Mixture Density Networks for WSN Localization

Julian Karoliny; Bernhard Etzlinger; Andreas Springer

doi:10.1109/iccworkshops49005.2020.9145035

Mixture Density Networks for WSN Localization

Julian Karoliny, Bernhard Etzlinger, Andreas Springer

Wireless Communications (WLC)

Research output: Contribution to conference (No Proceedings) › Paper › peer-review

Abstract

A new algorithm for determining soft range information in network localization is proposed. It applies a variant of neural networks called mixture density networks. When used in particle-based Bayesian localization procedures, it has a similar low computational complexity and provides comparable localization accuracy as existing methods. This property enables the proposed algorithm to be implemented on low-power wireless sensor network (WSN) nodes that are equipped with commercial ultra-wideband transceivers. The proposed algorithm is validated in indoor network localization experiments.

Original language	English
Pages	1-5
Number of pages	5
DOIs	https://doi.org/10.1109/iccworkshops49005.2020.9145035
Publication status	Published - 21 Jul 2020
Event	2020 IEEE International Conference on Communications Workshops (ICC Workshops) - Dublin, Ireland Duration: 7 Jun 2020 → 11 Jun 2020

Conference

Conference	2020 IEEE International Conference on Communications Workshops (ICC Workshops)
Period	7/06/20 → 11/06/20

Keywords

Mixture density networks
Network localization
Neural networks
Soft range information
Ultra-wideband
Wireless sensor network

Access to Document

10.1109/iccworkshops49005.2020.9145035

https://ieeexplore.ieee.org/document/9145035/

Cite this

@conference{180b3b1d67a441cfb959c786efacfb22,

title = "Mixture Density Networks for WSN Localization",

abstract = "A new algorithm for determining soft range information in network localization is proposed. It applies a variant of neural networks called mixture density networks. When used in particle-based Bayesian localization procedures, it has a similar low computational complexity and provides comparable localization accuracy as existing methods. This property enables the proposed algorithm to be implemented on low-power wireless sensor network (WSN) nodes that are equipped with commercial ultra-wideband transceivers. The proposed algorithm is validated in indoor network localization experiments.",

keywords = "Mixture density networks, Network localization, Neural networks, Soft range information, Ultra-wideband, Wireless sensor network",

author = "Julian Karoliny and Bernhard Etzlinger and Andreas Springer",

year = "2020",

month = jul,

day = "21",

doi = "10.1109/iccworkshops49005.2020.9145035",

language = "English",

pages = "1--5",

note = "2020 IEEE International Conference on Communications Workshops (ICC Workshops) ; Conference date: 07-06-2020 Through 11-06-2020",

}

TY - CONF

T1 - Mixture Density Networks for WSN Localization

AU - Karoliny, Julian

AU - Etzlinger, Bernhard

AU - Springer, Andreas

PY - 2020/7/21

Y1 - 2020/7/21

N2 - A new algorithm for determining soft range information in network localization is proposed. It applies a variant of neural networks called mixture density networks. When used in particle-based Bayesian localization procedures, it has a similar low computational complexity and provides comparable localization accuracy as existing methods. This property enables the proposed algorithm to be implemented on low-power wireless sensor network (WSN) nodes that are equipped with commercial ultra-wideband transceivers. The proposed algorithm is validated in indoor network localization experiments.

AB - A new algorithm for determining soft range information in network localization is proposed. It applies a variant of neural networks called mixture density networks. When used in particle-based Bayesian localization procedures, it has a similar low computational complexity and provides comparable localization accuracy as existing methods. This property enables the proposed algorithm to be implemented on low-power wireless sensor network (WSN) nodes that are equipped with commercial ultra-wideband transceivers. The proposed algorithm is validated in indoor network localization experiments.

KW - Mixture density networks

KW - Network localization

KW - Neural networks

KW - Soft range information

KW - Ultra-wideband

KW - Wireless sensor network

UR - https://www.mendeley.com/catalogue/1d7fb46a-885e-308f-a12f-be2bdbe68cb2/

U2 - 10.1109/iccworkshops49005.2020.9145035

DO - 10.1109/iccworkshops49005.2020.9145035

M3 - Paper

SP - 1

EP - 5

T2 - 2020 IEEE International Conference on Communications Workshops (ICC Workshops)

Y2 - 7 June 2020 through 11 June 2020

ER -

Mixture Density Networks for WSN Localization

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this