http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
전종화,조성진,채명호,Jeon, Jonghwa,Jo, Sungjin,Chae, Myoungho 한국군사과학기술학회 2020 한국군사과학기술학회지 Vol.23 No.1
In this paper, a 2-dimensional phase comparison direction finding receiver was designed and fabricated. For 2-D comparison direction finding, direction finding formulas were derived from a uniformly arranged of four antennas. Based on this, a direction finding receiver was designed using Matlab simulink, and the direction finding receiver was fabricated. To analyze the performance of the designed direction finding receiver, the injection direction finding accuracy and simulation results were compared. As a result of the test, the fabricated direction finding receiver showed a maximum of 3° RMS precision, and the result of both tests showed similar trends. Also, it was confirmed that the direction finding accuracy of elevation angle is about 2.7 times better than azimuth angle, and both models performed well within 0.7° RMS at the boresight.
Vision Transformer를 이용한 자동변조인식 기술
이민주(Minju Lee),채명호(Myoungho Chae),임완수(Wansu Lim) 한국통신학회 2024 韓國通信學會論文誌 Vol.49 No.8
자동변조인식 (AMR, Automatic Modulation Recognition)은 무선 통신 시스템에서 핵심적인 역할을 하는 기술로, 데이터 통신의 효율성 향상 및 무선 통신 시스템의 신뢰성과 보안 강화에 기여한다. 최근 딥러닝 기술 발전으로 AMR 분야도 딥러닝을 활용하여 변조 인식 성능을 향상하는 연구가 매우 활발히 수행되고 있다. 이에 본 논문은 시계열 이미지 데이터 처리 능력이 뛰어난 ViT (Vision Transformer) 모델 기반 AMR 기술을 제안한다. ViT 모델은 입력 이미지를 작은 이미지 단위인 패치로 나눈 후, 각 패치에 순서를 할당하여 Transformer Encoder의 입력으로 사용한다. ViT 기반 AMR 모델은 각 변조 방식의 성상도를 학습하여 변조 방식을 인식한다. 제안한 변조 인식 기법은 낮은 SNR에서도 변조 인식 정확도가 평균 약 2% 향상되었다. Automatic Modulation Recognition (AMR) is a technology that plays a key role in wireless communication systems, contributing to improving the efficiency of data communication and enhancing the reliability and security of wireless communication systems. Recently, due to the development of deep learning technology, research using deep learning has been actively conducted in the field of AMR. In this paper, we propose an AMR technique based on the ViT (Vision Transformer) model, which has excellent time series data processing capabilities. The ViT model divides the input image into patches, which are small image units, and assigns an order to each patch, which is used as an input to the transformer encoder. By doing so, the ViT-based AMR model learns the characteristics of each modulation scheme and automatically recognizes the modulation scheme. By using the ViT-based AMR model, we were able to achieve an average classification accuracy improvement of about 2% even at low SNR.