@inproceedings{Quezada2022c,
title = {Data Cleansing for Indoor Positioning Wi-Fi Fingerprinting Datasets},
author = {Darwin Quezada-Gaibor and Lucie Klus and Joaquín Torres-Sospedra and Elena Simona Lohan and Jari Nurmi and Carlos Granell-Canut and Joaquín Huerta-Guijarro},
doi = {https://doi.org/10.1109/MDM55031.2022.00079},
isbn = {978-1-6654-5176-5},
year = {2022},
date = {2022-06-10},
booktitle = {2022 23rd IEEE International Conference on Mobile Data Management (MDM)},
pages = {349-354},
publisher = {IEEE},
abstract = {Wearable and IoT devices requiring positioning and localisation services grow in number exponentially every year. This rapid growth also produces millions of data entries that need to be pre-processed prior to being used in any indoor positioning system to ensure the data quality and provide a high Quality of Service (QoS) to the end-user. In this paper, we offer a novel and straightforward data cleansing algorithm for WLAN fingerprinting radio maps. This algorithm is based on the correlation among fingerprints using the Received Signal Strength (RSS) values and the Access Points (APs)'s identifier. We use those to compute the correlation among all samples in the dataset and remove fingerprints with low level of correlation from the dataset. We evaluated the proposed method on 14 independent publicly-available datasets. As a result, an average of 14% of fingerprints were removed from the datasets. The 2D positioning error was reduced by 2.7% and 3D positioning error by 5.3% with a slight increase in the floor hit rate by 1.2% on average. Consequently, the average speed of position prediction was also increased by 14%.},
keywords = {Data science, Indoor positioning, Wi-Fi fingerprint},
pubstate = {published},
tppubtype = {inproceedings}
}