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

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-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 languageEnglish
Title of host publication2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020
PublisherIEEE
Pages195-200
Number of pages6
ISBN (Electronic)9781728192819
DOIs
Publication statusPublished - Oct 2020
Publication typeA4 Article in conference proceedings
EventInternational Congress on Ultra Modern Telecommunications and Control Systems and Workshops - Brno, Czech Republic
Duration: 5 Oct 20207 Oct 2020

Publication series

NameInternational Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Volume2020-October
ISSN (Print)2157-0221
ISSN (Electronic)2157-023X

Conference

ConferenceInternational Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Country/TerritoryCzech Republic
CityBrno
Period5/10/207/10/20

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

Fingerprint

Dive into the research topics of 'RSS Fingerprinting Dataset Size Reduction Using Feature-Wise Adaptive k-Means Clustering'. Together they form a unique fingerprint.

Cite this