• Biomolecules & Therapeutics
• /
• 제21권6호
• /
• pp.470-475
• /
• 2013

Ultraviolet (UV) radiation is a major environmental factor that leads to acute and chronic reactions in the human skin. UV exposure induces wrinkle formation, DNA damage, and generation of reactive oxygen species (ROS). Most mechanistic studies of skin physiology and pharmacology related with UV-irradiated skin have focused on proteins and their related gene expression or single-targeted small molecules. The present study identified and analyzed the alteration of skin metabolites following UVB irradiation and topical retinyl palmitate (RP, 5%) treatment in hairless mice using direct analysis in real time (DART) time-of-flight mass spectrometry (TOF-MS) with multivariate analysis. Under the negative ion mode, the DART ion source successfully ionized various fatty acids including palmitoleic and linolenic acid. From DART-TOF-MS fingerprints measured in positive mode, the prominent dehydrated ion peak (m/z: 369, M+H-$H_2O$) of cholesterol was characterized in all three groups. In positive mode, the discrimination among three groups was much clearer than that in negative mode by using multivariate analysis of orthogonal partial-least squares-discriminant analysis (OPLS-DA). DART-TOF-MS can ionize various small organic molecules in living tissues and is an efficient alternative analytical tool for acquiring full chemical fingerprints from living tissues without requiring sample preparation. DART-MS measurement of skin tissue with multivariate analysis proved to be a powerful method to discriminate between experimental groups and to find biomarkers for various experiment models in skin dermatological research.

• Asian-Australasian Journal of Animal Sciences
• /
• 제31권11호
• /
• pp.1700-1713
• /
• 2018

Objective: The aim of this study was to verify the usefulness of artificial neural networks (ANN), multivariate adaptive regression splines (MARS), naïve Bayes classifier (NBC), general discriminant analysis (GDA), and logistic regression (LR) for dystocia detection in Polish Holstein-Friesian Black-and-White heifers and cows and to indicate the most influential predictors of calving difficulty. Methods: A total of 1,342 and 1,699 calving records including six categorical and four continuous predictors were used. Calving category (difficult vs easy or difficult, moderate and easy) was the dependent variable. Results: The maximum sensitivity, specificity and accuracy achieved for heifers on the independent test set were 0.855 (for ANN), 0.969 (for NBC), and 0.813 (for GDA), respectively, whereas the values for cows were 0.600 (for ANN), 1.000 and 0.965 (for NBC, GDA, and LR), respectively. With the three categories of calving difficulty, the maximum overall accuracy for heifers and cows was 0.589 (for MARS) and 0.649 (for ANN), respectively. The most influential predictors for heifers were an average calving difficulty score for the dam's sire, calving age and the mean yield of the farm, where the heifer was kept, whereas for cows, these additionally included: calf sex, the difficulty of the preceding calving, and the mean daily milk yield for the preceding lactation. Conclusion: The potential application of the investigated models in dairy cattle farming requires, however, their further improvement in order to reduce the rate of dystocia misdiagnosis and to increase detection reliability.

• 인터넷정보학회논문지
• /
• 제7권1호
• /
• pp.75-89
• /
• 2006

본 연구는 IMF후에 도산한 기업을 대상으로 다변량판별분석 모형, 확률모형(로짓분석모형) 그리고 인공신경망 모형을 개발하여 각 모형의 도산예측력을 비교하고 인공신경망 모형의 일반화 가능성을 높이는데 목적이 있다. 본 연구는 도산예측 모형간의 예측력 비교 측면에서는 기존 연구와 유사하나 연구표본을 IMF후에 도산한 기업으로 하여 도산예측력을 향상시키고 모형의 일반화 가능성을 높이기 위해 상장회사 중 동일한 업종인 제조업종에 한정하여 모형을 개발한다는 측면에서 기존 연구와 차이가 있다고 할 수 있다. 또한, 보다 의미있는 연구를 위하여 학습용 표본과 검증용 표본을 동일한 기간에서 추출하지 않고 검증용 표본을 학습용 표본기간 이후의 기간에서 추출하여 도산예측의 타당성을 현재가 아닌 미래의 시점에서 검증함으로써, 개발한 모형이 미래의 환경변화에 적응력을 보이는지를 분석하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권3호
• /
• pp.473-483
• /
• 2014

