• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.285-288
• /
• 2003

신용위험 관리에서 필수적인 방법론이 스코어 카드이며 이를 작성하는 데에 있어서 널리 쓰이는 방법 중의 하나가 로지스틱 회귀분석이다. 본 논문에서는 로지스틱 회귀 방법에 기초한 스플라인 방법론을 소개하고자 한다. 최종 스코어 카드는 연속형 변수를 범주형 변수화 하므로 조각 선형 스플라인을 채택하였다. 모의 실험을 통하여 제안된 방법의 성 능을 규명 하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.316-321
• /
• 2003

Recently, support vector learning attracts great interests in the areas of pattern classification, function approximation, and abnormality detection. It is well-known that among the various support vector learning methods, the so-called no-versions are particularly useful in cases that we need to control the total number of support vectors. In this paper, we consider the problem of function approximation utilizing both predetermined basis functions and a no-version support vector learning called $\nu-SVR$. After reviewing $\varepsilon-SVR$, $\nu-SVR$, and a semi-parametric approach, this paper presents an extension of the conventional $\nu-SVR$ method toward the direction that can utilize Predetermined basis functions. Moreover, the applicability of the presented method is illustrated via an example.

• The Korean Journal of Applied Statistics
• /
• v.18 no.3
• /
• pp.543-553
• /
• 2005

Linear logistic regression is one of the most widely used method for credit scoring in credit risk management. This paper deals with credit scoring using splines based on Logistic regression. Linear splines and an automatic basis selection algorithm are adopted. The final model is an example of the generalized additive model. A simulation using a real data set is used to illustrate the performance of the spline method.

• Communications for Statistical Applications and Methods
• /
• v.5 no.3
• /
• pp.777-792
• /
• 1998

병원의 임상연구실험에서 종종 환자들의 치료에 따른 병세의 호전상태를 여러단계로 분류하여 상이한 치료방법에 대한 치료효과간의 차이론 알고자 하는 경우가 있다. 이와 같이 다중상태의 생존자료를 분석하기 위해서 본 논문에서는 semi-Markov 모형에 Cox 회귀모형을 적용하여 회귀계수와 기저생존함수를 추정하고 이를 바탕으로 반응확률함수를 추정하였다. 그리고 본 논문의 결과를 실제 임상실험에서 얻어진 자료에 적용하여 분석하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.735-740
• /
• 2012

In this paper, we introduce design methodologies of polynomial radial basis function neural network classifier with the aid of Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). By minimizing the information loss of given data, Feature data is obtained through preprocessing of PCA and LDA and then this data is used as input data of RBFNNs. The hidden layer of RBFNNs is built up by Fuzzy C-Mean(FCM) clustering algorithm instead of receptive fields and linear polynomial function is used as connection weights between hidden and output layer. In order to design optimized classifier, the structural and parametric values such as the number of eigenvectors of PCA and LDA, and fuzzification coefficient of FCM algorithm are optimized by Artificial Bee Colony(ABC) optimization algorithm. The proposed classifier is applied to some machine learning datasets and its result is compared with some other classifiers.

• Water for future
• /
• v.18 no.1
• /
• pp.85-94
• /
• 1985

A method is developed for the separation of the major base flow in a river hydrograph combining the numerical techniques and the empirical methods. The linearized Boussinesq equation and the storage function are used to obtain the base flow recession. The shape of base flow curve made by the recharge of the groundwater table aquifer resulting from rainfall in determined by the Singh and Stall's graphical method, and the continuous from for the curve is approximated by the multiple and polynomial regression. this procedure was successfully tested for the separation of base flow and the establishment of hydrograph in a natural watershed. It was found that the direct numerical method applied to the homogeneous linear second order ordinary differential equation system is not suited to obtain the recession curve, and the case that the loss is generated in the partially penetrating stream can not be solved by the method of this study.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.1
• /
• pp.79-87
• /
• 2013

An isogeometric topological shape optimization method is developed using the level sets and Heaviside enrichments. In the level set method, the initial domain is kept fixed and its boundary is represented by an implicit moving boundary embedded in the level set functions, which facilitates to handle complicated topological shape changes. The Heaviside enrichment improves the isogeometric analysis by adding some enrichment functions to model the internal boundaries. The proposed topological shape optimization method has several benefits: exact geometric models can be obtained using the isogeometric approach and the limitation of tensor-product patches can be overcome using the Heaviside enrichments to represent the internal voids. Even in a single patch, discontinuous displacement fields as well as smooth stress field can be obtained. Since the level sets offer the implicit moving boundary inside the domain, it is easy to represent the topological shape variations in the isogeometric analysis using Heaviside enrichments.

• Resources Recycling
• /
• v.26 no.2
• /
• pp.46-55
• /
• 2017

In this study, the design methodology of Radial Basis Function Neural Networks is developed with the aid of Laser Induced Breakdown Spectroscopy and also applied to the practical plastics sorting system. To identify black plastics such as ABS, PP, and PS, RBFNNs classifier as a kind of intelligent algorithms is designed. The dimensionality of the obtained input variables are reduced by using PCA and divided into several groups by using K-means clustering which is a kind of clustering techniques. The entire data is split into training data and test data according to the ratio of 4:1. The 5-fold cross validation method is used to evaluate the performance as well as reliability of the proposed classifier. In case of input variables and clusters equal to 5 respectively, the classification performance of the proposed classifier is obtained as 96.78%. Also, the proposed classifier showed superiority in the viewpoint of classification performance where compared to other classifiers.

• Journal of the Korean Chemical Society
• /
• v.53 no.5
• /
• pp.499-504
• /
• 2009

Metals have often played important roles to some enzymatic reactions that are essential to biological processes. Therefore many scientists have studied the reaction mechanisms of catalytic reactions in metaloenzymes for many years. Methane MonoOxygenase (MMO) is an enzyme that oxidize methane to methyl alcohol. Recently Tolman et al. studied a model reaction for MMO, which is a hydroxide transfer reaction in Bis-($\mu$-oxo)-dicopper complex, and suggested several possible mechanisms. Later a two-step mechanism, which is hydrogen transfer followed by hydroxide rebound, was proposed from theoretical studies. In this study we calculated the reactant, product, and the transition state structures, and energetics of the first hydrogen transfer reaction using various DFT methods including recently developed the MO6 family of DFT, namely, MO6, MO6L, and MO6-2X. We found that the M06/6-31G(d,p)/LANL2DZ method reproduce the experimental XRD structure of reactants very well. The TS structures, barrier heights, and reaction energies depend very much on the size of the basis sets.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5B
• /
• pp.439-446
• /
• 2006

In the present study, we applied wavelet transform to decompose the hydro-meteorological data such as precipitation and temperature into the components with different return periods with a primary objective for extraction of nonlinear dynamical component. For the transform, we used the Daubechies wavelet of order 9 ('db9') as a basis function. Also, we applied the correlation dimension analysis to determine whether or not the detail and approximation components at the respective decomposition stage with the increasing of scale in the wavelet transform reveal the nonlinear dynamical characteristics. In other words, we proposed the combined use of the wavelet transform and the correlation dimension analysis as methodology to extract the nonlinear dynamical component from the hydro-meteorological data. The derived result has shown the method proposed in the present study is suitable for the segregation and extraction of the nonlinear dynamical component which is, in general, difficult to reveal by using the raw data.