• 대한산업공학회지
• /
• 제32권1호
• /
• pp.18-28
• /
• 2006

Some issues which should be considered in an R&D project selection problem are as follows: First, quantitative analysis on the efficiencies of R&D projects is required to guarantee objective validity in the evaluation of the projects. For this reason, the methodology for selecting R&D projects should be based on mathematical models that perform quantitative analysis. Second, in general there are ordinal factors like Likert-scale in the data for evaluating R&D projects. Previous researches, however, couldn't suggest explicit methods incorporating these ordinal factors into models. Third, for the R&D project selection problems with limited resources like budget, it is necessary to decide the perfect ranking of the all projects. This paper develops a mathematical model that can be applicable to the problems of selecting R&D projects with the previous features. In this paper, we improve the original DEA model for evaluating efficiency to incorporate ordinal factors and suggest a new model which can decide the perfect ranking of all projects by merging the improved DEA model and AHP method. Furthermore a web-based R&D project selection system using the DEA/AHP model suggested in this paper is developed and illustrated.

• Communications for Statistical Applications and Methods
• /
• 제18권3호
• /
• pp.319-331
• /
• 2011

In this paper, we propose automatic procedures for the model selection of various univariate time series data. Automatic model selection is important, especially in data mining with large number of time series, for example, the number (in thousands) of signals accessing a web server during a specific time period. Several methods have been proposed for automatic model selection of time series. However, most existing methods focus on linear time series models such as exponential smoothing and autoregressive integrated moving average(ARIMA) models. The key feature that distinguishes the proposed procedures from previous approaches is that the former can be used for both linear time series models and nonlinear time series models such as threshold autoregressive(TAR) models and autoregressive moving average-generalized autoregressive conditional heteroscedasticity(ARMA-GARCH) models. The proposed methods select a model from among the various models in the prediction error sense. We also provide an R package autots that implements the proposed automatic model selection procedures. In this paper, we illustrate these algorithms with the artificial and real data, and describe the implementation of the autots package for R.

• 한국BIM학회 논문집
• /
• 제5권2호
• /
• pp.34-45
• /
• 2015

As buildings become larger and more complicated, construction costs have increased with a considerable effect on buildings' Life Cycle Cost (LCC). However, there has been little consideration on economic aspects in the selection of construction materials due to limited information on the materials and dependency in architects' experience and inefficiency in cost estimation, causing design changes, increase in maintenance cost, difficulty in budgeting, and decrease in building performance. To solve these problems, this study proposed a BIM-based material selection model which reflects the comprehensive economic efficiency of building materials. Our cost prediction model can estimates the material-related cost during the entire building life cycle. Furthermore, we implemented the proposed model in connection with BIM, which can analyze and compare LCC by material. Through the validation of the model, we could confirm the necessity of LCC-based material selection in comparison with the conventional cost-centered material selection.

• 한국전자거래학회지
• /
• 제18권4호
• /
• pp.327-338
• /
• 2013

IT프로젝트를 수행하는 기업은 정해진 예산범위 내에서 투자계획을 수립하고 실행하게 된다. 이 과정에서 IT프로젝트를 효과적, 효율적으로 선정하는 문제는 기업경쟁력과 직결되는 중요한 요소이다. 그동안 IT프로젝트의 선정을 위한 다양한 모형이 개발되었으나 예산제약을 고려한 효과적 프로젝트 선정에 대한 연구는 보고되지 않고 있다. 본 연구에서는 예산 제약을 고려하여 효과적으로 IT프로젝트를 선정하는 기법을 제시하였다. 본 연구에서 제안한 모델(AHP-K)에서는 AHP(Analytic Hierarchy Process : 계층분석법) 기법을 적용하여 평가 항목의 가중치와 프로젝트 후보군의 가중치를 산정한 후 배낭문제(Knapsack Problem)를 적용하여 예산 범위 내에서 프로젝트 효용을 최대화하는 선정안을 도출한다. 실제 적용단계에서 고려하는 대안이 많거나 신규대안이 추가되는 경우 쌍대비교의 수행이 어려운 점을 감안하여 대안 비교 단계에서 절대평가법을 적용하였다. 본 연구에서는 제시된 모델을 실제 사례에 적용하여 기존 AHP 모형과 비교 분석함으로써 효과성을 검증하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권6호
• /
• pp.1543-1550
• /
• 2013

