Abstract
Wi-Fi fingerprinting-based indoor localization has received increased attention due to its proven accuracy and global availability. The common received-signal-strength-based (RSS) fingerprinting presents performance degradation due to well-known signal fluctuations, but more recently, the more stable channel state information (CSI) has gained popularity. In this paper, we present SDR-Fi, the first reported Wi-Fi software-defined radio (SDR) receiver for indoor positioning using CSI measurements as features for deep learning (DL) classification. The CSI measurements are obtained from a fast-prototyping LabVIEW-based 802.11n SDR receiver platform. SDR-Fi measures CSI data passively from pilot beacon frames from a single access point (AP) at almost 10 Hz rate. A feed-forward neural network and a 1D convolutional neural network are examined to estimate location accuracy in representative testing scenarios for an indoor cluttered laboratory area, and an adjacent, covered outdoor area. The proposed DL classification methods leverage CSI-based fingerprinting for low AP scenarios, as opposed to traditional RSS-based systems, which require many APs for reliable positioning. Demonstration results are threefold: (a) A fast-prototyping SDR platform that passively extracts CSI measurements from Wi-Fi beacon frames, providing a genuine possibility for vendor network cards to provide such measurements, (b) two state-of-the-art DL classification methods outperforming traditional RSS-based methods for low AP scenarios, (c) a testing methodology for performance evaluation of the proposed indoor positioning system.
Highlights
Location-based services and navigation have become ubiquitous in the mobile computing era
We explore state-of-the-art deep learning (DL) methods on variants of channel state information (CSI) measurements obtained from software-defined radio (SDR)-Fi
WORK This paper presents SDR-Fi, a fast-prototyping SDR receiver capable of extracting RSS and CSI measurements passively from wireless local area network (WLAN) orthogonal frequency-division multiplexing-based (OFDM)-based beacon frames for an indoor positioning system (IPS)
Summary
Location-based services and navigation have become ubiquitous in the mobile computing era. The contributions of this paper are summarized as follows: (a) the first to propose a real-time WLAN OFDM-based SDR receiver that obtains CSI measurements in passive mode, i.e., beacon frame acquisition without dedicated connection, and without modifications to the WLAN infrastructure; (b) exploration of two state-of-the-art CSI-based DL methods with said SDR passive measurements for a single AP scenario; and (c) a testing methodology for performance evaluation of the proposed IPS. An SDR in [28] is proposed by using two USRP units synchronized by a clock and using similar OFDM symbol structure as the WLAN standard They collected 52 SCs and applied a 1D CNN as in this work. The proposed single-antenna SDR mimics legacy OFDM-based NICs that are capable of passively listening for available networks and decoding non-HT beacon frames. With sleep-mode, the receiver achieves real-time packet collection rates up to 9.5 Hz, which is close to the theoretical maximum of 9.76 Hz [17]
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
