Planned intervention: On Wednesday June 26th 05:30 UTC Zenodo will be unavailable for 10-20 minutes to perform a storage cluster upgrade.
Published February 4, 2021 | Version v1
Dataset Open

ProxyFAUG: Proximity-based Fingerprint Augmentation (data)

  • 1. Geneva School of Business Administration, HES-SO

Description

The supplementary data of the paper "ProxyFAUG: Proximity-based Fingerprint Augmentation".

Open access Author’s accepted manuscript version: https://arxiv.org/abs/2102.02706v2

Published paper: https://ieeexplore.ieee.org/document/9662590

 

The train/validation/test sets used in the paper "ProxyFAUG: Proximity-based Fingerprint Augmentation", after having passed the preprocessing process described in the paper, are made available here. Moreover, the augmentations produced by the proposed ProxyFAUG method are also made available with the files (x_aug_train.csv, y_aug_train.csv). More specifically:

x_train_pre.csv : The features side (x) information of the preprocessed training set.

x_val_pre.csv : The features side (x) information of the preprocessed validation set.

x_test_pre.csv  : The features side (x) information of the preprocessed test set.

x_aug_train.csv : The features side (x) information of the fingerprints generated by ProxyFAUG. 

y_train.csv : The location ground truth information (y) of the training set.

y_val.csv : The location ground truth information (y) of the validation set.

y_test.csv  : The location ground truth information (y) of the test set.

y_aug_train.csv : The location ground truth information (y) of the fingerprints generated by ProxyFAUG. 

Note that in the paper, the original training set (x_train_pre.csv) is used as a baseline, and is compared against the scenario where the concatenation of the original and the generated training sets (concatenation of x_train_pre.csv and x_aug_train.csv) is used. 

The full code implementation related to the paper is available here:

Code: https://zenodo.org/record/4457353

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

The original full dataset used in this study, is the public dataset sigfox_dataset_antwerp.csv which can be access here:

https://zenodo.org/record/3904158#.X4_h7y8RpQI

The above link is related to the publication "Sigfox and LoRaWAN Datasets for Fingerprint Localization in Large Urban and Rural Areas", in which the original full dataset was published. The publication is available here:

http://www.mdpi.com/2306-5729/3/2/13

The credit for the creation of the original full dataset goes to Aernouts, Michiel;  Berkvens, Rafael; Van Vlaenderen, Koen; and  Weyn, Maarten.

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

The train/validation/test split of the original dataset that is used in this paper, is taken from our previous work "A Reproducible Analysis of RSSI Fingerprinting for Outdoors Localization Using Sigfox: Preprocessing and Hyperparameter Tuning". Using the same  train/validation/test split in different works strengthens the consistency of the comparison of results. All relevant material of that work is listed below:

Preprint: https://arxiv.org/abs/1908.06851

Paper: https://ieeexplore.ieee.org/document/8911792

Code: https://zenodo.org/record/3228752

Data: https://zenodo.org/record/3228744

 

Files

x_aug_train.csv

Files (56.8 MB)

Name Size Download all
md5:fe5ea1d21c2d15e185f6aea9e8dece0e
44.4 MB Preview Download
md5:2b8b464dc880035fe97024ec76a72784
1.5 MB Preview Download
md5:0f1cf5343a254912678ba50ca93f62ec
7.1 MB Preview Download
md5:a52e37683c6ad9e908c9173a626be262
1.5 MB Preview Download
md5:b5c07db0a00525fd6c8d28e523db4934
1.8 MB Preview Download
md5:493d6c9a2767920a2abc6afb227ada9a
61.9 kB Preview Download
md5:1ea9f1a82bc64d270b371e19756fe4c6
289.3 kB Preview Download
md5:8ac9bafe582577d18dde6e01b03177de
61.8 kB Preview Download

Additional details