• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권4호
• /
• pp.277-281
• /
• 2006

Cyber counseling, one of the most compatible type of consultation for the information society, enables people to reveal their mental agonies and private problems anonymously, since it does not require face-to-face interview between a counsellor and a client. However, there are few cyber counseling centers which provide high quality and trustworthy service, although the number of cyber counseling center has highly increased. Therefore, this paper is intended to enable an appropriate consultation for each client by analyzing client propensity using Bayesian variable selection. Bayesian variable selection is superior to stepwise regression analysis method in finding out a regression model. Stepwise regression analysis method, which has been generally used to analyze individual propensity in linear regression model, is not efficient since it is hard to select a proper model for its own defects. In this paper, based on the case database of current cyber counseling centers in the web, we will analyze clients' propensities using Bayesian variable selection to enable individually target counseling and to activate cyber counseling programs.

• Journal of the Korean Data and Information Science Society
• /
• 제19권3호
• /
• pp.789-800
• /
• 2008

Current credit evaluation models based on financial data make use of smoothing estimated default ratios which are transformed from each financial variable. In this work, some problems of the credit evaluation models developed by financial experts are discussed and we propose improved credit evaluation models based on the stepwise variable selection method and Box-Cox transformed data whose distribution is much skewed to the right. After comparing goodness-of-fit tests of these models, the validation of the credit evaluation models using statistical methods such as the stepwise variable selection method and Box-Cox transformation function is explained.

• Structural Engineering and Mechanics
• /
• 제54권1호
• /
• pp.87-103
• /
• 2015

This paper focuses on an analytical research on the critical buckling load of cylindrical shells with stepwise variable wall thickness under axial compression. An arctan function is established to describe the thickness variation along the axial direction of this kind of cylindrical shells accurately. By using the methods of separation of variables, small parameter perturbation and Fourier series expansion, analytical formulas of the critical buckling load of cylindrical shells with arbitrary axisymmetric thickness variation under axial compression are derived. The analysis is based on the thin shell theory. Analytic results show that the critical buckling load of the uniform shell with constant thickness obtained from this paper is identical with the classical solution. Two important cases of thickness variation pattern are also investigated with these analytical formulas and the results coincide well with those obtained from other authors. The cylindrical shells with stepwise variable wall thickness, which are widely used in actual engineering, are studied by this method and the analytical formulas of critical buckling load under axial compression are obtained. Furthermore, an example is presented to illustrate the effects of each strake's length and thickness on the critical buckling load.

• 대한산업공학회지
• /
• 제42권5호
• /
• pp.314-326
• /
• 2016

The purpose of variable selection techniques is to select a subset of relevant variables for a particular learning algorithm in order to improve the accuracy of prediction model and improve the efficiency of the model. We conduct an empirical analysis to evaluate and compare seven well-known variable selection techniques for multiple linear regression model, which is one of the most commonly used regression model in practice. The variable selection techniques we apply are forward selection, backward elimination, stepwise selection, genetic algorithm (GA), ridge regression, lasso (Least Absolute Shrinkage and Selection Operator) and elastic net. Based on the experiment with 49 regression data sets, it is found that GA resulted in the lowest error rates while lasso most significantly reduces the number of variables. In terms of computational efficiency, forward/backward elimination and lasso requires less time than the other techniques.

• 한국주거학회논문집
• /
• 제8권2호
• /
• pp.71-84
• /
• 1997

The Purpose of this study is to estimate how inclination to move can be appeared by understanding the cognition of a resident on stress due to the residential environment. 240 housewives living in Chiniu were Questioned statistical analysis were used with factor analysis, F-test. Duncan's Multiple range analysis, stepwise regression analysis and stepwise discriminant analysis, The result were summarized as follows 1) The stress of residential environment were clissified by six factors indoor facility, educational environmental. indoor structure, air Pollution noise, traffic convenience. 2) The extent of a stress from residential environment was significantly different in the socio-demographic variable and housing-related variable. 3) The stress of residential environment were affected by the direction of house. 4) The variable discriminating inclination to move were the stress of residential environment(air Pollution). an educational level, the type of housing possession, residential Period and the size of house.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.949-952
• /
• 2002

A regression model is used in predicting the response variable given predictor variables However, in case of large number of predictor variables, a regression model has some problems such as multicollinearity, interpretation of the functional relationship between the response and predictors and prediction accuracy. A clustering method and stepwise regression could be used to reduce the amount of data by grouping predictors having similar properties and by selecting the subset of predictors. respectively. This paper proposes a prediction method combining clustering method and stepwise regression. The proposed method fits a global model and local models and predicts responses given new observations by using both models. The paper also compares the performance of proposed method with stepwise regression via a real data of ample obtained in a steel process.

