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
Chaejin Lim (Sejong University) Junhee Hyeon (Sejong University) Kiseong Lee (Sejong University) Dongil Han (Sejong University)
저널정보
대한전자공학회 대한전자공학회 학술대회 2024년도 대한전자공학회 하계학술대회 논문집
발행연도
2024.6
수록면
1,890 - 1,894 (5page)

이용수

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

초록· 키워드

오류제보하기
Support Vector Machine (SVM) is an algorithm that finds the decision boundary that best separates classes in each feature space. However, traditional SVM models have the drawback of requiring manual feature extraction. Recently, there has been an increasing trend of using deep learning models for feature extraction while employing SVM as the classifier. Nevertheless, using a linear layer for classification remains much more common. This study demonstrates that using SVM as the classifier improves classification performance compared to using a generic linear layer. We also investigate the impact of the feature extractor"s performance on the classifier. Although it may be theoretically obvious that better feature extraction leads to improved classification, directly validating this through research can be a valuable exploration. We use NCT CRC-HE data and plant data collected outside the laboratory to examine the performance of the feature extractor and the impact of the presence or absence of SVM. This study provides insights not only into the classification task but also into the backbone and head of the model. By investigating the relationship between the quality of the feature extractor and the performance of SVM, our research aims to contribute to a better understanding of the interplay between these components in classification tasks.

목차

Abstract
Ⅰ. Introduction
Ⅱ. Background
Ⅲ. Implementation
Ⅳ. Conclusion
Reference

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

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

최근 본 자료

전체보기

댓글(0)

0