Neural Network Based Data Estimation for Unique Word OFDM

Stefan Baumgartner; Gergö Bognar; Oliver Lang; Mario Huemer

doi:10.1109/IEEECONF53345.2021.9723229

Neural Network Based Data Estimation for Unique Word OFDM

Stefan Baumgartner, Gergö Bognar, Oliver Lang, Mario Huemer

Institute of Signal Processing

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

Abstract

Model-based methods have been employed for data estimation for several decades. Due to the incredible success of data-driven machine learning methods, efforts have recently been made to utilize neural networks (NNs) for data estimation in general multiple-input multiple-output (MIMO) communication systems. In this paper, NN-based data estimation is conducted for a communication system employing the unique word orthogonal frequency division multiplexing (UW-OFDM) signaling scheme. In particular, we utilize the so-called DetNet, an NN that has been proposed for data estimation in a general MIMO system. However, to achieve satisfying results for data estimation in a UW-OFDM system an appropriate pre-processing of the input data of DetNet has to be introduced. We investigate its bit error ratio performance in indoor frequency selective environments, we conduct a brief complexity analysis, and we highlight its partially peculiar estimation characteristics.

Original language	English
Title of host publication	Proceedings of the Asilomar Conference on Signals, Systems, and Computers (ACSSC 2021)
Publisher	IEEE
Pages	381-388
Number of pages	8
ISBN (Print)	978-1-6654-5828-3
DOIs	https://doi.org/10.1109/IEEECONF53345.2021.9723229
Publication status	Published - Nov 2021

Fields of science

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

JKU Focus areas

Digital Transformation

Access to Document

10.1109/IEEECONF53345.2021.9723229

Cite this

@inproceedings{b27cda5ac43c4368adbb1d959ff61ae6,

title = "Neural Network Based Data Estimation for Unique Word OFDM",

abstract = "Model-based methods have been employed for data estimation for several decades. Due to the incredible success of data-driven machine learning methods, efforts have recently been made to utilize neural networks (NNs) for data estimation in general multiple-input multiple-output (MIMO) communication systems. In this paper, NN-based data estimation is conducted for a communication system employing the unique word orthogonal frequency division multiplexing (UW-OFDM) signaling scheme. In particular, we utilize the so-called DetNet, an NN that has been proposed for data estimation in a general MIMO system. However, to achieve satisfying results for data estimation in a UW-OFDM system an appropriate pre-processing of the input data of DetNet has to be introduced. We investigate its bit error ratio performance in indoor frequency selective environments, we conduct a brief complexity analysis, and we highlight its partially peculiar estimation characteristics.",

author = "Stefan Baumgartner and Gerg{\"o} Bognar and Oliver Lang and Mario Huemer",

year = "2021",

month = nov,

doi = "10.1109/IEEECONF53345.2021.9723229",

language = "English",

isbn = "978-1-6654-5828-3",

pages = "381--388",

booktitle = "Proceedings of the Asilomar Conference on Signals, Systems, and Computers (ACSSC 2021)",

publisher = "IEEE",

}

TY - GEN

T1 - Neural Network Based Data Estimation for Unique Word OFDM

AU - Baumgartner, Stefan

AU - Bognar, Gergö

AU - Lang, Oliver

AU - Huemer, Mario

PY - 2021/11

Y1 - 2021/11

N2 - Model-based methods have been employed for data estimation for several decades. Due to the incredible success of data-driven machine learning methods, efforts have recently been made to utilize neural networks (NNs) for data estimation in general multiple-input multiple-output (MIMO) communication systems. In this paper, NN-based data estimation is conducted for a communication system employing the unique word orthogonal frequency division multiplexing (UW-OFDM) signaling scheme. In particular, we utilize the so-called DetNet, an NN that has been proposed for data estimation in a general MIMO system. However, to achieve satisfying results for data estimation in a UW-OFDM system an appropriate pre-processing of the input data of DetNet has to be introduced. We investigate its bit error ratio performance in indoor frequency selective environments, we conduct a brief complexity analysis, and we highlight its partially peculiar estimation characteristics.

AB - Model-based methods have been employed for data estimation for several decades. Due to the incredible success of data-driven machine learning methods, efforts have recently been made to utilize neural networks (NNs) for data estimation in general multiple-input multiple-output (MIMO) communication systems. In this paper, NN-based data estimation is conducted for a communication system employing the unique word orthogonal frequency division multiplexing (UW-OFDM) signaling scheme. In particular, we utilize the so-called DetNet, an NN that has been proposed for data estimation in a general MIMO system. However, to achieve satisfying results for data estimation in a UW-OFDM system an appropriate pre-processing of the input data of DetNet has to be introduced. We investigate its bit error ratio performance in indoor frequency selective environments, we conduct a brief complexity analysis, and we highlight its partially peculiar estimation characteristics.

UR - https://ieeexplore.ieee.org/document/9723229

U2 - 10.1109/IEEECONF53345.2021.9723229

DO - 10.1109/IEEECONF53345.2021.9723229

M3 - Conference proceedings

SN - 978-1-6654-5828-3

SP - 381

EP - 388

BT - Proceedings of the Asilomar Conference on Signals, Systems, and Computers (ACSSC 2021)

PB - IEEE

ER -

Neural Network Based Data Estimation for Unique Word OFDM

Abstract

Fields of science

JKU Focus areas

Access to Document

Other files and links

JKU LIT SAL eSPML Lab

Cite this

Neural Network Based Data Estimation for Unique Word OFDM

Abstract

Fields of science

JKU Focus areas

Access to Document

Other files and links

Projects

JKU LIT SAL eSPML Lab

Cite this