• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.12 no.4
• /
• pp.227-238
• /
• 2008

In this paper we extend primal-dual interior point algorithm for linear optimization (LO) problems to $P_*({\kappa})$ linear complementarity problems(LCPs) ([1]). We define proximity functions and search directions based on kernel functions, ${\psi}(t)=\frac{t^{p+1}-1}{p+1}-{\log}\;t$, $p{\in}$[0, 1], which is a generalized form of the one in [16]. It is the first to use this class of kernel functions in the complexity analysis of interior point method(IPM) for $P_*({\kappa})$ LCPs. We show that if a strictly feasible starting point is available, then new large-update primal-dual interior point algorithms for $P_*({\kappa})$ LCPs have $O((1+2{\kappa})nlog{\frac{n}{\varepsilon}})$ complexity which is similar to the one in [16]. For small-update methods, we have $O((1+2{\kappa})\sqrt{n}{\log}{\frac{n}{\varepsilon}})$ which is the best known complexity so far.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.2393-2398
• /
• 2003

In this paper, we proposes a new fuzzy inference system for modeling nonlinear systems given input and output data. In the suggested fuzzy inference system, the number of fuzzy rules and parameter values of membership functions are automatically decided by using the kernel-based method. The kernel-based method individually performs linear transformation and kernel mapping. Linear transformation projects input space into linearly transformed input space. Kernel mapping projects linearly transformed input space into high dimensional feature space. The structure of the proposed fuzzy inference system is equal to a Takagi-Sugeno fuzzy model whose input variables are weighted linear combinations of input variables. In addition, the number of fuzzy rules can be reduced under the condition of optimizing a given criterion by adjusting linear transformation matrix and parameter values of kernel functions using the gradient descent method. Once a structure is selected, coefficients in consequent part are determined by the least square method. Simulated result illustrates the effectiveness of the proposed technique.

• Journal of Korea Water Resources Association
• /
• v.39 no.6 s.167
• /
• pp.495-502
• /
• 2006

The importance of the bandwidth selection has been more emphasized than the kernel function selection for nonparametric frequency analysis since the interpolation is more reliable than the extrapolation method. However, when the extrapolation method is being applied(i.e. recurrence interval more than the length of data or extreme probabilities such as $200{\sim}500$ years), the selection of the kernel function is as important as the selection of the bandwidth. So far, the existing kernel functions have difficulties for extreme value estimations because the values extrapolated by kernel functions are either too small or too big. This paper suggests a Modified Cauchy kernel function that is suitable for both interpolation and extrapolation as an improvement.

• Bulletin of the Korean Mathematical Society
• /
• v.53 no.5
• /
• pp.1401-1409
• /
• 2016

In complex analysis, the Bergman kernels for two biholomorphically equivalent complex domains satisfy the transformation formula. Recently new Bergman theory of slice regular functions of the quaternion variables has been investigated. In this paper we construct the transformation formula of the slice Bergman kernels under slice biregular functions in the setting of the quaternion variables.

• Honam Mathematical Journal
• /
• v.36 no.3
• /
• pp.659-668
• /
• 2014

In this paper, we express the Green function in terms of the classical kernel functions in potential theory. In particular, we obtain a formula relating the Green function and the Szegő kernel function which consists of only the Szegő kernel function in a $C^{\infty}$ smoothly bounded finitely connected domain in the complex plane.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.6
• /
• pp.1231-1239
• /
• 2012

An estimating procedure is introduced for kernel Poisson regression when the input variables consist of numerical and categorical variables, which is based on the penalized negative log-likelihood and the component-wise product of two different types of kernel functions. The proposed procedure provides the estimates of the mean function of the response variables, where the canonical parameter is linearly and/or nonlinearly related to the input variables. Experimental results are then presented which indicate the performance of the proposed kernel Poisson regression.

• Journal of the Korean Mathematical Society
• /
• v.40 no.3
• /
• pp.447-460
• /
• 2003

In this paper we study the non-degenerate n-connected canonical domains with n>1 related to the conjecture of S. Bell in [4]. They are connected to the algebraic property of the Bergman kernel and the Szego kernel. We characterize the non-degenerate doubly connected canonical domains.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.11 no.4
• /
• pp.69-88
• /
• 2007

In this paper we propose new large-update primal-dual interior point algorithms for $P_{\neq}({\kappa})$ linear complementarity problems(LCPs). New search directions and proximity measures are proposed based on a specific class of kernel functions, ${\psi}(t)={\frac{t^{p+1}-1}{p+1}}+{\frac{t^{-q}-1}{q}}$, q>0, $p{\in}[0,\;1]$, which are the generalized form of the ones in [3] and [12]. It is the first to use this class of kernel functions in the complexity analysis of interior point method(IPM) for $P_*({\kappa})$LCPs. We showed that if a strictly feasible starting point is available, then new large-update primal-dual interior point algorithms for $P_*({\kappa})$ LCPs have the best known complexity $O((1+2{\kappa}){\sqrt{2n}}(log2n)log{\frac{n}{\varepsilon}})$ when p=1 and $q=\frac{1}{2}(log2n)-1$.

• East Asian mathematical journal
• /
• v.37 no.3
• /
• pp.333-354
• /
• 2021

A support vector machine (SVM) is a state-of-the-art machine learning model rooted in structural risk minimization. SVM is underestimated with regards to its application to real world problems because of the difficulties associated with its use. We aim at showing that the performance of SVM highly depends on which kernel function to use. To achieve these, after providing a summary of support vector machines and kernel function, we constructed experiments with various benchmark datasets to compare the performance of various kernel functions. For evaluating the performance of SVM, the F1-score and its Standard Deviation with 10-cross validation was used. Furthermore, we used taylor diagrams to reveal the difference between kernels. Finally, we provided Python codes for all our experiments to enable re-implementation of the experiments.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.11 no.4
• /
• pp.33-43
• /
• 2001

This paper presents a secure Linux OS in which multi-level security functions are implemented at the kernel level. Current security efforts such as firewall or intrusion detection system provided in application-space without security features of the secure OS suffer from many vulnerabilities. However the development of the secure OS in Korea lies in just an initial state, and NSA has implemented a prototype of the secure Linux but published just some parts of the technologies. Thus our commercialized secure Linux OS with multi-level security kernel functions meets the minimum requirements for TCSEC B1 level as well kernel-mode encryption, real-time audit trail with DB, and restricted use of root privileges.