• 드라이브 ㆍ 컨트롤
• /
• 제15권2호
• /
• pp.9-21
• /
• 2018

The aim of this study was to develop and test a model of an auto-sensing hydraulic breaker that can automatically change its 4-step impact mode according to the rock strength using SimulationX. The auto-sensing hydraulic breaker with a 4-step variable impact mode has the advantage of obtaining optimal impact energy and impact frequency under various rock conditions compared to an auto-sensing hydraulic breaker with a 2-step variable impact mode, which has already been developed overseas. Several steps were necessary to conduct this study. First, the operation principle of the auto-sensing hydraulic breaker with the 2-step variable impact mode was analyzed. Based on the findings, an analysis model of the auto-sensing hydraulic breaker with the 4-step variable impact mode was developed (and compared with the 2-step variable impact mode) Finally, an analysis of the results established that the stepwise variable of the impact mode was implemented according to the rock strength and the difference of each impact mode was confirmed. This study is expected to contribute to the development of auto-sensing hydraulic breakers that are superior to those developed by advanced companies in foreign countries.

• 수산해양교육연구
• /
• 제23권3호
• /
• pp.400-409
• /
• 2011

The purpose of this study was to investigate the influence of irrational beliefs on parenting stress of mothers with early children. For achieving this purpose, Irrational Belief Test and Parenting Stress Index were administered to 300 mothers with early children in Busan and data from 234 mothers were used for statistical analysis. Collected data were analyzed using Pearson correlation coefficient and stepwise multiple regression analysis. The results of correlational analysis showed that irrational beliefs were positively related to parenting stress. Anxious over-concern factor was related to all parenting stress variables. The results of stepwise regression analysis revealed that 2~4 irrational beliefs significantly influenced parenting stress; sub-factors of parenting stress variable that irrational beliefs had the most effect on was competence factor. Based upon these results, it can be concluded that irrational belief is an important variable which predicts parenting stress of mothers with early children.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.513-521
• /
• 2010

대부분의 대학들은 교수업적평가를 위해 강의평가제도를 실시하고 있다. 그러나 강의평가의 결과는 강좌규모, 강의형태, 개설학년, 이수구분, 평균평점 등과 같은 개설강좌의 특성에 많은 영향을 받게 된다. 따라서 이러한 각 강좌특성들이 강의평가 결과에 영향을 미치는 효과를 제거하지 않는다면, 담당교수가 강의평가 결과에 대한 공정성과 객관성을 신뢰할 수 없게 만들 정도로 심각한 편의를 갖게 된다. 따라서 강의평가의 공정성을 위해 강좌특성에 따른 편의를 제거하기 위한 사후조정된 점수가 요구된다. 따라서 본 연구에서는 단계적 변수선택법에 의한 회귀분석을 이용하여 강의평가 결과에 대한 균등화 방법을 이용하여 사후조정된 점수를 계산하는 방법을 제안한다. 그리고 제안된 방법은 기존의 방법과 비교를 하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제41권8호
• /
• pp.598-604
• /
• 2014

본 연구는 주요변수를 선정하는 기법을 개발하기 위해서 단계적 회귀와 변수들의 효율성을 평가하기 위해 사용되는 자료봉합분석을 결합한 새로운 방법을 제안하였다. 이를 위해서 먼저 단계적 회귀를 이용하여 중요 변수들을 일차적으로 선정하고, 선정된 각 변수들의 중요도를 이해하기 위해 귀무가설을 세웠고, 중요 변수를 선택하기 위해 Kruskal-Wallis 검정을 사용했다. 또한 해당되는 변수를 Conover-Inman 검정을 사용하여 변동이 발생하는 각 변수들의 우선순위를 결정하였다. 따라서 그 결과, 많은 변수들과 DEA(Data Envelopment Analysis)의 한계를 극복하기 위해 원래 계획된 변수들 중 기준에 의해 원래 유지된 변수와 높은 연관성을 가진 변수들을 남기는 방식으로 변수를 선정하는 기법을 개발한 Jenkins의 기존연구에서는 I2, I4, I5, I6 변수가 누락되었고 I1, I3 변수만이 DEA에 사용되었지만, 본 논문에서 제안된 모델의 효율성 결과로는 I2와 I4 변수를 각각 유지하였다. 본 연구는 다른 문헌에서 단계적 변수의 선택을 보여주기 위해 같은 데이터 집합을 사용하였는데, 여기서 Jenkins의 연구와 같이 변수 I6과 I1, I2를 삭제하였고, I3, I4, I5는 유지하였다. 결론적으로 단계적 회귀 DEA 모델을 사용하여 긴 계산적 절차 없이 변수 선택이 가능함을 발견했으며 기존 연구의 데이터를 적용하여 제안된 모델을 검증하였다. 개발한 DEA모델 결과는 상호 변수에 따라 포함되거나 생략할 수 있기 때문에 실제 현실 상황에서의 지식과 경영적 판단에 매우 유용할 것이다.