• Communications for Statistical Applications and Methods
• /
• 제25권3호
• /
• pp.297-306
• /
• 2018

Cardiovascular disease (CVD) is the leading cause of death worldwide and has a high mortality rate after onset; therefore, the CVD management requires the development of treatment plans and the prediction of prevalence rates. In our study, age, income, education level, marriage status, diabetes, and obesity were identified as risk factors for CVD. Using these 6 factors, we proposed a nomogram based on a $na{\ddot{i}}ve$ Bayesian classifier model for CVD. The attributes for each factor were assigned point values between -100 and 100 by Bayes' theorem, and the negative or positive attributes for CVD were represented to the values. Additionally, the prevalence rate can be calculated even in cases with some missing attribute values. A receiver operation characteristic (ROC) curve and calibration plot verified the nomogram. Consequently, when the attribute values for these risk factors are known, the prevalence rate for CVD can be predicted using the proposed nomogram based on a $na{\ddot{i}}ve$ Bayesian classifier model.

• 한국컴퓨터정보학회논문지
• /
• 제21권12호
• /
• pp.115-124
• /
• 2016

In this paper, a method to generate the extended model automatically on the critical elements in enterprise system based real time distributed architecture as well as the platform specific model(PSM) for Microsoft(MS) .NET platform is proposed. The key ideas of this method are real time distributed architecture should performed with satisfying strict constraints on life cycle of object and response time such as synchronization, transaction and so on, and .NET platform is able to implement functionalities including before mentioned by only specifying Attribute Code and maximizing advantages of MDA. In order to realize the ideas, functionalities which should be considered enterprise system development are specified and these are to be defined in Meta Model and extended UML profile. In addition, after definition of UML profile for .NET specification, by developing and applying these into plug-in of open source MDA tool, and extended models are generated automatically through this tool. Accordingly, by using proposed specification technology, the profile and tools easily and quickly reusable extended model can be generated even though low level of detailed information for functionalities which is considered in .NET platform and real time distributed architecture. In addition, because proposed profile is MOF which is basis of standard extended and applied, UML and MDA tools which observed MOF is reusable.

• 간호행정학회지
• /
• 제10권4호
• /
• pp.473-484
• /
• 2004

Purpose: This study was performed to investigate the perception gap about the factor of nursing service quality and the hospital revisiting intend between consumers and providers. Method: The questionnaire was developed and distributed to 300 patients and 210 nurses at the three general hospitals in three provincial city, Korea. For data analysis, SPSS/PC program was used. Result: the 20 attributes of nursing service are perceived as satisfaction factors by consumers and the 14 attributes are by providers. No attributes is perceived as hygiene factor by consumers and providers. The gender of consumers' demographic characteristics has a significant difference and don't have affection for hospital revisiting intent, and the position and education level of providers' demographic characteristics have a significant difference and explain 4.5% of hospital revisiting intent. The 12 attributes of nursing service by consumers and 3 attributes by providers correlate to hospital revisiting intent, and the only 'nurse's sincerely attitude' attribute in consumers and the only 'credible nursing service' attribute in providers explain of hospital revisiting intent. Conclusion: there are definitely perception gap between consumers and providers. So nursing organization have to recognize and try to overcome these perception gaps.

• 응용통계연구
• /
• 제28권1호
• /
• pp.75-82
• /
• 2015

본 연구에서는 민감한 이항특성에 대한 신뢰구간 추정에 직접질문법과 간접질문법을 사용한다. 간접질문법으로 응답자들의 응답부담을 줄여주기 위해서 확률장치를 사용하는 Warner (1965)의 확률화응답기법(RRT)을 고려한다. 두 방법에 의한 신뢰구간을 비교하기 위해서 평가기준으로 평균포함확률(MCP), 평균제곱오차의 제곱근(RMSE), 그리고 평균기대폭(MEW)을 사용한다. 수치적 비교 결과 RRT의 MCP가 명목수준()을 크게 초과하여 보수적이고 MEW도 매우 크다. 따라서 이들을 보완해 주어야 실제적으로 간접질문법의 유용성을 높일 수 있다.

• 한국정밀공학회지
• /
• 제21권9호
• /
• pp.85-94
• /
• 2004

As over 70% of the total life cycle cost (LCC) of a product is committed at the early design stage, designers are in an important position to substantially reduce the LCC of the products they design by giving due to life cycle implications of their design decisions. During early design stages, there may be competing concepts with dramatic differences. In addition, the detailed information is scarce and decisions must be made quickly. Thus, both the overhead in developing parametric LCC models fur a wide range of concepts, and the lack of detailed information make the application of traditional LCC models impractical. A different approach is needed, because a traditional LCC method is to be incorporated in the very early design stages. This paper explores an approximate method for providing the preliminary LCC, Learning algorithms trained to use the known characteristics of existing products might allow the LCC of new products to be approximated quickly during the conceptual design phase without the overhead of defining new LCC models. Artificial neural networks are trained to generalize product attributes and LCC data from pre-existing LCC studies. Then the product designers query the trained artificial model with new high-level product attribute data to quickly obtain an LCC for a new product concept. Foundations fur the learning LCC approach are established, and then an application is provided.

