Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

딥러닝을 이용한 동일 주파수 대역에 공존하는 통신 및 레이더 신호 분리Separation of Coexisting Communication and Radar Signals within the Same Frequency Band Using Deep Learning

Other Titles
Separation of Coexisting Communication and Radar Signals within the Same Frequency Band Using Deep Learning
Authors
정석현남해운
Issue Date
Apr-2025
Publisher
한국통신학회
Keywords
Deep learning; Communication signal; Radar signal; Interference; Frequency overlap; Signal separation; U-Net; Conv-TasNet
Citation
한국통신학회논문지, v.49, no.4, pp 611 - 615
Pages
5
Indexed
SCOPUS
KCI
Journal Title
한국통신학회논문지
Volume
49
Number
4
Start Page
611
End Page
615
URI
https://scholarworks.bwise.kr/erica/handle/2021.sw.erica/125350
DOI
10.7840/kics.2025.50.4.611
ISSN
1226-4717
2287-3880
Abstract
통신 신호와 레이더 신호가 동일 주파수 대역에서공존할 때 신호 중첩으로 인한 간섭이 불가피하게 발생하는데, 이로 인해 통신의 품질이 저하된다. 기존의주파수 필터링 방식은 주파수가 완전히 겹치는 상황에서 성능이 제한적이므로, 이를 해결하기 위해 딥러닝 기반 접근법이 주목받고 있다. 본 논문에서는 중첩된 통신 및 레이더 신호를 분리하기 위해 딥러닝모델인 U-Net과 Conv-TasNet을 사용하여 비트 오류율(Bit Error Rate, BER)을 통해 성능을 비교하였다. 실험 결과, 전반적으로 Conv-TasNet 방식이 U-Net 방식에 비해 BER이 낮게 나타났지만, 신호 대 간섭비(Signal-to-Interference Ratio, SIR)가 낮은 환경에서는 U-Net의 BER이 더 낮게 나타났다.
When communication signals and radar signals coexist in the same frequency band, interference due to signal overlap inevitably occurs, resulting in degraded communication quality. Traditional frequency filtering methods are limited in performance when the frequencies completely overlap, which has led to the growing attention towards deep learning-based approaches. In this paper, U-Net and Conv-TasNet, deep learning models, are used to separate the overlapped communication and radar signals, and their performance is compared in terms of Bit Error Rate (BER). The experimental results show that, overall, the Conv-TasNet approach yields a lower BER than the U-Net approach. However, in environments with low Signal-to-Interference Ratio (SIR), U-Net shows a lower BER than Conv-TasNet.
Files in This Item
Go to Link
Appears in
Collections
COLLEGE OF ENGINEERING SCIENCES > SCHOOL OF ELECTRICAL ENGINEERING > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Nam, Hae woon photo

Nam, Hae woon
ERICA 공학대학 (SCHOOL OF ELECTRICAL ENGINEERING)
Read more

Altmetrics

Total Views & Downloads

BROWSE