• Journal of applied mathematics & informatics
• /
• v.28 no.1_2
• /
• pp.351-361
• /
• 2010

The solution of large sparse linear systems is one of the most important problems in large scale scientific computing. Among the many methods developed, the preconditioned Krylov subspace methods are considered the preferred methods. Selecting a suitable preconditioner with appropriate parameters for a specific sparse linear system presents a challenging task for many application scientists and engineers who have little knowledge of preconditioned iterative methods. The prediction of ILU type preconditioners was considered in [27] where support vector machine(SVM), as a data mining technique, is used to classify large sparse linear systems and predict best preconditioners. In this paper, we apply the data mining approach to the sparse approximate inverse(SAI) type preconditioners to find some parameters with which the preconditioned Krylov subspace method on the linear systems shows best performance.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• v.20 no.3
• /
• pp.225-242
• /
• 2016

The phase-type representation is strongly connected with the positive realization in positive system. We attempt to transform phase-type representation into sparse mono-cyclic positive representation with as low order as possible. Because equivalent positive representations of a given phase-type distribution are non-unique, it is important to find a simple sparse positive representation with lower order that leads to more effective use in applications. A Hypo-Feedback-Coxian Block (HFCB) representation is a good candidate for a simple sparse representation. Our objective is to find an HFCB representation with possibly lower order, including all the eigenvalues of the original generator. We introduce an efficient nonlinear optimization method for computing an HFCB representation from a given phase-type representation. We discuss numerical problems encountered when finding efficiently a stable solution of the nonlinear constrained optimization problem. Numerical simulations are performed to show the effectiveness of the proposed algorithm.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.336-338
• /
• 1998

This paper presents a novel neural network structure to the blind deconvolution task where the input (source) to a system is not available and the source has any type of distribution including sparse distribution. We employ multiple sensors so that spatial information plays a important role. The resulting learning algorithm is linear so that it works for both sub-and super-Gaussian source. Moreover, we can successfully deconvolve the mixture of a sparse source, while most existing algorithms [5] have difficulties in this task. Computer simulations confirm the validity and high performance of the proposed algorithm.

• Journal of the Korean Society for information Management
• /
• v.40 no.2
• /
• pp.59-80
• /
• 2023

Traditional models for categorizing researcher types have mostly utilized research output metrics. This study proposes a new model that classifies researchers based on the characteristics of research collaboration. The model uses only research collaboration indicators and does not rely on citation data, taking into account that citation impact is related to collaborative research. The model categorizes researchers into four types based on their collaborative research pattern and scope: Sparse & Wide (SW) type, Dense & Wide (DW) type, Dense & Narrow (DN) type, Sparse & Narrow (SN) type. When applied to the quantum metrology field, the proposed model was statistically verified to show differences in citation indicators and co-author network indicators according to the classified researcher types. The proposed researcher type classification model does not require citation information. Therefore, it is expected to be widely used in research management policies and research support services.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.11 no.4
• /
• pp.143-150
• /
• 1991

This paper presents an overview of a system of computer programs for the solution of a large geodetic network of about 2,000 stations. The system arranges the matrices in systematic sparse form which is applied to observation equations of RR(C)U (Row-wise Representation Complete Unordered) type and to normal equations of RR(U)U (Row-wise Representation Upper Unordered) type. The solution is done by a Modified Cholesky's algorithm in view of large networks. The implementation program are tested in PC-386 by korean new secondary networks, the results show that the sparse techniques are highly useful to geodetic networks in core-storage management and processing time.

• The KIPS Transactions:PartA
• /
• v.8A no.3
• /
• pp.227-234
• /
• 2001

In this paper we propose a block-type parallel preconditioner for solving large sparse nonsymmetric linear systems, which we expect to be scalable. It is Multi-Color Block SOR preconditioner, combined with direct sparse matrix solver. For the Laplacian matrix the SOR method is known to have a nondeteriorating rate of convergence when used with Multi-Color ordering. Since most of the time is spent on the diagonal inversion, which is done on each processor, we expect it to be a good scalable preconditioner. We compared it with four other preconditioners, which are ILU(0)-wavefront ordering, ILU(0)-Multi-Color ordering, SPAI(SParse Approximate Inverse), and SSOR preconditiner. Experiments were conducted for the Finite Difference discretizations of two problems with various meshsizes varying up to $1025{\times}1024$. CRAY-T3E with 128 nodes was used. MPI library was used for interprocess communications, The results show that Multi-Color Block SOR is scalabl and gives the best performances.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.12
• /
• pp.67-74
• /
• 2015

The heat conduction equation, a type of a Poisson equation which can be applied in various areas of engineering is calculating its value with the iteration method in general. The equation which had difference discretization of the heat conduction equation is the simultaneous equation, and each line has the characteristic of expressing in sparse matrix of the equivalent number of none-zero elements with neighboring grids. In this paper, we propose a data structure for sparse matrix that can calculate the value faster with less memory use calculate the heat conduction equation. To verify whether the proposed data structure efficiently calculates the value compared to the other sparse matrix representations, we apply the representative iteration method, CG (Conjugate Gradient), and presents experiment results of time consumed to get values, calculation time of each step and relevant time consumption ratio, and memory usage amount. The results of this experiment could be used to estimate main elements of calculating the value of the general heat conduction equation, such as time consumed, the memory usage amount.

• Bulletin of the Korean Mathematical Society
• /
• v.57 no.4
• /
• pp.851-864
• /
• 2020

This paper gives a sparse domination for the iterated commutators of multilinear pseudo-differential operators with the symbol σ belonging to the Hörmander class, and establishes the quantitative bounds of the Bloom type estimates for such commutators. Moreover, the C_p estimates for the corresponding multilinear pseudo-differential operators are also obtained.

• Journal of applied mathematics & informatics
• /
• v.25 no.1_2
• /
• pp.435-443
• /
• 2007

Computing the interior spectrum of large sparse generalized eigenvalue problems $Ax\;=\;{\lambda}Bx$, where A and b are large sparse and SPD(Symmetric Positive Definite), is often required in areas such as structural mechanics and quantum chemistry, to name a few. Recently, CG-type methods have been found useful and hence, very amenable to parallel computation for very large problems. Also, as in the case of linear systems proper choice of preconditioning is known to accelerate the rate of convergence. After the smallest eigenpair is found we use the orthogonal deflation technique to find the next m-1 eigenvalues, which is also suitable for parallelization. This offers advantages over Jacobi-Davidson methods with partial shifts, which requires re-computation of preconditioner matrx with new shifts. We consider as preconditioners Incomplete LU(ILU)(0) in two variants, ever-relaxation(SOR), and Point-symmetric SOR(SSOR). We set m to be 5. We conducted our experiments on matrices from discretizations of partial differential equations by finite difference method. The generated matrices has dimensions up to 4 million and total number of processors are 32. MPI(Message Passing Interface) library was used for interprocessor communications. Our results show that in general the Multi-Color ILU(0) gives the best performance.

• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.281-288
• /
• 2015

In this paper, we study an approximate procedure to evaluate a penalized maximum likelihood estimator (MLE) for a mixed effects model. The procedure approximates the Hessian matrix of the penalized MLE with a structured sparse matrix or an arrowhead type matrix to speed its computation. In this paper, we numerically investigate the gain in computation time as well as approximation error from the considered approximation procedure.