Can I Trust This Location Estimate? Reproducibly Benchmarking the Methods of Dynamic Accuracy Estimation of Localization (code)

The code implementation, and supplementary material, of the paper "Can I Trust This Location Estimate?  Reproducibly Benchmarking the Methods of Dynamic Accuracy Estimation of Localization".

Open access link to the paper: https://www.mdpi.com/1424-8220/22/3/1088

-----------------------------------------------------------------------------------------------------------------------------------------------------------------

The following files are provided:

DAE_Benchmarking_Public.ipynb : The main Jupyter Notebook file of this work, with all the experiments of the paper.

DAE_script.py : The python script with the implementation of the DAE methods and relevant assisting functions.

haversine_script.py : Assisting script for geographic distance calculations, based on the Haversine project (https://pypi.org/project/haversine/).

Creating_files_LoRaWAN_dataset.ipynb : The Jupyter Notebook used to prepare the data of the LoRaWAN dataset.

Creating_files_DSI_dataset.ipynb : The Jupyter Notebook used to prepare the data of the DSI dataset.

Creating_files_MAN_dataset.ipynb : The Jupyter Notebook used to prepare the data of the MAN dataset.

files.zip : The folder structure containing the data files used.

results.zip : The folder structure containing the resulting figures.

-----------------------------------------------------------------------------------------------------------------------------------------------------------------

The datasets used are adapted versions of public datasets that were published in the following works:

1) Aernouts, M.; Berkvens, R.; Van Vlaenderen, K.; Weyn, M. Sigfox and LoRaWAN Datasets for Fingerprint Localization in Large Urban and Rural Areas. 2019. Available online: https://zenodo.org/record/3904158#.YfNIfOpBxPY

2) Moreira, A.; Silva, I.; Torres-Sospedra, J. The DSI dataset for Wi-Fi fingerprinting using mobile devices. 2020. Available online: https://zenodo.org/record/3778646#.YfNHtOpBxPY

3) King, T.; Kopf, S.; Haenselmann, T.; Lubberger, C.; Effelsberg, W. CRAWDAD Dataset Mannheim/Compass (v. 2008-04-11). 2008. Available online: https://crawdad.org/mannheim/compass/20080411

All credit for the creation of these datasets goes to their authors.

We publish here the train/validation/test splits of the processed datasets, used in the current work.