ROC 곡선과 ROC 곡면을 확장한 4차원 이상의 공간에서의 ROC 다면체는 시각적인 표현이 어렵기 때문에 활용하기 어려우나, ROC 다면체 아래 공간을 측정하는 HUM 통계량에 대하여는 AUC와 VUS 통계량을 기반으로 정의가 가능하고 값을 구할 수 있으므로 본 연구는 네 가지 범주의 분류모형의 판별력을 측정하는 확률을 정의하고 연구한다. 그리고 Basel II를 기반한 부도확률에 대한 AUC의 판별력 판단기준을 제안한 연구를 확장하여, 네 범주 분류모형의 판별력을 측정하는 HUM 통계량에 관한 판단기준을 13단계로 구분하여 제안하고 활용하는 방법을 설명한다. 다양한 분포함수에 대하여 얻은 HUM 값을 바탕으로 제안한 판단기준을 탐색하기 위하여 삼원구획그림을 활용하여 판단기준을 설명한다.

• 응용통계연구
• /
• 제32권4호
• /
• pp.593-605
• /
• 2019

ROC 곡선 아래 면적과 ROC 곡면 아래 부피를 이용하여 분류모형의 판별력을 측정하는 통계량인 AUC와 VUS에 관한 많은 연구가 있다. ROC 곡선을 구성하는 FPR과 TPR 모두에 제한을 두는 양방향 부분 AUC는 부분 AUC보다 더 효과적이고 정확하게 제안되었다. ROC 곡면에서도 부분 VUS 뿐만 아니라 세 방향 부분 VUS 통계량이 개발되었다. 본 연구에서는 ROC 곡선의 FPR과 TPR 모두에 제한된 두 개의 절단함수를 이용하여 확률 개념과 적분 표현으로 대안적인 AUC를 제안한다. 또한 이 AUC는 양방향 부분 AUC와 관계가 있음을 알 수 있다. ROC 곡면에서의 세 방향 부분 VUS도 절단함수를 이용하는 VUS와 관련되어 있음을 발견하였다. 그리고 이러한 대안적인 AUC와 VUS는 맨-휘트니 통계량으로 표현되고 추정된다. 정규분포와 확률표본을 기반으로 이들의 모수적인 추정 방법과 비모수적인 추정 방법을 탐색한다.

• Journal of Korea Trade
• /
• 제26권1호
• /
• pp.57-80
• /
• 2022

Purpose - This study aims to examine the relationships between the acceptance of the 4th industrial revolution logistics technology, logistics safety behavior, and logistics safety performance, as well as the moderated mediating effects of logistics safety behavior through safety culture in Korea. Design/methodology - Research models and hypotheses were established based on prior research related to the 4th industrial revolution logistics technology, logistics safety, and logistics performance. The survey was conducted on the employees of logistics companies, and reliability analysis, confirmatory factor analysis, discriminant validity analysis, structural equation model analysis, and mediating effect analysis were performed. In addition, the moderated mediating effect analysis applying SPSS Process Model No. 7 was conducted. Findings - Usefulness and sociality of the acceptance of the 4th industrial revolution logistics technology had a significant effect on logistics safety behavior. Ease of use, sociality, and efficiency had meaningful effect on logistics safety performance. And in the relationships between the acceptance of logistics technology and logistics safety performance, logistics safety behavior had a significant mediating effect. But the moderated mediating effect of safety behavior through safety culture was not significant. Logistics companies can improve logistics safety performance through the utilization of new logistics technologies such as intelligent logistics robots, autonomous driving technology, and artificial intelligence, etc. Originality/value - This is the first study to analyze the relationships between the acceptance of logistics technology in the 4th industrial revolution and logistics safety. In addition, previous studies analyzed mediating effects or moderating effects, but this is the first study to identify the moderated mediating effects of safety behavior through safety culture. In other words, it has originality in terms of research methodology.

