2020/09/06 by Emre Gönültaş, Gönültaş, Emre, Eric Lei +7 · 5 citations
Computer Science · Engineering · #FOS: Computer and information sciences #FOS: Electrical engineering #Indoor and Outdoor Localization Technologies #Information Theory (cs.IT) #Millimeter-Wave Propagation and Modeling #Signal Processing (eess.SP) #Speech and Audio Processing #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2009.02798
openalex publication_date 2020/09/06 · openalex created_date 2022/07/25 · openalex updated_date 2026/07/28
Channel state information (CSI)-based fingerprinting via neural networks\n(NNs) is a promising approach to enable accurate indoor and outdoor positioning\nof user equipments (UEs), even under challenging propagation conditions. In\nthis paper, we propose a positioning pipeline for wireless LAN MIMO-OFDM\nsystems which uses uplink CSI measurements obtained from one or more\nunsynchronized access points (APs). For each AP receiver, novel features are\nfirst extracted from the CSI that are robust to system impairments arising in\nreal-world transceivers. These features are the inputs to a NN that extracts a\nprobability map indicating the likelihood of a UE being at a given grid point.\nThe NN output is then fused across multiple APs to provide a final position\nestimate. We provide experimental results with real-world indoor measurements\nunder line-of-sight (LoS) and non-LoS propagation conditions for an 80MHz\nbandwidth IEEE 802.11ac system using a two-antenna transmit UE and two AP\nreceivers each with four antennas. Our approach is shown to achieve\ncentimeter-level median distance error, an order of magnitude improvement over\na conventional baseline.\n