메뉴 건너뛰기
.. 내서재 .. 알림
소속 기관/학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술저널
저자정보
유승수 (건국대학교)
저널정보
제어로봇시스템학회 제어로봇시스템학회 논문지 제어로봇시스템학회 논문지 제26권 제11호
발행연도
2020.11
수록면
1,016 - 1,027 (12page)
DOI
10.5302/J.ICROS.2020.20.0112

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
In this paper, we propose an improved global navigation satellite system (GNSS) jamming classification scheme using a convolutional neural network that directly uses an intermediate frequency (IF) sampled GNSS received signal without pre-processing. The machine learning-based GNSS jamming classification scheme recently proposed in [17] requires a short-time Fourier transform (STFT) process and a binary black-and-white image processing process through image mapping of the obtained spectrogram. The average jamming classification accuracy of the conventional scheme is approximately 94.31%, where the maximum, average, and minimum classification accuracies for single frequency modulation (FM) jamming are as low as approximately 89.55%, 83.43%, and 77.61%, respectively. The major performance deterioration factor of the conventional scheme is information loss caused by the pre-processing for the designed machine learning technique. To tackle this problem, we construct a sophisticated convolutional neural network (CNN) that directly uses the IF sampled GNSS received signal without pre-processing the conventional scheme. To evaluate the performance of the proposed scheme, the confusion matrix of the jamming classification between the conventional and the proposed schemes is compared and analyzed by Monte-Carlo simulation using 106 test samples in five representative jamming environments with no jamming. As a result of the simulation, the average jamming classification accuracy of the proposed scheme is approximately 99.41%, which improves the classification accuracy by 5.1% compared with that achieved by the conventional scheme. Additionally, the average classification accuracy of 99.07% is dramatically improved by 15.64% compared with that achieved by the conventional scheme.

목차

Abstract
I. 서론
II. 수신 신호와 재밍 신호 모형
III. 기존 기법 [17]
IV. 제안한 기법
V. 모의실험과 성능분석
VI. 결론
REFERENCES

참고문헌 (17)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

이 논문의 저자 정보

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-ECN-0101-2020-003-001571167