Identification of Distorted RF Components via Deep Multi-Task Learning

Mehmet Ali Aygul; Ebubekir Memisoglu; Hakan Ali Cirpan; Huseyin Arslan

doi:10.1109/VTC2022-Fall57202.2022.10012986

Identification of Distorted RF Components via Deep Multi-Task Learning

Mehmet Ali Aygul^*, Ebubekir Memisoglu, Hakan Ali Cirpan, Huseyin Arslan

^*Corresponding author for this work

Department of Electronics and Communication Engineering

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

Abstract

High-quality radio frequency (RF) components are imperative for efficient wireless communication. However, these components can degrade over time and need to be identified so that either they can be replaced or their effects can be compensated. The identification of these components can be done through observation and analysis of constellation diagrams. However, in the presence of multiple distortions, it is very challenging to isolate and identify the RF components responsible for the degradation. This paper highlights the difficulties of distorted RF components' identification and their importance. Furthermore, a deep multi-task learning algorithm is proposed to identify the distorted components in the challenging scenario. Extensive simulations show that the proposed algorithm can automatically detect multiple distorted RF components with high accuracy in different scenarios.

Original language	English
Title of host publication	2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781665454681
DOIs	https://doi.org/10.1109/VTC2022-Fall57202.2022.10012986
Publication status	Published - 2022
Event	96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022 - London, United Kingdom Duration: 26 Sept 2022 → 29 Sept 2022

Publication series

Name	IEEE Vehicular Technology Conference
Volume	2022-September
ISSN (Print)	1550-2252

Conference

Conference	96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022
Country/Territory	United Kingdom
City	London
Period	26/09/22 → 29/09/22

Bibliographical note

Publisher Copyright:
© 2022 IEEE.

Keywords

Deep learning
distorted RF components identification
multi-task learning
RF impairments

Access to Document

10.1109/VTC2022-Fall57202.2022.10012986

Cite this

Aygul, M. A., Memisoglu, E., Cirpan, H. A., & Arslan, H. (2022). Identification of Distorted RF Components via Deep Multi-Task Learning. In 2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings (IEEE Vehicular Technology Conference; Vol. 2022-September). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/VTC2022-Fall57202.2022.10012986

@inproceedings{982fdb1b79cc4f698ba559f6d3e39150,

title = "Identification of Distorted RF Components via Deep Multi-Task Learning",

abstract = "High-quality radio frequency (RF) components are imperative for efficient wireless communication. However, these components can degrade over time and need to be identified so that either they can be replaced or their effects can be compensated. The identification of these components can be done through observation and analysis of constellation diagrams. However, in the presence of multiple distortions, it is very challenging to isolate and identify the RF components responsible for the degradation. This paper highlights the difficulties of distorted RF components' identification and their importance. Furthermore, a deep multi-task learning algorithm is proposed to identify the distorted components in the challenging scenario. Extensive simulations show that the proposed algorithm can automatically detect multiple distorted RF components with high accuracy in different scenarios.",

keywords = "Deep learning, distorted RF components identification, multi-task learning, RF impairments",

author = "Aygul, {Mehmet Ali} and Ebubekir Memisoglu and Cirpan, {Hakan Ali} and Huseyin Arslan",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022 ; Conference date: 26-09-2022 Through 29-09-2022",

year = "2022",

doi = "10.1109/VTC2022-Fall57202.2022.10012986",

language = "English",

series = "IEEE Vehicular Technology Conference",

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

booktitle = "2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings",

address = "United States",

}

Aygul, MA, Memisoglu, E, Cirpan, HA & Arslan, H 2022, Identification of Distorted RF Components via Deep Multi-Task Learning. in 2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings. IEEE Vehicular Technology Conference, vol. 2022-September, Institute of Electrical and Electronics Engineers Inc., 96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022, London, United Kingdom, 26/09/22. https://doi.org/10.1109/VTC2022-Fall57202.2022.10012986

Identification of Distorted RF Components via Deep Multi-Task Learning. / Aygul, Mehmet Ali; Memisoglu, Ebubekir; Cirpan, Hakan Ali et al.
2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2022. (IEEE Vehicular Technology Conference; Vol. 2022-September).

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

TY - GEN

T1 - Identification of Distorted RF Components via Deep Multi-Task Learning

AU - Aygul, Mehmet Ali

AU - Memisoglu, Ebubekir

AU - Cirpan, Hakan Ali

AU - Arslan, Huseyin

PY - 2022

Y1 - 2022

N2 - High-quality radio frequency (RF) components are imperative for efficient wireless communication. However, these components can degrade over time and need to be identified so that either they can be replaced or their effects can be compensated. The identification of these components can be done through observation and analysis of constellation diagrams. However, in the presence of multiple distortions, it is very challenging to isolate and identify the RF components responsible for the degradation. This paper highlights the difficulties of distorted RF components' identification and their importance. Furthermore, a deep multi-task learning algorithm is proposed to identify the distorted components in the challenging scenario. Extensive simulations show that the proposed algorithm can automatically detect multiple distorted RF components with high accuracy in different scenarios.

AB - High-quality radio frequency (RF) components are imperative for efficient wireless communication. However, these components can degrade over time and need to be identified so that either they can be replaced or their effects can be compensated. The identification of these components can be done through observation and analysis of constellation diagrams. However, in the presence of multiple distortions, it is very challenging to isolate and identify the RF components responsible for the degradation. This paper highlights the difficulties of distorted RF components' identification and their importance. Furthermore, a deep multi-task learning algorithm is proposed to identify the distorted components in the challenging scenario. Extensive simulations show that the proposed algorithm can automatically detect multiple distorted RF components with high accuracy in different scenarios.

KW - Deep learning

KW - distorted RF components identification

KW - multi-task learning

KW - RF impairments

UR - http://www.scopus.com/inward/record.url?scp=85147035617&partnerID=8YFLogxK

U2 - 10.1109/VTC2022-Fall57202.2022.10012986

DO - 10.1109/VTC2022-Fall57202.2022.10012986

M3 - Conference contribution

AN - SCOPUS:85147035617

T3 - IEEE Vehicular Technology Conference

BT - 2022 IEEE 96th Vehicular Technology Conference, VTC 2022-Fall 2022 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 96th IEEE Vehicular Technology Conference, VTC 2022-Fall 2022

Y2 - 26 September 2022 through 29 September 2022

ER -

Identification of Distorted RF Components via Deep Multi-Task Learning

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this