Publication detail

Improving the Precision of Wireless Localization Algorithms: ML Techniques for Indoor Positioning

MAŠEK, P. SEDLÁČEK, P. OMETOV, A. MEKYSKA, J. MLÝNEK, P. HOŠEK, J. KOMAROV, M.

Original Title

Improving the Precision of Wireless Localization Algorithms: ML Techniques for Indoor Positioning

English Title

Improving the Precision of Wireless Localization Algorithms: ML Techniques for Indoor Positioning

Type

conference paper

Language

en

Original Abstract

Due to the tremendous increase in the number of wearable devices and proximity-based services, the need for improved indoor localization techniques becomes more significant. The evolution of the positioning from a hardware perspective is pacing its way along with various software-based approaches also powered by Machine Learning (ML). In this paper, we apply ML algorithms to the real-life collected signal parameters in an indoor localization system based on Ultra-Wideband (UWB) technology to make an analysis of the signal and classify it accordingly. The contribution aims to answer the question of whether an indoor positioning system could benefit from utilizing ML for signal parameter analysis in order to increase its location accuracy, reliability, and robustness across various environments. To this end, we compare different applications of ML approaches and detail the trade-off between computational speed and accuracy.

English abstract

Due to the tremendous increase in the number of wearable devices and proximity-based services, the need for improved indoor localization techniques becomes more significant. The evolution of the positioning from a hardware perspective is pacing its way along with various software-based approaches also powered by Machine Learning (ML). In this paper, we apply ML algorithms to the real-life collected signal parameters in an indoor localization system based on Ultra-Wideband (UWB) technology to make an analysis of the signal and classify it accordingly. The contribution aims to answer the question of whether an indoor positioning system could benefit from utilizing ML for signal parameter analysis in order to increase its location accuracy, reliability, and robustness across various environments. To this end, we compare different applications of ML approaches and detail the trade-off between computational speed and accuracy.

Keywords

Indoor Positioning Systems; Ultra-Wideband; UWB; Machine Learning; Precision Improvement

Released

11.08.2020

Publisher

IEEE

ISBN

978-1-7281-6376-5

Book

43nd International Conference on Telecommunications and Signal Processing (TSP 2020).

Pages from

1

Pages to

6

Pages count

6

Documents

BibTex


@inproceedings{BUT164722,
  author="Pavel {Mašek} and Petr {Sedláček} and Aleksandr {Ometov} and Jiří {Mekyska} and Petr {Mlýnek} and Jiří {Hošek} and Mikhail {Komarov}",
  title="Improving the Precision of Wireless Localization Algorithms: ML Techniques for Indoor Positioning",
  annote="Due to the tremendous increase in the number of wearable devices and proximity-based services, the need for improved indoor localization techniques becomes more significant. The evolution of the positioning from a hardware perspective is pacing its way along with various software-based approaches also powered by Machine Learning (ML). In this paper, we apply ML algorithms to the real-life collected signal parameters in an indoor localization system based on Ultra-Wideband (UWB) technology to make an analysis of the signal and classify it accordingly. The contribution aims to answer the question of whether an indoor positioning system could benefit from utilizing ML for signal parameter analysis in order to increase its location accuracy, reliability, and robustness across various environments. To this end, we compare different applications of ML approaches and detail the trade-off between computational speed and accuracy.",
  address="IEEE",
  booktitle="43nd International Conference on Telecommunications and Signal Processing (TSP 2020).",
  chapter="164722",
  doi="10.1109/TSP49548.2020.9163551",
  howpublished="online",
  institution="IEEE",
  year="2020",
  month="august",
  pages="1--6",
  publisher="IEEE",
  type="conference paper"
}