• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.733-745
• /
• 2017

Local composite quantile regression is a useful non-parametric regression method widely used for its high efficiency. Data smoothing methods using kernel are typically used in the estimation process with performances that rely largely on the smoothing parameter rather than the kernel. However, $L_2$-norm is generally used as criterion to estimate the performance of the regression function. In addition, many studies have been conducted on the selection of smoothing parameters that minimize mean square error (MSE) or mean integrated square error (MISE). In this paper, we explored the optimality of selecting smoothing parameters that determine the performance of non-parametric regression models using local linear composite quantile regression. As evaluation criteria for the choice of smoothing parameter, we used mean absolute error (MAE) and mean integrated absolute error (MIAE), which have not been researched extensively due to mathematical difficulties. We proved the uniqueness of the optimal smoothing parameter based on MAE and MIAE. Furthermore, we compared the optimal smoothing parameter based on the proposed criteria (MAE and MIAE) with existing criteria (MSE and MISE). In this process, the properties of the proposed method were investigated through simulation studies in various situations.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.4
• /
• pp.993-1000
• /
• 2016

Semi-supervised learning makes it easy to use an unlabeled data in the supervised learning such as classification. Applying the semi-supervised learning on the regression analysis, we propose two methods for a better regression function estimation. The proposed methods have been assumed different marginal densities of independent variables and different smoothing parameters in unlabeled and labeled data. We shows that the overfitted pilot estimator should be used to achieve the fastest convergence rate and unlabeled data may help to improve the convergence rate with well estimated smoothing parameters. We also find the conditions of smoothing parameters to achieve optimal convergence rate.

• Journal of the Korean Data and Information Science Society
• /
• v.7 no.2
• /
• pp.211-217
• /
• 1996

본 논문은 확률밀도함수의 l 번째 도함수의 커널추정법에 관하여 다루고 있다. 확률밀도함수 도함수의 커널추정에 사용될 수 있는 두가지 평활량의 선택법, 교차타당성방법과 삽입방법에 의한 평활량의 점근분포를 규명하고 이들의 상대적 수렴속도를 각각 밝히고 삽입방법의 우수성을 소표본 모의실험을 통하여 확인하였다.

• Geophysics and Geophysical Exploration
• /
• v.16 no.4
• /
• pp.211-216
• /
• 2013

In general, smoothing filters regularize functions by reducing differences between adjacent values. The smoothing filters, therefore, can regularize inverse solutions and produce more accurate subsurface structure when we apply it to full waveform inversion. If we apply a smoothing filter with a constant coefficient to subsurface image or velocity model, it will make layer interfaces and fault structures vague because it does not consider any information of geologic structures and variations of velocity. In this study, we develop a selective smoothing regularization technique, which adapts smoothing coefficients according to inversion iteration, to solve the weakness of smoothing regularization with a constant coefficient. First, we determine appropriate frequencies and analyze the corresponding wavenumber coverage. Then, we define effective maximum wavenumber as 99 percentile of wavenumber spectrum in order to choose smoothing coefficients which can effectively limit the wavenumber coverage. By adapting the chosen smoothing coefficients according to the iteration, we can implement multi-scale full waveform inversion while inverting multi-frequency components simultaneously. Through the successful inversion example on a salt model with high-contrast velocity structures, we can note that our method effectively regularizes the inverse solution. We also verify that our scheme is applicable to field data through the numerical example to the synthetic data containing random noise.

• Journal of the Korean Society of Radiology
• /
• v.2 no.1
• /
• pp.23-29
• /
• 2008

The present study proposed a method that dissolves ultrasonographic images into multiple resolutions using wavelet conversion and a boundary detection filter and improves the quality of ultrasonographic images through boundary detection filtering. In order to reduce noises and strengthen edges, the proposed method adjusted selectivity coefficient by area step by step from a low resolution image obtained from wavelet converted images to a high resolution image and performed edge filtering in consideration of direction. Through this method, we generated a selective low pass filtering effect in areas except edges by decreasing the wavelet coefficient for pixels in spot areas, improved continuity by smoothing edges in the tangential direction, and enhanced contrast by thinning in the normal direction. Through an experiment, we compared the filtering method using a non linear anisotropic expansion model and the filtering method using wavelet contraction structure in single resolution.

• Fashion & Textile Research Journal
• /
• v.1 no.3
• /
• pp.280-287
• /
• 1999

The aims of this research were to study on the relationship between the mechanical properties and the deformation behavior of weft-knitted fabrics as a function of knit structure and knit density. Eighteen weft-knitted fabrics were produced with six different knit structures ($1{\times}1$ rib, half-cardigan rib, half-milano rib, interlock, single-pique, and crossmiss interlock) and three different knit densities (loose, medium, tight). The mechanical properties of these samples were measured using the KES-F system. The 2HBIW increased as knit density was raised. The increase was greater for the double knit fabrics in all samples. Half-milano rib and crossmiss interlock samples showed the lowest 2HG/G values. The double knits were smaller than those of single knits indicate a higher degree of surface smoothness. The ratio of compression energy to weight per unit area of the double knits had lower values than the single knits.