http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
폴리부틸렌테레프탈레이트/유리섬유 복합재료의 열적 및 충격성질에 관한 연구 -유리섬유 함량 및 시험온도의 영향-
박헌진,호광일,Park, Heon-Jin,Ho, Gwang-Il 한국섬유공학회 1997 한국섬유공학회지 Vol.34 No.6
The thermal and impact behavior of poly(butylene terephthalate) (PBT) and its composites toughened with E-glass fiber were investigated at various testing temperatures. The crystallization rate of PBT composites was faster than that of pure PBT due to the nucleation agent role of glass fiber in the PBT melt, and the degree of crystallinity increased with glass fiber content regardless of testing temperatures. Notched Izod impact strength increased more rapidly at 1$25^{\circ}C$ and 175$^{\circ}C$ than at $25^{\circ}C$ and 75$^{\circ}C$. The fracture morphology and subsurface structure of specimens fractured by impact test were observed using SEM (Scanning Electron Microscope) and POM (Polarized Optical Microscope) . And the results were utilized to illuminate the relationship between morphology and impact properties. By the morphological analyses, plastic deformation in matrix, interfacial debonding phenomenon between matrix and glass fiber, and cavities that occurred by pulling out glass fiber from the matrix were observed on the fractured surfaces.
COPD 코호트 자료에서의 Machine Learning 방법론 비교
정현명,박헌진,이진국,이종민,Jeong, Hyeon-Myeong,Park, Heon-Jin,Rhee, Chin-Kook,Lee, Jong-min 한국빅데이터학회 2017 한국빅데이터학회 학회지 Vol.2 No.2
최근 머신러닝 방법은 높은 예측력과 함께 널리 이용되지만 머신러닝을 제대로 활용하기 위해서 데이터가 가진 한계를 통계적 기법으로 해결한다면 기존보다 더 높은 예측력을 이끌어 낼 수 있다. 본 연구에서는 Longitudinal and Imbalanced Data에서 SMOTE 방법을 활용하여 불균형 문제를 해결한 결과 예측력이 증가하는 것을 확인할 수 있었다. 추가적으로 만성폐쇄성폐질환 급성악화 관련 연구가 활발히 이루어지고 있지만 급성악화와 관련 있는 요인을 찾는 연구만 이루어지고 있어 여러 요인들에 대한 복합적인 관철과 예측모형을 통한 급성악화 예측 연구는 이루어지지 않는다. 본 연구에서는 여러 요인을 같이 살펴봤을 때 어떤 요인들이 만성폐쇄성폐질환 급성악화와 관련이 있는지 확인하고 개인 맞춤형 특정 질환 예측 모형을 구축하였다. Recently, Machine Learning Methods are widely used with high prediction performance. But if the limit of the data is solved by the statistical technique, It can, lead to higher prediction performance than the existing one. In this study, the SMOTE method is used to solve the imbalance problem in the longitudinal and imbalanced data. As a result, It, was confirmed that the prediction performance increases. Additionally, Although, studies on COPD have been actively conducted, only studies that are related to acute exacerbation have been conducted. So there are no studies on the prediction of acute exacerbation through multiple perspectives and predictive models for various factors. In this study, We examined the factors related to acute exacerbation of COPD and constructed a personalized specific disease prediction model.