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
학술대회자료
저자정보
Kwonin Yoon (Ulsan National Institute of Science and Technology (UNIST)) Jaemin Park (THYROSCOPE) Sungil Kim (Ulsan National Institute of Science and Technology (UNIST))
저널정보
대한산업공학회 대한산업공학회 추계학술대회 논문집 2021년 대한산업공학회 추계학술대회
발행연도
2021.11
수록면
1,860 - 1,886 (27page)

이용수

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

초록· 키워드

오류제보하기
With the increasing importance of maritime logistics, scheduling of resources has become a crucial factor for ensuring smooth port operations, considering the large number of stakeholders and resources related to a vessel and the complex and lengthy logistics involved. To optimize work plans and resources, real-time detection of anomalies is important because it allows stakeholders to plan ahead, considering the possible changes or delays in arrival, and to reduce waiting costs caused by delays. This paper proposes a VAE-based monitoring chart, VAE-CUSUM, based on a novel monitoring statistic combining a feature extracted from a variational autoencoder (VAE) and a monitoring statistic from a cumulative sum (CUSUM) control chart. The proposed method was validated using simulated and real-world automatic identification system (AIS) data concerning the trajectory of a vessel captured by a satellite. A comparison study was carried out with the existing benchmarks, which revealed a superior detection performance and robustness of the proposed method. Moreover, the reconstruction error and the reconstruction probability, obtained from the VAE, are compared as a monitoring statistic.

목차

Abstract
1. Introduction
2. Related Works
3. Methodology
4. Experimental Results
5. Discussion: Reconstruction Error versus Reconstruction Probability
6. Conclusion
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

이 논문의 저자 정보

최근 본 자료

전체보기

댓글(0)

0