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
- 이석훈
- 발행연도
- 2018
- 저작권
- 충남대학교 논문은 저작권에 의해 보호받습니다.
이용수6
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
As interest in health and quality of life has increased, interest in dietary therapy has increased along with the interest in the classification of constitution. Constitutional medicine says that prevention and treatment should be different depending on the inherited constitution. Diet therapy, which is particularly important in constitutional medicine, is to consume foods by separating beneficial and harmful foods according to their natural constitution. However, the criteria for differentiating beneficial and harmful foods have not yet been scientifically clarified. The characteristics of food used in this study were based on the nutritional characteristics and the characteristics explained in Oriental medicine. We analyze how the benefits and harms of food can be explained by these characteristics through decision trees, logistic regression models, ensemble models, and neural network models. Among the classification models, the prediction accuracy was high in the random forest, an ensemble model with the highest accuracy 83.52% for 71.44% the lowest. Among the characteristics of food, food nutritional characteristics have more influence on classification than oriental medicine which is difficult to explain objectively. The results of the analysis suggest that nutritional characteristics of the foods recommended by constitutional medical experts may be useful for research.
목차
1. 서론 ······················································································································12. 연구 동향과 연구 방법 ··················································································62.1 체질 관련 관심도·····················································································62.2 선행 연구 동향·························································································82.3 연구 방법·································································································103. 연구 대상 자료 ·······························································································153.1 자료 수집 과정·······················································································153.2 연구 자료 구성·······················································································194. 자료 탐색 ·········································································································244.1 체질별 자료 탐색···················································································244.2 독립 변수들 간의 자료 탐색·······························································314.3 자료 분석에 사용한 독립변수·····························································355. 자료 분석 ·········································································································365.1 의사결정나무···························································································365.2 로지스틱 회귀 모형···············································································455.3 앙상블 모형·····························································································565.4 서포트 벡터 머신···················································································645.5 신경망 모형·····························································································655.6 로지스틱 회귀모형의 체질별 예측 확률을 반영한 모형···············705.7 새로운 식품에 대한 체질별 유익여부 예측·····································726. 결론 및 고찰 ···································································································74참 고 문 헌 ···········································································································76
최근 본 자료
댓글(0)
0