• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.26 no.1
• /
• pp.39-48
• /
• 2013

This paper develops a 2-D moving least squares(MLS) difference method for Stefan problem by extending the 1-D version of the conventional method. Unlike to 1-D interfacial modeling, the complex topology change in 2-D domain due to arbitrarily moving boundary is successfully modelled. The MLS derivative approximation that drives the kinetics of moving boundary is derived while the strong merit of MLS Difference Method that utilizes only nodal computation is effectively conserved. The governing equations are differentiated by an implicit scheme for achieving numerical stability and the moving boundary is updated by an explicit scheme for maximizing numerical efficiency. Numerical experiments prove that the MLS Difference Method shows very good accuracy and efficiency in solving complex 2-D Stefan problems.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.5
• /
• pp.438-447
• /
• 2008

This study is focused on reliability based design optimization (RBDO) using moving least squares. A response surface is used to derive a limit-state equation for reliability based design optimization. Response surface method (RSM) with least square method (LSM) or Kriging will be used as a response surface. RSM is fast to make the response surface. On the other hand, RSM has disadvantage to make the response surface of nonlinear equation. Kriging can make the response surface in nonlinear equation precisely but needs considerable amount of computations. The moving least square method (MLSM) is made of both methods (RSM with LSM+Kriging). Numerical results by MLSM are compared with those by LMS in Rosenbrock function and six-hump carmel back function. The RBDO of engine duct of smart UAV is pursued in this paper. It is proved that RBDO is useful tool for aerospace structural optimal design problems.

• Archives of Pharmacal Research
• /
• v.10 no.1
• /
• pp.1-8
• /
• 1987

One of the problems of derivatie spectrophotometry, the decrease of signal-to-noise ratio by derivative operations, was solved by three concepts of digital filtering, ensemble averaging, least squares polynomial smoothing and Fourier smoothing. The suthors made several compouter programs written in APPLE SOFT BASIC language for the actual applications of the concepts of these digital filters on UV spectrophotometer system. As a result, ensemble averaging could not be used as a routine operation for the spectrophotometer used. The maximum S/N ratio enhancement factors achieved by least squares polynomial smoothing were 6.17 and 7.47 for the spectra of Gaussian and Lorentzian distribution models, and by Fourier smoothing 16.42 and 11.78 for the spectra of two models, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.2045-2050
• /
• 2004

An optimal combination of arbitrary number correlated estimates is derived. In particular, for two estimates this combination represents the well-known Millman and Bar-Shalom-Campo formulae for uncorrelated and correlated estimation errors, respectively. This new result is applied to the various estimation problems as least-squares estimation, Kalman filtering, and adaptive filtering. The new approximate adaptive filter with a parallel structure is proposed. It is shown that this filter is very effective for multisensor systems containing different types of sensors. Examples demonstrating the accuracy of the proposed filter are given.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.1
• /
• pp.45-61
• /
• 2010

In the communication channel, the received signal is affected by many factors that can cause errors. These effects mean that received signal strength (RSS) based methods incur more errors in measuring distance and consequently result in low precision in the location detection process. As one of the approaches to overcome these problems, we propose using direction calibration to improve the performance of the RSS-based method for distance measurement, and sequentially a weighted least squares (WLS) method using reliability factors in conjunction with a conventional RSS weighting matrix is proposed to solve an over-determined localization process. The proposed scheme focuses on the features of the RSS method to improve the performance, and these effects are proved by the simulation results.

• Proceedings of the Korea Society for Simulation Conference
• /
• 2001.10a
• /
• pp.373-379
• /
• 2001

There is a big issue to generate 3D hexahedral finite element (FE) model, since a process to divide the whole domain into several simple-shaped sub-domains is required before generating a continuous mesh with mapped mesh generators. In general, it is nearly impossible to set up proper division numbers interactively to keep mesh connectivity between sub-domains on a complicated arbitrary-shaped domain. If mesh continuity between sub-domains is not required in an analysis, this complicated process can be omitted. Element-free Galerkin method (EFGM) can accept discontinuous meshes, which only requires nodal information. However it is difficult to choose a reasonable influenced domain in moving least squares scheme with non-uniformly distributed nodes in discontinuous FE models. A new FE scheme fur discontinuous mesh is proposed in this paper by applying improved EFGM with some modification to derive FE approximated function in discontinuous parts. Its validity is evaluated on linear elastic problems.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.5
• /
• pp.319-322
• /
• 2016

We propose a parametric blind deconvolution method for bi-level images with unknown intensity levels that estimates unknown parameters for point spread functions and images by minimizing a penalized nonlinear least squares objective function based on normalized correlation coefficients and two regularization functions. Unlike conventional methods, the proposed method does not require knowledge about true intensity values. Moreover, the objective function of the proposed method can be effectively minimized, since it has the special structure of nonlinear least squares. We demonstrate the effectiveness of the proposed method through simulations and experiments.

• Industrial Engineering and Management Systems
• /
• v.14 no.3
• /
• pp.312-317
• /
• 2015

The dynamic system approach in time series has been used in many real problems. Based on Taken's embedding theorem, we can build the predictive function where input is the time delay coordinates vector which consists of the lagged values of the observed series and output is the future values of the observed series. Although the time delay coordinates vector from multivariate time series brings more information than the one from univariate time series, it can exhibit statistical redundancy which disturbs the performance of the prediction function. We apply dimension reduction techniques to solve this problem and analyze the effect of this approach for prediction. Our experiment uses delayed Lorenz series; least squares support vector regression approximates the predictive function. The result shows that linearly preserving projection improves the prediction performance.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.393-396
• /
• 2011

In this paper, we propose a constrained alternating least squares nonnegative matrix factorization algorithm (cALSNMF) to detect active brain regions from single subject's task-related fMRI data. In cALSNMF, we define a new cost function which considers the uncorrelation and noisy problems of fMRI data by adding decorrelation and smoothing constraints in original Euclidean distance cost function. We also generate a novel training procedure by modifying the update rules and combining with optimal brain surgeon (OBS) algorithm. The experimental results on visuomotor task fMRI data show that our cALSNMF fits fMRI data better than original ALSNMF in detecting task-related brain activation from single subject's fMRI data.

• Structural Engineering and Mechanics
• /
• v.35 no.4
• /
• pp.511-533
• /
• 2010

As a truly meshfree method, meshless equilibrium on line method (MELM), for 2D elasticity problems is presented. In MELM, the problem domain is represented by a set of distributed nodes, and equilibrium is satisfied on lines for any node within this domain. In contrary to conventional meshfree methods, test domains are lines in this method, and all integrals can be easily evaluated over straight lines along x and y directions. Proposed weak formulation has the same concept as the equilibrium on line method which was previously used by the authors for enforcement of the Neumann boundary conditions in the strong-form meshless methods. In this paper, the idea of the equilibrium on line method is developed to use as the weak forms of the governing equations at inner nodes of the problem domain. The moving least squares (MLS) approximation is used to interpolate solution variables in this paper. Numerical studies have shown that this method is simple to implement, while leading to accurate results.