RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering

Lucie Klus; Darwin Quezada-Gaibor; Joaquin Torres-Sospedra; Elena Simona Lohan; Carlos Granell; Jari Nurmi

doi:10.1109/ICUMT51630.2020.9222458

RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering

Lucie Klus, Darwin Quezada-Gaibor, Joaquin Torres-Sospedra, Elena Simona Lohan, Carlos Granell, Jari Nurmi

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

2 Downloads (Pure)

Abstract

Modern IoT devices, that include smartphones and wearables, usually have limited resources. They require efficient methods to optimize the use of internal storage, provide computational efficiency, and reduce energy consumption. Device resources should be used appropriately, especially when employed for time-consuming and energy-intensive computations such as positioning or localization. However, reducing computational costs usually degrades the positioning methods. Therefore, the goal of this article is to propose and compare compression mechanisms of the fingerprinting datasets for energy-saving without losing relevant information, by using adaptive k-means clustering. As a result, we achieved a compression ratio of up to 15.97 with a small decrease (1%) in position error.

Original language	English
Title of host publication	2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020
Publisher	IEEE
Pages	195-200
Number of pages	6
ISBN (Electronic)	9781728192819
DOIs	https://doi.org/10.1109/ICUMT51630.2020.9222458
Publication status	Published - Oct 2020
Publication type	A4 Article in conference proceedings
Event	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops - Brno, Czech Republic Duration: 5 Oct 2020 → 7 Oct 2020

Publication series

Name	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Volume	2020-October
ISSN (Print)	2157-0221
ISSN (Electronic)	2157-023X

Conference

Conference	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Country/Territory	Czech Republic
City	Brno
Period	5/10/20 → 7/10/20

Keywords

clustering
compression ratio
data compression
fingerprinting
indoor positioning
k-means
k-nearest neighbors

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

Computer Networks and Communications
Control and Systems Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICUMT51630.2020.9222458

RSS Fingerprinting Dataset Size Reduction 2020
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Accepted author manuscript, 286 KB

http://urn.fi/URN:NBN:fi:tuni-202011308316

Cite this

Klus, L., Quezada-Gaibor, D., Torres-Sospedra, J., Lohan, E. S., Granell, C., & Nurmi, J. (2020). RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering. In 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020 (pp. 195-200). (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops; Vol. 2020-October). IEEE. https://doi.org/10.1109/ICUMT51630.2020.9222458

Klus, Lucie ; Quezada-Gaibor, Darwin ; Torres-Sospedra, Joaquin et al. / RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering. 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. IEEE, 2020. pp. 195-200 (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops).

@inproceedings{91660cf8ac3f495f9867a7b0e70f3c34,

title = "RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering",

abstract = "Modern IoT devices, that include smartphones and wearables, usually have limited resources. They require efficient methods to optimize the use of internal storage, provide computational efficiency, and reduce energy consumption. Device resources should be used appropriately, especially when employed for time-consuming and energy-intensive computations such as positioning or localization. However, reducing computational costs usually degrades the positioning methods. Therefore, the goal of this article is to propose and compare compression mechanisms of the fingerprinting datasets for energy-saving without losing relevant information, by using adaptive k-means clustering. As a result, we achieved a compression ratio of up to 15.97 with a small decrease (1%) in position error. ",

keywords = "clustering, compression ratio, data compression, fingerprinting, indoor positioning, k-means, k-nearest neighbors",

author = "Lucie Klus and Darwin Quezada-Gaibor and Joaquin Torres-Sospedra and Lohan, {Elena Simona} and Carlos Granell and Jari Nurmi",

note = "Funding Information: Corresponding Author: Lucie Klus (lucie.klus@tuni.fi) The authors gratefully acknowledge funding from European Union{\textquoteright}s Horizon 2020 Research and Innovation programme under the Marie Sklodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). Publisher Copyright: {\textcopyright} 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved. jufoid=72315; International Congress on Ultra Modern Telecommunications and Control Systems and Workshops ; Conference date: 05-10-2020 Through 07-10-2020",

year = "2020",

month = oct,

doi = "10.1109/ICUMT51630.2020.9222458",

language = "English",

series = "International Congress on Ultra Modern Telecommunications and Control Systems and Workshops",

publisher = "IEEE",

pages = "195--200",

booktitle = "2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020",

}

Klus, L , Quezada-Gaibor, D, Torres-Sospedra, J, Lohan, ES, Granell, C & Nurmi, J 2020, RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering. in 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, vol. 2020-October, IEEE, pp. 195-200, International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, Brno, Czech Republic, 5/10/20. https://doi.org/10.1109/ICUMT51630.2020.9222458

RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering. / Klus, Lucie ; Quezada-Gaibor, Darwin; Torres-Sospedra, Joaquin et al.

2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. IEEE, 2020. p. 195-200 (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops; Vol. 2020-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering

AU - Klus, Lucie

AU - Quezada-Gaibor, Darwin

AU - Torres-Sospedra, Joaquin

AU - Lohan, Elena Simona

AU - Granell, Carlos

AU - Nurmi, Jari

N1 - Funding Information: Corresponding Author: Lucie Klus (lucie.klus@tuni.fi) The authors gratefully acknowledge funding from European Union’s Horizon 2020 Research and Innovation programme under the Marie Sklodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). Publisher Copyright: © 2020 IEEE. Copyright: Copyright 2020 Elsevier B.V., All rights reserved. jufoid=72315

PY - 2020/10

Y1 - 2020/10

N2 - Modern IoT devices, that include smartphones and wearables, usually have limited resources. They require efficient methods to optimize the use of internal storage, provide computational efficiency, and reduce energy consumption. Device resources should be used appropriately, especially when employed for time-consuming and energy-intensive computations such as positioning or localization. However, reducing computational costs usually degrades the positioning methods. Therefore, the goal of this article is to propose and compare compression mechanisms of the fingerprinting datasets for energy-saving without losing relevant information, by using adaptive k-means clustering. As a result, we achieved a compression ratio of up to 15.97 with a small decrease (1%) in position error.

AB - Modern IoT devices, that include smartphones and wearables, usually have limited resources. They require efficient methods to optimize the use of internal storage, provide computational efficiency, and reduce energy consumption. Device resources should be used appropriately, especially when employed for time-consuming and energy-intensive computations such as positioning or localization. However, reducing computational costs usually degrades the positioning methods. Therefore, the goal of this article is to propose and compare compression mechanisms of the fingerprinting datasets for energy-saving without losing relevant information, by using adaptive k-means clustering. As a result, we achieved a compression ratio of up to 15.97 with a small decrease (1%) in position error.

KW - clustering

KW - compression ratio

KW - data compression

KW - fingerprinting

KW - indoor positioning

KW - k-means

KW - k-nearest neighbors

U2 - 10.1109/ICUMT51630.2020.9222458

DO - 10.1109/ICUMT51630.2020.9222458

M3 - Conference contribution

AN - SCOPUS:85094872061

T3 - International Congress on Ultra Modern Telecommunications and Control Systems and Workshops

SP - 195

EP - 200

BT - 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020

PB - IEEE

T2 - International Congress on Ultra Modern Telecommunications and Control Systems and Workshops

Y2 - 5 October 2020 through 7 October 2020

ER -

Klus L , Quezada-Gaibor D, Torres-Sospedra J, Lohan ES, Granell C, Nurmi J. RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering. In 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. IEEE. 2020. p. 195-200. (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops). https://doi.org/10.1109/ICUMT51630.2020.9222458