• International Journal of CAD/CAM
• /
• v.7 no.1
• /
• pp.11-20
• /
• 2007

A topology optimization methodology, named "smooth boundary topology optimization," is proposed to overcome the shortcomings of cell-based methods. Material boundary is represented by B-spline curves and their control points are considered as design variables. The design is improved by either creating a hole or moving control points. To determine which is more beneficial, a selection criterion is defined. Once determined to create a hole, it is represented by a new B-spline and recognized as a new boundary. Because the proposed method deals with the control points of B-spline as design variables, their total number is much smaller than cell-based methods and it ensures smooth boundaries. Differences between our method and level set method are also discussed. It is shown that our method is a natural way of obtaining smooth boundary topology design effectively combining computer graphics technique and design sensitivity analysis.

• The Korean Journal of Applied Statistics
• /
• v.5 no.2
• /
• pp.271-282
• /
• 1992

A statistical method to investigate the relationship between the occurrence of Langerahans cells and neoplastic transformation of uterine cerivx. The best fitting submodel which satisfies the selection criterion similar in type to AIC is selected among the possible submodels based on Poisson probability models. A bootstrap method is used to approximate the sampling distribution of the selection criterion and the usual normal approximation is used to find the asymptotic distribution of the estimated rates.

• Communications for Statistical Applications and Methods
• /
• v.17 no.6
• /
• pp.909-916
• /
• 2010

A trend in software reliability engineering is to take into account the coverage growth behavior during testing. A coverage growth function that represents the coverage growth behavior is an essential factor in software reliability models. When multiple competitive coverage growth functions are available, there is a need for a criterion to select the best coverage growth functions. This paper proposes a selection criterion based on the prediction error. The conditional coverage growth function is introduced for predicting future coverage growth. Then the sum of the squares of the prediction error is defined and used for selecting the best coverage growth function.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.1
• /
• pp.187-194
• /
• 2014

We consider a Bayesian nonignorable selection model to accommodate the selection bias. Markov chain Monte Carlo methods is known to be very useful to fit the nonignorable selection model. However, sensitivity to prior assumptions on parameters for selection mechanism is a potential problem. To quantify the sensitivity to prior assumption, the deviance information criterion and the conditional predictive ordinate are used to compare the goodness-of-fit under two different prior specifications. It turns out that the 'MLE' prior gives better fit than the 'uniform' prior in viewpoints of goodness-of-fit measures.

• The Research Journal of the Costume Culture
• /
• v.4 no.2
• /
• pp.173-185
• /
• 1996

The purpose of this study was to identify the relationship of clothing involvement and clothing buying behavior of women. A questionnaire was developed to measure clothing involvement, clothing purchasing motives, clothing purchasing criteria, fashion information sources, store selection criteria, and demographic characteristics. The questionnaire was administered to 430 female adults in Taegu. The data were analyzed using percentage, frequency, factor analysis, and t-test. The results of the study were s follows: 1. Subjects were divided into low clothing involved and high clothing involved groups. 2. Three dimensions of clothing purchasing motives were derived by factor analysis such as Aesthetic dependant, Impulsive, and Practical motive. Clothing purchasing criteria were factor analysed as Aesthetic, Qualitative, External, and Economical criterion. Fashion information sources were factor analysed as Printed & audio-visual oriented media, Marketer intensive search, Store search, Observation & Interpersonal search, and Experience. Store selection criteria were factor analyzed as Merchandise & Store atmosphere, Store convenience, and Brand & fashion. 3. There were significant differences between high involved and low involved consumers in clothing purchasing behavior. The high involved consumers showed more importance than low involved consumers about purchasing criteria expecially in aesthetic dependant. The high involved consumers put more importance to aesthetic, qualitative, and external criterion as clothing purchasing criteria. The high involved information sources. The high involved consumers were more concerned about merchandise & store atmosphere, and brand & fashion than low involved consumers in store selection criteria.

• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.531-540
• /
• 2007

The recursive feature elimination for support vector machine is known to be useful in selecting relevant genes. Since the criterion for choosing relevant genes is the absolute value of a coefficient, the recursive feature elimination may suffer from a scaling problem. We propose a modified version of the recursive feature elimination algorithm using bootstrap. In our method, the criterion for determining relevant genes is the absolute value of a coefficient divided by its standard error, which accounts for statistical variability of the coefficient. Through numerical examples, we illustrate that our method is effective in gene selection.

• Journal of KIISE:Software and Applications
• /
• v.34 no.11
• /
• pp.1001-1010
• /
• 2007

HMM tends to output high probability for not only the proper class data but confusable class data, since the modeling power increases as the number of parameters increases. Thus it may not be helpful for discrimination to simply increase the number of parameters of HMM. We proposed two methods in this paper. One is a CMC(Confusion Likelihood Model Selection Criterion) using confusion class data probability, the other is a new recognition method, RCM(Recognition Using Confusion Models). In the proposed recognition method, confusion models are constructed using confusable class data, then confusion models are used to depress misrecognition by confusion likelihood is subtracted from the corresponding standard model probability. We found that CMC showed better results using fewer number of parameters compared with ML, ALC2, and BIC. RCM recorded 93.08% recognition rate, which is 1.5% higher result by reducing 17.4% of errors than using standard model only.

• The KIPS Transactions:PartA
• /
• v.10A no.1
• /
• pp.59-68
• /
• 2003

3-D data modeling of a volumetric scattered data is highly demanded for geological structure inspection, environment visualization and supersonic testing. The data used in these area are generally irregularly scattered in a volume data space, which are much different from the structured points data (cuberille data) used in Marching cube algorithm. In this paper, first we explore a volume modeling method for the scattered data based on tetrahedral domain. Next we propose a method for solving the ambiguity of tetrahedral domain decision using asymptotic decider criterion. Last we implement a simple visualization system based on the proposed asymptotic decider criterion and compare it with a system based on sphere criterion. In deciding tetrahedral domain, sphere criterion considers only positional values but asymptotic decider criterion considers not only positional values but also functional values, so asymptotic decider criterion is more accurate on deciding tetrahedral domain than sphere criterion.

• Journal of Korea Port Economic Association
• /
• v.38 no.3
• /
• pp.15-28
• /
• 2022

Bunkering refers to the supply of bunker fuel necessary for the ship operation, as well as minimizing the price and supply cost of fuel itself, and includes supplying good quality fuel oil in a timely manner and at the optimal port. Bunkering is an important criterion in terms of cost for shipping companies because bunkering involves a significant cost to the purchaser of bunkering from the time of initial purchase. This study aims to prioritize selection criteria for tramper companies to call port for bunkering. For this study, the variables were selected by analyzing the common criteria such as price, location, bunker quality and service and infrastructure etc. employed in previous studies. The AHP method was employed to prioritize the criteria in order. As a result of the analysis, the high level factors appeared in the order of price, location, bunkering quality and port service and infrastructure factors. The importance of price criterion and location criterion was found to be high. In the low level criterion of price, the bunker price per MT was ranked first in importance. In terms of location criteria, the location on the main trade route was high. In the low criteria of bunker quality and port service, the bunkering available types and bunker quality were found to be important factors, and in the low level criteria of infrastructure, anchorage and availability of bunkering during loading and discharging and port security factors were found to be important criteria. This study provides the guidelines for research designed to compare the bunkering port selection factors and to derive their importance suggesting the ways to enhance competitiveness as a bunkering port.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.3C
• /
• pp.209-214
• /
• 2003

Multi-mode coding method is a reliable DC-suppression method. There are two ways to improve the DC-suppression performance. One is improving scrambler's performance, and the other is improving selection criteria. The latter uses the MRDS(minimum running digital sum) criterion. It is easy to calculate, but its performance goes down when the length of codeword is getting longer. The MSW(mean squared weight) criterion that is known as the best so far regardless of the length of codeword has the high complexity. In this paper, we present the new selection criteria, MPRDS(minimum peak RDS) and A BSRDS(absolute RDS). Their performance are close to the MSW, implementation is simple. And also we present the SC(sign change) that has a subsidiary role with the original selection criteria and improve the capacity.