RSSI Fingerprinting-based Localization Using Machine Learning in LoRa Networks

TL;DR

This paper investigates machine learning-based RSSI fingerprinting for localization in LoRa networks, demonstrating its potential for accurate indoor and outdoor tracking in smart city applications.

Contribution

It introduces a novel approach using machine learning models for RSSI-based localization in LoRa networks and evaluates its accuracy compared to other wireless technologies.

Findings

Machine learning models achieve promising localization accuracy in LoRa networks.

LoRa-based positioning outperforms ZigBee, WiFi, and Bluetooth in certain scenarios.

Challenges include satellite-independent tracking and deployment feasibility.

Abstract

The scale of wireless technologies penetration in our daily lives, primarily triggered by the Internet-of-things (IoT)-based smart cities, is beaconing the possibilities of novel localization and tracking techniques. Recently, low-power wide-area network (LPWAN) technologies have emerged as a solution to offer scalable wireless connectivity for smart city applications. LoRa is one such technology that provides energy efficiency and wide-area coverage. This article explores the use of intelligent machine learning techniques, such as support vector machines, spline models, decision trees, and ensemble learning, for received signal strength indicator (RSSI)-based ranging in LoRa networks, on a training dataset collected in two different environments: indoors and outdoors. The suitable ranging model is then used to experimentally evaluate the accuracy of localization and tracking using trilateration in the studied environments. Later, we present the accuracy of LoRa-based positioning system (LPS) and compare it with the existing ZigBee, WiFi, and Bluetooth-based solutions. In the end, we discuss the challenges of satellite-independent tracking systems and propose future directions to improve accuracy and provide deployment feasibility.