Room-Level Localization System Based on LoRa Backscatters

The aim of this paper is to propose a novel room-level localization approach to locate LoRa backscatter devices, which can be easily embedded into wearable devices or smartphones. The advantages of this system lie in its series of low-cost, low-power, low-complexity and long-range features. LoRa bac...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2021, Vol.9, p.16004-16018
Main Authors: Lazaro, Antonio, Lazaro, Marc, Villarino, Ramon
Format: Article
Language:English
Subjects:
Backscatter
Backscatter communications
Backscattering
Discriminant analysis
Frequency shift
Internet of Things (IoT)
Localization
Location awareness
LoRa
Machine learning
Microcontrollers
Modulation
Received signal strength indicator
Receivers
RFID
Signal strength
Wearable technology
Wireless fidelity
wireless sensor networks
zero-power sensor
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The aim of this paper is to propose a novel room-level localization approach to locate LoRa backscatter devices, which can be easily embedded into wearable devices or smartphones. The advantages of this system lie in its series of low-cost, low-power, low-complexity and long-range features. LoRa backscattering operates by alternatively connecting an antenna, through a switch, to two loads with high reflection coefficients and opposite phase. The result is a frequency shift of the LoRa incident signal equal to the backscatter switching frequency. The localization system comprises several LoRa receivers distributed among the rooms, a LoRa transmitter located at a central point and the backscatter device, which is carried or worn by a subject. The position of the LoRa backscatter device can be determined by comparing the received signal strength between all receivers. In order to improve the accuracy of the system, different machine learning classifiers were compared. System performance was tested in a real-life scenario, achieving an accuracy up to 89.7% using linear discriminant analysis (LDA).
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2021.3053144