• Journal of KIISE:Software and Applications
• /
• v.31 no.11
• /
• pp.1474-1482
• /
• 2004

In this paper, we propose an approach for extracting and filtering block motion vectors using an adaptive weight function. We first extract motion vectors from a sequence of images by using size-varibale block matching and then process them by adaptive robust estimation to filter out outliers (motion vectors out of concern). The proposed adaptive robust estimation defines a continuous sigmoid weight function. It then adaptively tunes the sigmoid function to its hard-limit as the residual errors between the model and input data are decreased, so that we can effectively separate non-outliers (motion vectors of concern) from outliers with the finally tuned hard-limit of the weight function. The experimental results show that the suggested approach is very effective in filtering block motion vectors.

• Communications for Statistical Applications and Methods
• /
• v.20 no.6
• /
• pp.481-490
• /
• 2013

Classification is an important research area as data can be easily obtained even if the number of predictors becomes huge. The support vector machine(SVM) is widely used to classify a subject into a predetermined group because it gives sound theoretical background and better performance than other methods in many applications. The SVM can be viewed as a penalized method with the hinge loss function and penalty functions. Instead of $L_2$ penalty function Fan and Li (2001) proposed the smoothly clipped absolute deviation(SCAD) satisfying good statistical properties. Despite the ability of SVMs, they have drawbacks of non-robustness when there are outliers in the data. We develop a robust SVM method using a weight function with the SCAD penalty function based on the local quadratic approximation. We compare the performance of the proposed SVM with the SVM using the $L_1$ and $L_2$ penalty functions.

• 연구논문집
• /
• s.28
• /
• pp.123-135
• /
• 1998

A shape function for element free Galerkin method is carved from Shepard interpolant of singular weight and consistency condition. Thus present shape function is an interpolation and has no singularities. The shape function is applied to cantilever bending problems and gives good results in comparison with beam theory. Finally it is shown that the coupling with finite element method is made easily without any additional treaties.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.20 no.7
• /
• pp.2167-2173
• /
• 1996

An approximate weight function technique using the indirect boundary integral equation has been presented for the analysis of stress intensity foactors(SIFs) of a thick pipe. One-term boundary integral was introduced to represent the crack surface displacement field for the displacement based weight function technique. An explicit closed-form SIF solution applicable to symmetric cracked pipes without any modification of the solution including both circumferential and radial cracks has been derived. The necessary information in the analysis is two or three reference SIFs. In most cases the SIF solution were in good agreement with those available in the literature.

• Journal of Ocean Engineering and Technology
• /
• v.23 no.1
• /
• pp.146-151
• /
• 2009

In this paper, a weight function theory for the calculation of the mode III stress intensity factor in a rectilinear anisotropic body is formulated. This formulation employs Lekhnitskii's formalism for two dimensional anisotropic materials. To illustrate the method used for the weight function theory, we calculated the mode III stress intensity factor in a single edge-notched configuration.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2001.11a
• /
• pp.161-166
• /
• 2001

This study intends to reduce the weight of structure without changing the dynamic characteristics. At first, the Vibration analyses by the Substructure Synthesis Method and FEM using the ANSYS are performed for the engine speed converter to confirm the reliability of the analyzing tools. Weight minimization is performed by the Sensitivity Analysis and the Optimum Structural Modification. To decrease the converter weight ideally, the parts with low sensitivity are to be cut mainly, and the changing quantity of the natural frequency by the cut is to be recovered by the weight modification of the parts with high sensitivity. As the unique mathematical solution for the homogeneous problem( i.e. 0 object function problem) does not exist, the converter is redesigned with much thinner initial thickness. The goal of this study is to recover the dynamic characteristics of redesigned structure to those of the original one. To say in the other words, the modified structure has the same dynamic characteristics and the more lighter weight to compare with the original one. In this analysis, the modification was performed with the redesigned initial thickness of 60 mm and 70 mm. And the numbers of the interesting natural frequencies are 1, 2, 4 respectively. Consequently 27％ of weight reduction effects were earned.

• Journal of the Chungcheong Mathematical Society
• /
• v.28 no.3
• /
• pp.491-497
• /
• 2015

In this paper, we have suggested an extended double Newton's method with sixth-order convergence by considering a control parameter ${\gamma}$ and a weight function H(s, u). We have determined forms of ${\gamma}$ and H(s, u) in order to induce the greatest order of convergence and established the main theorem utilizing related properties. The developed theory is ensured by numerical experiments with high-precision computation for a number of test functions.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.3048-3050
• /
• 1999

This paper suggests a position estimating algorithm using mono vision system with projective geometry method. Generally, 3-D information can not be easily extracted from mono vision system which is taken by a camera at a specific point. But this defect is overcome by adopting model-based image analysis and selecting lines and points on the ground as natural landmarks. And this paper suggests a method that estimates position from many natural landmarks by distance error weight function.

• Journal of the Korean Statistical Society
• /
• v.29 no.2
• /
• pp.247-260
• /
• 2000

This paper is concerned with a modification of the k-spatial medians clustering. To find a suitable number of clusters, the number k of clusters is incorporated into the k-spatial medians clustering criterion through a weight function. Proposed method for the choice of the weight function offers a reasonable number of clusters. Some theoretical properties of the method are investigated along with some examples.

• Industrial Engineering and Management Systems
• /
• v.8 no.4
• /
• pp.247-256
• /
• 2009

In mass production industries such as steel making that have large equipment, sudden stops of production process due to machine failure can cause severe problems. To prevent such situations, machine diagnosis techniques play important roles. Many methods have been developed focusing on this subject. In this paper, we propose a method for the early detection of the failure on rotating machine, which is the most common theme in the machine failure detection field. A simplified method of calculating autocorrelation function is introduced and is utilized for ARMA model identification. Furthermore, an absolute deterioration factor such as Bicoherence is introduced. Machine diagnosis can be executed by this simplified calculation method of system parameter distance with weight. Proposed method proved to be a practical index for machine diagnosis by numerical examples.