TY - GEN
T1 - New Cluster Selection and Fine-grained Search for k-Means Clustering and Wi-Fi Fingerprinting
AU - Torres-Sospedra, Joaquin
AU - Quezada-Gaibor, Darwin
AU - Mendoza-Silva, German M.
AU - Nurmi, Jari
AU - Koucheryavy, Yevgeni
AU - Huerta, Joaquin
N1 - Funding Information:
Corresponding Author: J. Torres-Sospedra (torres@ubikgs.com) The authors gratefully acknowledge funding from Ministerio de Ciencia, In-novación y Universidades (INSIGNIA, PTQ2018-009981); European Union’s H2020 Research and Innovation programme under the Marie Skłodowska-Curie grant agreement No.813278 (A-WEAR, http://www.a-wear.eu/); and Universitat Jaume I (PREDOC/2016/55).
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
jufoid=72237
PY - 2020/6
Y1 - 2020/6
N2 - Wi-Fi fingerprinting is a popular technique for Indoor Positioning Systems (IPSs) thanks to its low complexity and the ubiquity of WLAN infrastructures. However, this technique may present scalability issues when the reference dataset (radio map) is very large. To reduce the computational costs, k-Means Clustering has been successfully applied in the past. However, it is a general-purpose algorithm for unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge in the coarse and fine-grained searches. Due to the heterogeneity either in the IPS side (including radio map generation) and in the network infrastructure, we used an evaluation framework composed of 16 datasets. In terms of general positioning accuracy and computational costs, the best proposed k-means variant provided better general positioning accuracy and a significantly better computational cost -around 40% lower- than the original k-means.
AB - Wi-Fi fingerprinting is a popular technique for Indoor Positioning Systems (IPSs) thanks to its low complexity and the ubiquity of WLAN infrastructures. However, this technique may present scalability issues when the reference dataset (radio map) is very large. To reduce the computational costs, k-Means Clustering has been successfully applied in the past. However, it is a general-purpose algorithm for unsupervised classification. This paper introduces three variants that apply heuristics based on radio propagation knowledge in the coarse and fine-grained searches. Due to the heterogeneity either in the IPS side (including radio map generation) and in the network infrastructure, we used an evaluation framework composed of 16 datasets. In terms of general positioning accuracy and computational costs, the best proposed k-means variant provided better general positioning accuracy and a significantly better computational cost -around 40% lower- than the original k-means.
KW - Clustering
KW - RSS
KW - Wi-Fi Fingerprinting
U2 - 10.1109/ICL-GNSS49876.2020.9115419
DO - 10.1109/ICL-GNSS49876.2020.9115419
M3 - Conference contribution
AN - SCOPUS:85086034882
T3 - International Conference on Localization and GNSS
BT - 2020 International Conference on Localization and GNSS, ICL-GNSS 2020 - Proceedings
A2 - Nurmi, Jari
A2 - Lohan, Elena-Simona
A2 - Torres-Sospedra, Joaquin
A2 - Kuusniemi, Heidi
A2 - Ometov, Aleksandr
PB - IEEE
T2 - International Conference on Localization and GNSS
Y2 - 2 June 2020 through 4 June 2020
ER -