• 품질경영학회지
• /
• 제27권2호
• /
• pp.218-236
• /
• 1999

The purpose of parameter design is to determine optimal settings of design parameters of a product or a process such that the performance characteristics of a product exhibit small variabilities around their target values. Taguchi made significant contributions in this area. However, his analysis of the problem focused on only one performance characteristic or response, although in product and process design, multiple characteristics are more common. The critical problem in dealing with multiple characteristics is how to compromise the conflict among the selected levels of the design parameters for each individual characteristic. In this paper, Methodology using SN ratio optimized by univariate technique is proposed and a parameter design procedure to achieve the optimal balance among several different response variables is developed. Existing case studies are solved by the proposed method and the results are compared with ones by the sum of SN ratios, the expected weighted loss, the desirability function, and EXTOPSIS model.

• 품질경영학회지
• /
• 제28권2호
• /
• pp.123-134
• /
• 2000

In the survey, it is very hard to get the complete response. Because the respondents tend to refuse to the questionnaire with something like incomes of the individual or may not be at home in the survey time. These nonresponses are classified into two groups as the item nonresponse and the unit nonresponse. When the nonresponse happen to the special item of the questionnaire, it is caned item nonresponse. On the other hand the unit nonresponse occurs to the totally missing in questionnaire. In this paper, we only consider to the unit nonresponse situation. We propose that the optimal estimator which is minimized the variance of the estimator under a fixed cost function for the survey and response.

• 경영과정보연구
• /
• 제27권
• /
• pp.131-147
• /
• 2008

The study examines common component existing in five Asian countries from 1991 to 2007. To do this, the daily stock market indices of Korea, Malaysia, Thailand, Indonesia, and the Philippines were used. Using a Vector Autoregressive Model this paper analyzes causal relations and dynamic interactions between five Asian stock markets. The findings in this study indicate that level of five Asian stock markets' stock return linkages are low. First, from the statistics for pair-wise Granger causality tests, I find Granger-causal relationship between Korea and Indonesia and between Malaysia and and Indonesia. Second, from the results of response function and the statistics of variance decomposition, I find that week shocks to Korean stock market return on Malaysia, Indonesia, Thailand, and the Philippines stock market returns. The results indicate increased Asian stock market linkages but the level is very low. This implies that the benefits of diversification within the five Asian stock markets are still existed.

• 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.

• 대한안전경영과학회지
• /
• 제13권1호
• /
• pp.69-73
• /
• 2011

Questionnaire survey has been made for the above study. First, 65 question sheets have been distributed to railway operators and 55 sheets of them have been collected from them. SPSS 12.0 program package has been used to analyze those sheets concerning age, experience, school, background as a frequency analysis and t-test has been made to find out recognition level difference of a cheer response, depending on the operator's experience. T-verification has been made for two groups such as less than 10 years, and 10 years or more experience. Result from correlation analysis showed that there was no difference due to operators' experience.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2005년도 춘계종합학술대회
• /
• pp.196-199
• /
• 2005

이 논문에서는 과학적 응용에서 발생하는 군집을 이루는 시간 데이터를 관리하는 방법을 제안한다. 먼저, 시간데이터를 구분하는 경계값 LB와 RB를 정의하고 과거, 현재, 미래 세그먼트에 각각 저장되는 개체버전을 정의하였다. 또한 Hotspot 분포를 가지는 시간 데이터에 대하여 각 세그먼트 사이에 이동하는 알고리즘을 나타내었다. 이 논문에서 제안하는 최소중복을 이용한 이동 방법과 기존방법에 대하여 성능을 비교하였다. 질의에 대한 평균 응답 시간에서는 기존의 방법과 비슷한 결과를 보였다. 제안한 이동 방법은 세그먼트 사이에 중복해서 저장되는 데이터 수를 적게 하므로 공간 이용율 측면에서는 기존의 이동 방법보다 효율적이었다.

• Industrial Engineering and Management Systems
• /
• 제2권1호
• /
• pp.55-62
• /
• 2003

This paper deals with the difficulties involved in analyzing and designing a management system to reduce the risks and improve the productivity of new product development. In this paper, a method is described to analyze user information and determine product specifications based on a stimulus-response model, the conjoint measurement of users needs, and product characteristics deployment. The proposed method can analyze the effect of a partial price on the contribution ratio based on the order of preference of product profiles through a smaller number of product profiles. The strengths and weaknesses of this method are examined as the method is applied to the case study of a mobile computer intended for personal use.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2003년도 춘계학술대회
• /
• pp.400-409
• /
• 2003

Collaborative filtering (CF) recommendation is a knowledge sharing technology for distribution of opinions and facilitating contacts in network society between people with similar interests. The main concerns of the CF algorithm are about prediction accuracy, speed of response time, problem of data sparsity, and scalability. In general, the efforts of improving prediction algorithms and lessening response time are decoupled. We propose a three-step CF recommendation model which is composed of profiling, inferring, and predicting steps while considering prediction accuracy and computing speed simultaneously. This model combines a CF algorithm with two machine learning processes, SOM (Self-Organizing Map) and CBR (Case Based Reasoning) by changing an unsupervised clustering problem into a supervised user preference reasoning problem, which is a novel approach for the CF recommendation field. This paper demonstrates the utility of the CF recommendation based on SOM cluster-indexing CBR with validation against control algorithms through an open dataset of user preference.

• 품질경영학회지
• /
• 제26권1호
• /
• pp.143-160
• /
• 1998

This article is concerned with the selection of subsets of predictor variables to be included in bulding the binary response logistic regression model. It is based on a Bayesian aproach, intended to propose and develop a procedure that uses probabilistic considerations for selecting promising subsets. This procedure reformulates the logistic regression setup in a hierarchical normal mixture model by introducing a set of hyperparameters that will be used to identify subset choices. It is done by use of the fact that cdf of logistic distribution is a, pp.oximately equivalent to that of $t_{(8)}$/.634 distribution. The a, pp.opriate posterior probability of each subset of predictor variables is obtained by the Gibbs sampler, which samples indirectly from the multinomial posterior distribution on the set of possible subset choices. Thus, in this procedure, the most promising subset of predictors can be identified as that with highest posterior probability. To highlight the merit of this procedure a couple of illustrative numerical examples are given.

• 품질경영학회지
• /
• 제27권1호
• /
• pp.101-110
• /
• 1999

Products are often evaluated on rating scales to measure and quantify their attributes of interest. In case that one wishes to compare multiple rating datasets simultaneously, there must be a standardized scale with which one can discriminate relative differences among corresponding scale means. In this regard, the concept of Thurstonian modeling applied to various discrimination tests including the triangular method has been recently being reconsidered. In this paper we extend previous researches on the triangular method and evaluate the effect of unequal variances and correlated variables upon the probability of correct response using Monte-Carlo simulation. We observed that the probability of correct response depends on dimensionality, variances, and correlation structure of stimulus sets. But it does not depend on the relative orientation in a multidimensional space.