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
Young-Chan Lee (Korea Maritime & Ocean Universiy) Mi-rae Kim (Korea Maritime & Ocean Universiy) HeeJoo Jang (Korea Maritime & Ocean Universiy) Tae-youl Jeon (Korea Maritime & Ocean Universiy)
저널정보
한국마린엔지니어링학회 Journal of Advanced Marine Engineering and Technology (JAMET) 한국마린엔지니어링학회지 제48권 제6호
발행연도
2024.12
수록면
502 - 509 (8page)
DOI
10.5916/jamet.2024.48.6.502

이용수

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

초록· 키워드

오류제보하기
This study addresses the challenges of ship spare parts management, a critical task for ensuring maritime safety and operational efficiency. Due to the large number of components and reliance on manual processes, inventory discrepancies often occur, increasing the risk of safety incidents. To address these challenges, this research investigates transfer learning algorithms for the classification of ship spare parts. Pre-trained models, including Xception, DenseNet-201, InceptionV3, and NASNet-Large, were finetuned using MATLAB with the ImageNet dataset. Among the models tested, DenseNet-201 demonstrated superior performance with the lowest loss function and the highest validation accuracy. Its dense connectivity structure proved effective in minimizing misclassifications and enhancing recognition accuracy. These findings suggest that DenseNet-201 is the most suitable model for ship spare parts classification. Future work will focus on developing a real-time spare parts management system incorporating this model. The system aims to optimize operational efficiency, reduce human error, and adapt to changing requirements through automated alerts and reporting functionalities.

목차

Abstract
1. Introduction
2. Current Status and Regulations for Ship Spare Parts Management
3. Proposed Model for Ship Spare Parts Management Using Transfer Learning
4. Model Training and Results
5. Conclusion
References

참고문헌 (0)

참고문헌 신청

이 논문과 함께 이용한 논문

최근 본 자료

전체보기

댓글(0)

0

UCI(KEPA) : I410-151-25-02-092105022