Our paper "A Reproducible Comparison of RSSI Fingerprinting Localization Methods Using LoRaWAN" was presented by Grigorios Anagnostopoulos, in the 16th IEEE Workshop on Positioning, Navigation and Communications (WPNC 2019), in Bremen, Germany. The scope of the WPNC contributions this year ranged from IoT and 5G positioning, to autonomous car localisation using LiDAR descriptors. The strive for more transparent and reproducible research in the field, which Greg promotes in his paper, was well appreciated by the community.
The paper characterises the achievable accuracy of LoRaWAN localisation with the use of RSSI fingerprinting methods in a large scale urban environment. It compares the classical k-nearest neighbour method to extra trees and feed-forward neural network using a solid and well-documented experimental protocal. The primary aim of the paper is to contribute to the field with a reproducible study, that other researchers can refer to when evaluating the performance of various localization systems. The hope is that such regular and consistent comparisons will bring more transparency into the evaluation process and will improve the understanding of the pros and cons of the evaluated methods. To facilitate this goal, we have made the train/validation/test datasets and the full code to reproduce the current study publicly available.
If you have any questions or comments related to this study, do not hesitate to contact Greg. He will be happy to delve into the details.