Deep Learning Transceiver for Terahertz Band Communication System with 1-bit ADC and Oversampling

Metasebia D. Gemeda; Min S. Han; Ameha T. Abebe; Chung G. Kang

doi:10.1109/CCNC49033.2022.9700716

Deep Learning Transceiver for Terahertz Band Communication System with 1-bit ADC and Oversampling

Metasebia D. Gemeda, Min S. Han, Ameha T. Abebe, Chung G. Kang

School of Electrical Engineering

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

Abstract

In this study, with the aim of reducing power consumption for terahertz band wireless communication, we present a deep learning-based solution for transceiver design with 1-bit quantization and oversampling at the receiver, and Faster- than-Nyquist transmission. Our simulation results illustrate that the studied system with 1-bit quantization achieves bit-error- rate performance comparable to that of an end-to-end channel autoencoder without the constraint of 1-bit quantization subject to the same spectral efficiency. It is also demonstrated that reliable communication can be achieved at rates exceeding 5.3 bits/sec/Hz which corresponds to 80% of the achievable capacity at adequate SNR.

Original language	English
Pages (from-to)	515-516
Number of pages	2
Journal	Proceedings - IEEE Consumer Communications and Networking Conference, CCNC
DOIs	https://doi.org/10.1109/CCNC49033.2022.9700716
Publication status	Published - 2022
Event	19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022 - Virtual, Online, United States Duration: 2022 Jan 8 → 2022 Jan 11

Keywords

autoencoder
deep learning
one-bit-quantization
oversampling

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1109/CCNC49033.2022.9700716

Cite this

@article{1f9fd5f7b4974eebb6b2a768ee173a43,

title = "Deep Learning Transceiver for Terahertz Band Communication System with 1-bit ADC and Oversampling",

abstract = "In this study, with the aim of reducing power consumption for terahertz band wireless communication, we present a deep learning-based solution for transceiver design with 1-bit quantization and oversampling at the receiver, and Faster- than-Nyquist transmission. Our simulation results illustrate that the studied system with 1-bit quantization achieves bit-error- rate performance comparable to that of an end-to-end channel autoencoder without the constraint of 1-bit quantization subject to the same spectral efficiency. It is also demonstrated that reliable communication can be achieved at rates exceeding 5.3 bits/sec/Hz which corresponds to 80% of the achievable capacity at adequate SNR.",

keywords = "autoencoder, deep learning, one-bit-quantization, oversampling",

author = "Gemeda, {Metasebia D.} and Han, {Min S.} and Abebe, {Ameha T.} and Kang, {Chung G.}",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022 ; Conference date: 08-01-2022 Through 11-01-2022",

year = "2022",

doi = "10.1109/CCNC49033.2022.9700716",

language = "English",

pages = "515--516",

journal = "Proceedings - IEEE Consumer Communications and Networking Conference, CCNC",

issn = "2331-9860",

}

TY - JOUR

T1 - Deep Learning Transceiver for Terahertz Band Communication System with 1-bit ADC and Oversampling

AU - Gemeda, Metasebia D.

AU - Han, Min S.

AU - Abebe, Ameha T.

AU - Kang, Chung G.

PY - 2022

Y1 - 2022

N2 - In this study, with the aim of reducing power consumption for terahertz band wireless communication, we present a deep learning-based solution for transceiver design with 1-bit quantization and oversampling at the receiver, and Faster- than-Nyquist transmission. Our simulation results illustrate that the studied system with 1-bit quantization achieves bit-error- rate performance comparable to that of an end-to-end channel autoencoder without the constraint of 1-bit quantization subject to the same spectral efficiency. It is also demonstrated that reliable communication can be achieved at rates exceeding 5.3 bits/sec/Hz which corresponds to 80% of the achievable capacity at adequate SNR.

AB - In this study, with the aim of reducing power consumption for terahertz band wireless communication, we present a deep learning-based solution for transceiver design with 1-bit quantization and oversampling at the receiver, and Faster- than-Nyquist transmission. Our simulation results illustrate that the studied system with 1-bit quantization achieves bit-error- rate performance comparable to that of an end-to-end channel autoencoder without the constraint of 1-bit quantization subject to the same spectral efficiency. It is also demonstrated that reliable communication can be achieved at rates exceeding 5.3 bits/sec/Hz which corresponds to 80% of the achievable capacity at adequate SNR.

KW - autoencoder

KW - deep learning

KW - one-bit-quantization

KW - oversampling

UR - http://www.scopus.com/inward/record.url?scp=85135728458&partnerID=8YFLogxK

U2 - 10.1109/CCNC49033.2022.9700716

DO - 10.1109/CCNC49033.2022.9700716

M3 - Conference article

AN - SCOPUS:85135728458

SN - 2331-9860

SP - 515

EP - 516

JO - Proceedings - IEEE Consumer Communications and Networking Conference, CCNC

JF - Proceedings - IEEE Consumer Communications and Networking Conference, CCNC

T2 - 19th IEEE Annual Consumer Communications and Networking Conference, CCNC 2022

Y2 - 8 January 2022 through 11 January 2022

ER -

Deep Learning Transceiver for Terahertz Band Communication System with 1-bit ADC and Oversampling

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this