Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets

Getaneh Berie Tarekegn; Rong Terng Juang; Hsin Piao Lin; Yirga Yayeh Munaye; Abebe Belay Adege

doi:10.1109/ICPAI51961.2020.00012

Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets

Getaneh Berie Tarekegn
, Rong Terng Juang
, Hsin Piao Lin
, Yirga Yayeh Munaye
, Abebe Belay Adege

Institute of Aerospace and System Engineering

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

6 Scopus citations

Abstract

Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments.

Original language	English
Title of host publication	Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	23-28
Number of pages	6
ISBN (Electronic)	9781665404839
DOIs	https://doi.org/10.1109/ICPAI51961.2020.00012
State	Published - Dec 2020
Event	1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020 - Taipei, Taiwan Duration: 3 Dec 2020 → 5 Dec 2020

Publication series

Name	Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

Conference

Conference	1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020
Country/Territory	Taiwan
City	Taipei
Period	3/12/20 → 5/12/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Deep Convolutional Generative Adversarial Network
Linear Discriminant Analysis
Long Short-Term Memory
Positioning
Radio signal
Support Vector Machine

Access to Document

10.1109/ICPAI51961.2020.00012

Cite this

Tarekegn, G. B., Juang, R. T., Lin, H. P., Munaye, Y. Y., & Belay Adege, A. (2020). Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets. In Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020 (pp. 23-28). Article 9302595 (Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPAI51961.2020.00012

Tarekegn, Getaneh Berie ; Juang, Rong Terng ; Lin, Hsin Piao et al. / Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets. Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. pp. 23-28 (Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020).

@inproceedings{e3fc3bfab0d647c2b5afc83257bf7a3e,

title = "Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets",

abstract = "Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments.",

keywords = "Deep Convolutional Generative Adversarial Network, Linear Discriminant Analysis, Long Short-Term Memory, Positioning, Radio signal, Support Vector Machine",

author = "Tarekegn, \{Getaneh Berie\} and Juang, \{Rong Terng\} and Lin, \{Hsin Piao\} and Munaye, \{Yirga Yayeh\} and \{Belay Adege\}, Abebe",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020 ; Conference date: 03-12-2020 Through 05-12-2020",

year = "2020",

month = dec,

doi = "10.1109/ICPAI51961.2020.00012",

language = "???core.languages.en\_GB???",

series = "Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "23--28",

booktitle = "Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020",

}

Tarekegn, GB, Juang, RT , Lin, HP, Munaye, YY & Belay Adege, A 2020, Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets. in Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020., 9302595, Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020, Institute of Electrical and Electronics Engineers Inc., pp. 23-28, 1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020, Taipei, Taiwan, 3/12/20. https://doi.org/10.1109/ICPAI51961.2020.00012

Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets. / Tarekegn, Getaneh Berie; Juang, Rong Terng ; Lin, Hsin Piao et al.
Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. p. 23-28 9302595 (Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020).

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

TY - GEN

T1 - Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets

AU - Tarekegn, Getaneh Berie

AU - Juang, Rong Terng

AU - Lin, Hsin Piao

AU - Munaye, Yirga Yayeh

AU - Belay Adege, Abebe

PY - 2020/12

Y1 - 2020/12

N2 - Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments.

AB - Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments.

KW - Deep Convolutional Generative Adversarial Network

KW - Linear Discriminant Analysis

KW - Long Short-Term Memory

KW - Positioning

KW - Radio signal

KW - Support Vector Machine

UR - https://www.scopus.com/pages/publications/85100001829

U2 - 10.1109/ICPAI51961.2020.00012

DO - 10.1109/ICPAI51961.2020.00012

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85100001829

T3 - Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

SP - 23

EP - 28

BT - Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020

Y2 - 3 December 2020 through 5 December 2020

ER -

Tarekegn GB, Juang RT , Lin HP, Munaye YY, Belay Adege A. Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets. In Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020. Institute of Electrical and Electronics Engineers Inc. 2020. p. 23-28. 9302595. (Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020). doi: 10.1109/ICPAI51961.2020.00012

Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this