• 한국지능시스템학회논문지
• /
• 제9권4호
• /
• pp.367-374
• /
• 1999

본 논문은 대규모 데이터베이스에서 의사 결정을 위한 지식을 효율적으로 추출하기 위해 개념 상승과 속성 감축에 기반한 통합적 방법을 제안한다. 본 방법은 클리스터링 기법에 의해 개념 트리를 자동생성하고 개념 상승기법에 의해 데이터 베이스를 일반화하며 속성의 중요도를 사용한 속성 감축에 의해 최적감축을 하고 식별가능 행렬과 함수를 사용하여 효율적으로 속성값을 감축하여 최적의 최소결정 규칙을 유도한다. 본 방법은 투자 계획이나 가격 결정과 같은 의사결정 업무 각종 고장 진단이나 의료 진단을 위한 지식 베이스구축 마케팅 분석이나 실험 데이터 분석 고수준의 질의 에 의한 정보검색 등에 효과적으로 사용될수 있다.

• 인터넷정보학회논문지
• /
• 제20권2호
• /
• pp.69-76
• /
• 2019

Recent Enterprise System has component driven real-time distributed architecture (RDA) and this kind of architecture should performed with satisfying strict constraints on life cycle of object and response time such as synchronization, transaction and so on. Microsoft's .NET platform supports RDA and is able to implement services including before mentioned time restriction and security service by only specifying attribute code and maximizing advantages of OMG's Model Driven Architecture (MDA). In this study, a method to automatically generate an extended model of essential elements in an enterprise-system-based RDA as well as the platform specific model (PSM) for Microsoft's .NET platform are proposed. To realize these ideas, the functionalities that should be considered in enterprise system development are specified and defined in a meta-model and an extended UML profile. In addition, after defining the UML profile for .NET specification, these are developed and applied as plug-ins of the open source MDA tool, and extended models are automatically generated using this tool. Accordingly, by using the proposed specification technology, the profile and tools can easily and quickly generate a reusable extended model even without detailed coding-level information about the functionalities considered in the .NET platform and RDA.

• Communications for Statistical Applications and Methods
• /
• 제30권6호
• /
• pp.589-603
• /
• 2023

Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.

• 한국생활과학회지
• /
• 제14권1호
• /
• pp.155-165
• /
• 2005

The purpose of this study is 1) to investigate the effects of Internet apparel store attributes, shopping values, Internet usage, and consumers' characteristics on consumers' Internet apparel purchasing behavior; and 2) to identify the influence of Internet apparel store attributes, Internet usage, and consumers' characteristics on the Internet apparel purchasing behavior of hedonic or utilitarian consumers. The data were collected via an online survey. A total of 4,254 Internet users participated in this survey. Only 589 out of the users' reponses were used as a sample for this research, because those users had previously experienced Internet apparel purchasing. Factor analysis revealed five dimensions of Internet apparel store attributes: site design/navigation, promotion programs, trust, product assortment/ information, and customer service. Based on the respondents' shopping value scores, we identified them as hedonic or utilitarian consumers. Through multiple regression analyses, site design/navigation and promotion programs among store attribute variables, hedonistic or utilitarian shopping values, the number of years on the Internet, income, and educational level were found to be significant predictors of Internet apparel shopping frequency. Among them, hedonistic shopping values were the best predictor of Internet apparel purchasing frequency. Based on the Internet apparel purchasers' shopping value, purchasers were divided into two groups. For hedonic Internet apparel shoppers, the number of years on the Internet, educational level, sex, age, and income were significant predictors of Internet apparel shopping behavior. On the other hand, promotion programs among store attribute variables was the only significant factor that affects utilitarian consumers' Internet apparel shopping behavior.

• 한국융합학회논문지
• /
• 제8권11호
• /
• pp.7-13
• /
• 2017

최근 다양한 기기들이 사용되면서 원격으로 서비스를 제공받는 클라우드 컴퓨팅 기술이 사회적으로 대두되고 있다. 그러나, 몇몇 사용자들이 악의적인 목적을 가지고 클라우드 컴퓨팅 서비스를 제공받으려는 시도가 증가하고 있다. 본 논문에서는 클라우드 환경에서 서버에 접근하는 사용자의 인증 접근을 손쉽게 하기 위해서 속성 기반의 다단계 계층 접근 방법을 제안한다. 제안 방법은 사용자의 속성 값을 일정한 규칙에 따라 속성 값들을 계층적으로 분산 배치하여 서버의 효율성뿐만 아니라 안전성을 향상시켰다. 성능평가 결과, 제안방법은 기존 기법보다 속성수에 따른 인증 정확도가 평균 15.8% 이상 높게 나타났고, 사용자 수 증가에 따른 서버의 인증 지연 시간은 평균 10.7% 단축되었다. 사용자의 속성 수가 증가할수록 오버헤드 변화가 기존 기법보다 평균 8.5% 낮은 결과를 얻었다.