지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 지도교수
- 이유태
- 발행연도
- 2022
- 저작권
- 동의대학교 논문은 저작권에 의해 보호받습니다.
이용수1
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
최근 이동통신, 디지털 멀티미디어 방송(Digital Multimedia Broadcasting : DMB) 뿐만 아니라, 유비쿼터스 센서 네트워크(Ubiquitous Sensor Network : USN) 와 같은 무선 통신시스템 기술이 발달하면서 주파수 수요가 빠르게 증가하고 있다. 주파수 비점유 시간 동안 다른 사용자가 주파수를 활용하여 효율적으로 운용할 수 있는 방안 으로 인지 무선(Cognitive Radio : CR) 기술이 제안되었다.
인지 무선망은 주 사용자(Primary User : PU)의 점유/비점유 시간을 분석하여 비점유 시간 동안 부 사용자(Secondary User : SU)가 사용할 수 있도록 만든 기술이다. 점유/비점유 시간은 스펙트럼 센싱 기법으로 알 수 있다.
본 연구에서는 순환 신경망을 활용한 인지 무선망 접속 기법을 다룬다. 원활한 인지 무선 주파수 사용을 위해 인지 무선망에서는 주파수 결과 데이터를 기반으로 순환 신경망을 활용하여 주 사용자가 주파수를 점유하지 않은 시점을 예측하고자 한다. 순환 신경망의 LSTM(Long Short Term Memory), GRU(Gate Recurrent Unit) 모델을 사용하여 주 사용자가 주파수를 점유하지 않은 시점을 비교적 높은 정확도로 예측할 수 있다.
인지 무선망은 주 사용자(Primary User : PU)의 점유/비점유 시간을 분석하여 비점유 시간 동안 부 사용자(Secondary User : SU)가 사용할 수 있도록 만든 기술이다. 점유/비점유 시간은 스펙트럼 센싱 기법으로 알 수 있다.
본 연구에서는 순환 신경망을 활용한 인지 무선망 접속 기법을 다룬다. 원활한 인지 무선 주파수 사용을 위해 인지 무선망에서는 주파수 결과 데이터를 기반으로 순환 신경망을 활용하여 주 사용자가 주파수를 점유하지 않은 시점을 예측하고자 한다. 순환 신경망의 LSTM(Long Short Term Memory), GRU(Gate Recurrent Unit) 모델을 사용하여 주 사용자가 주파수를 점유하지 않은 시점을 비교적 높은 정확도로 예측할 수 있다.
목차
제 1장 서 론 ···························································································· 1제 2 장 인지 무선망(Cognitive Radio) ··············································· 32.1 인지 무선망 기술 ······················································································· 3제 3 장 딥러닝(Deep Learning) ··························································· 63.1 퍼셉트론(Perceptron) ························································································ 73.2 순환신경망(Recurrent Neural Network) ····················································· 113.3 LSTM(Long Short Term Memory) ································································ 123.4 GRU(Gate Recurrent Unit) ············································································ 14제 4 장 모의실험 ·················································································· 164.1 데이터 ················································································································ 164.2 실험 및 분석 ···································································································· 16제 5 장 결론 ·························································································· 24참 고 문 헌 ···························································································· 25ABSTRACT ······························································································ 27감사의 글 ······························································································ 28
최근 본 자료
댓글(0)
0