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
- 이주홍
- 발행연도
- 2018
- 저작권
- 인하대학교 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
기존의 시계열 군집화 알고리즘들은 시계열의 동조화 관계를 찾는데 있어 적합하지 못
하다. 일반적으로 시계열을 생성하는 시스템은 시간의 흐름에 따라 시스템의 상태변수
들이 변하기 때문에 시계열의 동조화분석에 이를 고려해야 한다. 본 논문에서는 동조화
관계를 갖는 시계열 군집을 찾기 위해 CTC(Co-movement Time series Clustering)
알고리즘을 제안한다. 해당 알고리즘은 시간의 흐름에 따른 시계열 데이터의 중요도를
동조화분석에 고려하기 위하여 가중거리함수를 정의하였다. 또한 CTC알고리즘에 정제
과정을 포함하여 알고리즘에 의하여 생성된 군집에 동조화정도가 현저히 벗어나는 노이
즈 데이터가 포함되지 않도록 하였다. 실험을 통하여 동조화 관계를 갖는 시계열 군집
를 비교 알고리즘들 보다 더 잘 찾아주는 것을 보였다.
하다. 일반적으로 시계열을 생성하는 시스템은 시간의 흐름에 따라 시스템의 상태변수
들이 변하기 때문에 시계열의 동조화분석에 이를 고려해야 한다. 본 논문에서는 동조화
관계를 갖는 시계열 군집을 찾기 위해 CTC(Co-movement Time series Clustering)
알고리즘을 제안한다. 해당 알고리즘은 시간의 흐름에 따른 시계열 데이터의 중요도를
동조화분석에 고려하기 위하여 가중거리함수를 정의하였다. 또한 CTC알고리즘에 정제
과정을 포함하여 알고리즘에 의하여 생성된 군집에 동조화정도가 현저히 벗어나는 노이
즈 데이터가 포함되지 않도록 하였다. 실험을 통하여 동조화 관계를 갖는 시계열 군집
를 비교 알고리즘들 보다 더 잘 찾아주는 것을 보였다.
목차
제 1 장 서 론 ································································································································· 1제 2 장 관련 연구 ··························································································································· 3제 3 장 제안 모델 ··························································································································· 43.1 데이터 전처리 ··············································································································· 43.1.1 데이터 정규화 ······································································································ 43.1.2 차원 축소 ·············································································································· 53.2 클러스터링 ····················································································································· 63.2.1 사전군집화 ············································································································ 63.2.2 정 제 ······················································································································ 8제 4 장 실 험 ······························································································································ 104.1 차원 축소 방법 평가 ································································································· 104.2 알고리즘 비교 평가 ··································································································· 12제 5 장 참고 문헌 ······················································································································ 17
최근 본 자료
댓글(0)
0