In this paper, we study Bayesian estimation for the finite population proportion in binary data under selection bias. We use a Bayesian nonignorable selection model to accommodate the selection mechanism. We compare four possible estimators of the finite population proportions based on data analysis as well as Monte Carlo simulation. It turns out that nonignorable selection model might be useful for weekly biased samples.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.233-233
• /
• 2022

As the world's population grows and food needs diversify, the demand for horticultural crops for beneficial traits is increasing. In order to meet this demand, it is necessary to develop suitable cultivars and breeding methods accordingly. Breeding methods have changed over time. With the recent development of sequencing technology, the concept of genomic selection (GS) has emerged as large-scale genome information can be used. GS shows good predictive ability even for quantitative traits by using various markers, breaking away from the limitations of Marker Assisted Selection (MAS). Moreover, GS using machine learning (ML) and deep learning (DL) has been studied recently. In this study, we aim to build a system that selects phenotype-related markers using the genomic information of the pepper population and trains a genomic selection model to select individuals from the validation population. We plan to establish an optimal genome wide association analysis model by comparing and analyzing five models. Validation of molecular markers by applying linkage markers discovered through genome wide association analysis to breeding populations. Finally, we plan to establish an optimal genome selection model by comparing and analyzing 12 genome selection models. Then We will use the genome selection model of the learning group in the breeding group to verify the prediction accuracy and discover a prediction model.

• Communications for Statistical Applications and Methods
• /
• 제19권3호
• /
• pp.345-358
• /
• 2012

표본선택 모형을 최우추정법으로 추정할 때 오차항의 분포를 제대로 가정하는 것이 매우 중요하다. 표본선택 모형의 선택 방정식과 본 방정식의 오차항 분포를 일반적으로 이변량 정규분포로 가정하지만, 이 가정이 오차항의 실제 분포를 과도하게 제약할 가능성이 있다. 본 연구는 표본선택 모형의 오차항 분포로 $S_U$-정규분포를 도입한다. $S_U$-정규분포는 분포의 비대칭성과 초과첨도를 허용한다는 측면에서 정규분포보다 훨씬 유연하면서, 동시에 정규분포를 극한분포의 형태로 포함하고 있다. 또한 정규분포처럼 다변량 분포함수가 존재하기 때문에 표본선택 모형과 같은 다변량 모형에서도 활용할 수 있다. 본 논문은 $S_U$-정규분포를 이용한 표본선택 모형에서 로그우도 함수와 조건부 기댓값을 도출하고, 시뮬레이션을 통해 정규분포 모형과 추정성과를 비교한다. 또한 자동차 보유 가구들의 자동차 유지비에 관한 실제 데이터를 이용하여 $S_U$-정규분포 표본선택 모형의 추정결과를 제시한다.

• 한국데이터정보과학회:학술대회논문집
• /
• 한국데이터정보과학회 2006년도 PROCEEDINGS OF JOINT CONFERENCEOF KDISS AND KDAS
• /
• pp.171-179
• /
• 2006

For the problem of variable selection in linear models, we consider the errors are correlated with V covariance matrix. Hocking's theorems on the effects of the overfitting and the underfitting in linear model are extended to the less than full rank and correlated error model, and to the ANCOVA model.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 추계 학술발표회 논문집
• /
• pp.187-192
• /
• 2005

For the problem of variable selection in linear models, we consider the errors are correlated with V covariance matrix. Hocking's theorems on the effects of the overfitting and the undefitting in linear model are extended to the less than full rank and correlated error model, and to the ANCOVA model

• Journal of information and communication convergence engineering
• /
• 제9권5호
• /
• pp.491-499
• /
• 2011

In this paper, we offer a new strategic portfolio model for national IT R&D project selection in Korea. A risk and return (R-R) portfolio model was developed using an objectively quantified index on the two axes of risk and return, in order to select a strategic project and allocate resources in compliance with a national IT R&D strategy. We strategize using the R-R portfolio model to solve the non-strategy and subjectivity problems of the existing national R&D project selection model. We also use the quantified evaluation index of the IT technology road map (TRM) and the technical level reports (TLR) for the subjectivity of project selection, and try to discover the weights using the analytic hierarchy process (AHP). In addition, we intend to maximize the chance for a successful national IT R&D project, by selecting a strategic portfolio project and balancing the allocation of resources effectively and objectively.