# A Reproducible Comparison of RSSI Fingerprinting Localization Methods Using LoRaWAN

## TL;DR

This paper compares different machine learning methods for LoRaWAN RSSI fingerprinting localization, demonstrating that neural networks achieve the highest accuracy with a mean error of 358 meters.

## Contribution

It provides a reproducible evaluation framework for localization methods using LoRaWAN RSSI data, including code and dataset splits.

## Key findings

- Neural networks outperform other methods in accuracy.
- Reproducible code and dataset splits are provided.
- Mean localization error is 358 meters.

## Abstract

The use of fingerprinting localization techniques in outdoor IoT settings has started to gain popularity over the recent years. Communication signals of Low Power Wide Area Networks (LPWAN), such as LoRaWAN, are used to estimate the location of low power mobile devices. In this study, a publicly available dataset of LoRaWAN RSSI measurements is utilized to compare different machine learning methods and their accuracy in producing location estimates. The tested methods are: the k Nearest Neighbours method, the Extra Trees method and a neural network approach using a Multilayer Perceptron. To facilitate the reproducibility of tests and the comparability of results, the code and the train/validation/test split of the dataset used in this study have become available. The neural network approach was the method with the highest accuracy, achieving a mean error of 358 meters and a median error of 204 meters.