exploit the 3D multipath characteristics. The proposed system is the first to exploit 3D multipath channel characteristics for indoor wireless beacon localization via vector sensing methodologies, a software defined radio (SDR) platform, and multipath channel estimation.
Highlights
Localization is an essential procedure needed for mobile wireless communications
The results demonstrate that the optimum placement of the triad dipole vector sensor (TDVS) antenna with the 3D channel state information (CSI) feature approach varied based on the transmitter polarization
The results showed that the presence of interference in only the testing set for traditional 3D CSI method severely degraded the localization performance
Summary
Localization is an essential procedure needed for mobile wireless communications. The deficiency of GPS due to poor signal propagation characteristics in indoor environments leads to the requirement of developing methods for indoor localization. There are two commonalities between all of these developments that conform either to received signal strength (RSS) or channel state information (CSI) based localization, both of which employ machine learning and fingerprinting to obtain location estimates, none of which considers cross-polarized links (i.e., conditions where the transmitter and receiver are not the same polarization). Intel 5300 NIC, realizing a minimal modification to the DeepFi learning protocol via change in the input feature vectors while leveraging a linear array of three antennas [10] Both DeepFi and PhaseFi realized localization errors around 1 m in performance with a restricted Boltzmann machine (RBM), once again with APs positioned in LoS conditions with non-existent documentation on the polarization state of the transmitters and receivers.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
