Neural Network Based Single-Carrier Frequency Domain Equalization

Stefan Baumgartner; Oliver Lang; Mario Huemer

doi:10.1007/978-3-031-25312-6_34

Neural Network Based Single-Carrier Frequency Domain Equalization

Stefan Baumgartner, Oliver Lang, Mario Huemer

Institute of Signal Processing

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

Abstract

The task of equalization on the receiver side of a wireless communication system is typically accomplished with model-based estimation methods. However, the utilization of data-driven approaches, e.g., neural networks (NNs), for equalization is in focus of current research. In this work, we investigate two different NNs for single-carrier frequency domain equalization. We elaborate on how existing model knowledge can be incorporated into NNs, we introduce a data normalization scheme required for the regarded NNs, and we compare these data-driven methods with model-based approaches concerning performance and complexity.

Original language	English
Title of host publication	Computer Aided Systems Theory - EUROCAST 2022, Lecture Notes in Computer Science (LNCS)
Publisher	Springer Nature Switzerland
Pages	295-302
Number of pages	8
Volume	13789
ISBN (Print)	978-3-031-25312-6
DOIs	https://doi.org/10.1007/978-3-031-25312-6_34
Publication status	Published - 2023

Publication series

Name	Lecture Notes in Computer Science (LNCS)

Fields of science

202040 Transmission technology
102019 Machine learning
202 Electrical Engineering, Electronics, Information Engineering
202015 Electronics
202022 Information technology
202027 Mechatronics
202030 Communication engineering
202037 Signal processing
202041 Computer engineering

JKU Focus areas

Digital Transformation

Access to Document

10.1007/978-3-031-25312-6_34

JKU LIT SAL eSPML Lab
Baumgartner, S. (Researcher), Bognar, G. (Researcher), Hochreiter, S. (Researcher), Hofmarcher, M. (Researcher), Kovacs, P. (Researcher), Schmid, S. (Researcher), Shtainer, A. (Researcher), Springer, A. (Researcher), Wille, R. (Researcher) & Huemer, M. (PI)
01.07.2020 → 31.12.2023
Project: Other › Other project

Cite this

@inproceedings{dc9e945b0b7b47259ee89a1025e78d35,

title = "Neural Network Based Single-Carrier Frequency Domain Equalization",

abstract = "The task of equalization on the receiver side of a wireless communication system is typically accomplished with model-based estimation methods. However, the utilization of data-driven approaches, e.g., neural networks (NNs), for equalization is in focus of current research. In this work, we investigate two different NNs for single-carrier frequency domain equalization. We elaborate on how existing model knowledge can be incorporated into NNs, we introduce a data normalization scheme required for the regarded NNs, and we compare these data-driven methods with model-based approaches concerning performance and complexity.",

author = "Stefan Baumgartner and Oliver Lang and Mario Huemer",

year = "2023",

doi = "10.1007/978-3-031-25312-6_34",

language = "English",

isbn = "978-3-031-25312-6",

volume = "13789",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer Nature Switzerland",

pages = "295--302",

booktitle = "Computer Aided Systems Theory - EUROCAST 2022, Lecture Notes in Computer Science (LNCS)",

}

Neural Network Based Single-Carrier Frequency Domain Equalization. / Baumgartner, Stefan; Lang, Oliver ; Huemer, Mario.
Computer Aided Systems Theory - EUROCAST 2022, Lecture Notes in Computer Science (LNCS). Vol. 13789 Springer Nature Switzerland, 2023. p. 295-302 (Lecture Notes in Computer Science (LNCS)).

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

TY - GEN

T1 - Neural Network Based Single-Carrier Frequency Domain Equalization

AU - Baumgartner, Stefan

AU - Lang, Oliver

AU - Huemer, Mario

PY - 2023

Y1 - 2023

N2 - The task of equalization on the receiver side of a wireless communication system is typically accomplished with model-based estimation methods. However, the utilization of data-driven approaches, e.g., neural networks (NNs), for equalization is in focus of current research. In this work, we investigate two different NNs for single-carrier frequency domain equalization. We elaborate on how existing model knowledge can be incorporated into NNs, we introduce a data normalization scheme required for the regarded NNs, and we compare these data-driven methods with model-based approaches concerning performance and complexity.

AB - The task of equalization on the receiver side of a wireless communication system is typically accomplished with model-based estimation methods. However, the utilization of data-driven approaches, e.g., neural networks (NNs), for equalization is in focus of current research. In this work, we investigate two different NNs for single-carrier frequency domain equalization. We elaborate on how existing model knowledge can be incorporated into NNs, we introduce a data normalization scheme required for the regarded NNs, and we compare these data-driven methods with model-based approaches concerning performance and complexity.

U2 - 10.1007/978-3-031-25312-6_34

DO - 10.1007/978-3-031-25312-6_34

M3 - Conference proceedings

SN - 978-3-031-25312-6

VL - 13789

T3 - Lecture Notes in Computer Science (LNCS)

SP - 295

EP - 302

BT - Computer Aided Systems Theory - EUROCAST 2022, Lecture Notes in Computer Science (LNCS)

PB - Springer Nature Switzerland

ER -

Neural Network Based Single-Carrier Frequency Domain Equalization

Abstract

Publication series

Fields of science

JKU Focus areas

Access to Document

Projects

JKU LIT SAL eSPML Lab

Cite this