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
Taek-Ho Lee (POSTECH) Chi-Hyuck Jun (POSTECH)
저널정보
한국경영과학회 한국경영과학회 학술대회논문집 한국경영과학회 2016년 춘계공동학술대회 논문집
발행연도
2016.4
수록면
4,688 - 4,692 (5page)

이용수

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

이 논문의 연구 히스토리 (2)

초록· 키워드

오류제보하기
Diabetes is one of the major chronic diseases. The death rate from diabetes is more and more increasing, so causing the financial burdens of the nation to increase. Because chronic diseases, if occur, require continuous management and they are hard to be completely cured, it is important to predict its occurrence in advance. Our goal is to make diabetes risk prediction model based on machine learning techniques using database established by Korean National Health Insurance Corporation. The procedure to build the prediction model consists of two phases, i.e., ‘variable selection’ to find significant factors of diabetes and ‘learning classifier’ to learn a statistical risk prediction model. For the former, we apply correlationbased feature selection, minimum redundancy maximum relevance, classification and regression tree (CART) variable importance, and support vector machine (SVM)-recursive feature elimination. On the other hand, we apply logistic regression, linear discriminant analysis, CART, naïve Bayes (NB), and SVM for the latter. For the purpose of comparison, we conducted numerical experiments for the combinations of each variable selection method and classifier. As a result, the variable selection methods give somewhat consistent results. In the result of performance comparison, no significant difference has been observed among 5 classifiers except NB which showed poor performance.

목차

Abstract
1. Introduction
2. Methods: Variable Selection
3. Methods: Classification
4. Data and Pre-Processing
5. Result
6. Conclusion
7. Acknowledgement
8. Reference

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

UCI(KEPA) : I410-ECN-0101-2018-020-000857279