• 대한토목학회논문집
• /
• 제26권3D호
• /
• pp.535-540
• /
• 2006

본 논문에서는 고해상도 컬러 입체영상을 활용하여 도심지역의 3차원 건물정보를 효율적으로 복원하기 위한 일련의 처리방법을 제안하고자 한다. 본 연구에서 제안된 방법은 BDT 기법을 활용한 건물 추출, Hausdorff 거리와 컬러인덱싱 기법을 활용한 영상정합, 마지막으로 사진측량기법을 활용한 건물복원 등의 3단계의 처리과정을 포함하고 있다. 제안된 알고리즘의 실험은 고해상도 위성영상의 대표격인 IKONOS 컬러 입체영상을 대상으로 수행되었으며, 실험을 통해 건물추출에 있어서 영상의 배경부분과 건물부분의 밝기값의 분산을 증가시키는 BDT 기법이 건물추출에 우수함을 확인할 수 있었다. 또한, 2가지 건물인식기법을 활용한 영상정합 과정에 있어서도 컬러정보와 경계정보를 모두 사용할 경우 대부분의 추출건물들을 자동인식하고 이를 초기위치로 원활한 영상정합이 수행될 수 있음을 확인하였다. 최종적으로 실험지역에 대한 3차원 건물정보는 전방 다항식비례모형을 통해 획득되었으며 기준자료와의 비교를 통해 정확도 분석을 수행하였다.

• 경영정보학연구
• /
• 제16권3호
• /
• pp.161-177
• /
• 2014

기업신용등급은 금융시장의 신뢰를 구축하고 거래를 활성화하는데 있어 매우 중요한 요소로서, 오래 전부터 학계에서는 보다 정확한 기업신용등급 예측을 가능케 하는 다양한 모형들을 연구해 왔다. 구체적으로 다중판별분석(Multiple Discriminant Analysis, MDA)이나 다항 로지스틱 회귀분석(multinomial logistic regression analysis, MLOGIT)과 같은 통계기법을 비롯해, 인공신경망(Artificial Neural Networks, ANN), 사례기반추론(Case-based Reasoning, CBR), 그리고 다분류 문제해결을 위해 확장된 다분류 Support Vector Machines(Multiclass SVM)에 이르기까지 다양한 기법들이 학자들에 의해 적용되었는데, 최근의 연구결과들에 따르면 이 중에서도 다분류 SVM이 가장 우수한 예측성과를 보이고 있는 것으로 보고되고 있다. 본 연구에서는 이러한 다분류 SVM의 성능을 한 단계 더 개선하기 위한 대안으로 유전자 알고리즘(GA, Genetic Algorithm)을 활용한 최적화 모형을 제안한다. 구체적으로 본 연구의 제안모형은 유전자 알고리즘을 활용해 다분류 SVM에 적용되어야 할 최적의 커널 함수 파라미터값들과 최적의 입력변수 집합(feature subset)을 탐색하도록 설계되었다. 실제 데이터셋을 활용해 제안모형을 적용해 본 결과, MDA나 MLOGIT, CBR, ANN과 같은 기존 인공지능/데이터마이닝 기법들은 물론 지금까지 가장 우수한 예측성과를 보이는 것으로 알려져 있던 전통적인 다분류 SVM 보다도 제안모형이 더 우수한 예측성과를 보임을 확인할 수 있었다.

• Asia pacific journal of information systems
• /
• 제18권3호
• /
• pp.67-90
• /
• 2008

Prior to making choices among online products and services, consumers often search online product reviews written by other consumers. Online product reviews have great influences on consumer behavior because they are believed to be more reliable than information provided by sellers. However, ever-increasing lists of product reviews make it difficult for consumers to find the right information efficiently. A customized search mechanism is a method to provide personalized information which fits the user's requirements. This study examines effects of a customized search mechanism and perceived similarity between consumers and product reviewers on consumer behaviors. More specifically, we address the following research questions: (1) Can a customized search mechanism increase perceived similarity between product review authors and readers? (2) Are product reviews perceived as more credible when product reviews were written by the authors perceived similar to them? (3) Does credibility of product reviews have a positive impact on acceptance of product reviews? (4) Does acceptance of product reviews have an influence on purchase intention of the readers? To examine these research questions, a lab experiment with a between-subject factor (whether a customized search mechanism is provided or not) design was employed. In order to enhance mundane realism and increase generalizability of the findings, the experiment sites were built based on a real online store, cherrya.com (http://www.cherrya.com/). Sixty participants were drawn from a pool that consisted of undergraduate and graduate students in a large university. Participation was voluntary; all the participants received 5,000 won to encourage their motivation and involvement in the experiment tasks. In addition, 15 participants, who selected by a random draw, received 30,000 won to actually purchase the product that he or she decided to buy during the experiment. Of the 60 participants, 25 were male and 35 were female. In examining the homogeneity between the two groups, the results of t-tests revealed no significant difference in gender, age, academic years, online shopping experience, and Internet usage. To test our research model, we completed tests of the measurement models and the structural models using PLS Graph version 3.00. The analysis confirmed individual item reliability, internal consistency, and discriminant validity of measurements. The results show that participants feel more credible when product reviews were written by the authors perceived similar to them, credibility of product reviews have a positive impact on acceptance of product reviews, and acceptance of product reviews have an influence on purchase intention of the readers. However, a customized search mechanism did not increase perceived similarity between product review authors and readers. The results imply that there is an urgent need to develop a better customized search tool in order to increase perceived similarity between product review authors and readers.

• 유통과학연구
• /
• 제11권10호
• /
• pp.17-25
• /
• 2013

Purpose - This study analyzes the effect of customers' perceived service innovativeness of service centers for electronic goods, on repurchase intentions of customers, using behavior intentions of service centers as a mediator variable. In customer management and customer relationship marketing, service centers can be the most representative customer relationship management departments because they are most closely placed at the interface with customers. In addition, this study intends to investigate if continuous relationship with customers during one-time product-selling can affect their repurchase intentions. Specifically, this research aims to investigate if the expansion of the saturated physical market of the manufacturing business, to intangible service markets, can be competitive enough to satisfy customer needs. Research design, data, and methodology - This study targets college students, and especially those who have computers, digital cameras, or cell-phones, and often use electronic products and services. In order to investigate our hypothesis, we analyzed dates through SEM (structural equation modeling) using SPSS for Windows 18.0 and AMOS 18.0. In addition, we measured Cronbach's α coefficient using SPSS for Windows 18.0 in order to measure reliability. Further, using AMOS 18.0, this research statistically measured convergent validity as well as discriminant validity, and examined mediation models and path models in which service innovativeness leads to customers' repurchase intentions of electronic products. Results - As a result, this research shows that customers' perceived service innovativeness of service centers for electronic goods has significant positive influence on customers' behavior intentions of service centers. In addition, service innovativeness of electronic goods' service centers also has significant positive influence on repurchase intentions of customers. Conclusion - This study investigates the effect of customers' positive relation with the innovativeness of electronic service center on their behavior intention and product repurchase. The more concrete, important results of the study are as follows. Through the mediating effect, the findings of the study suggest that customers' behavior intentions of service centers partially mediate the effect of customers'perceived service innovativeness of service centers for electronic goods on customers' repurchase intentions. This research also provides an insight that the importance of service innovativeness and innovative approaches in managing customers should be recognized in the process of repurchase and service roles of manufacturing business as a way for customer management. As a result, the relationship between customer satisfaction and service quality of service centers for the electronic products is very sensitive. Although previous studies focus on certain aspects of the case for enhancing service innovation (Kim, 2012), this research recommends that the service centers need to understand the customers'desire first and try to adapt to achieve customer satisfaction by being innovative. This innovativeness of service centers would make customers visit them consistently, which in the long run, will also influence their repurchase decisions.