• Communications for Statistical Applications and Methods
• /
• v.23 no.1
• /
• pp.71-83
• /
• 2016

In this paper we discuss a deconvolution density estimator obtained using the support vector machines (SVM) and Tikhonov's regularization method solving ill-posed problems in reproducing kernel Hilbert space (RKHS). A remarkable property of SVM is that the SVM leads to sparse solutions, but the support vector deconvolution density estimator does not preserve sparsity as well as we expected. Thus, in section 3, we propose another support vector deconvolution estimator (method II) which leads to a very sparse solution. The performance of the deconvolution density estimators based on the support vector method is compared with the classical kernel deconvolution density estimator for important cases of Gaussian and Laplacian measurement error by means of a simulation study. In the case of Gaussian error, the proposed support vector deconvolution estimator shows the same performance as the classical kernel deconvolution density estimator.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.501-509
• /
• 2009

Recently the interval estimation of binomial proportions is revisited in various literatures. This is mainly due to the erratic behavior of the coverage probability of the well-known Wald confidence interval. Various alternatives have been proposed. Among them, the Agresti-Coull confidence interval, the Wilson confidence interval and the Bayes confidence interval resulting from the noninformative Jefferys prior were recommended by Brown et al. (2001). However, unlike the binomial distribution case, little is known about the properties of the confidence intervals in finite population sampling. In this note, the property of confidence intervals is investigated in anile population sampling.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.11a
• /
• pp.821-824
• /
• 2008

This paper presents a systematic approach for estimating material performance of concrete mixture design based on satisfaction curves developed from statistical evaluation of existing or newly obtained material property related data. In performance based material design (PBMD) method, concrete material used for construction of a structure is designed considering a structure's specified performance requirements based on its usage and characteristics such as environmental conditions, structure types, expected design life, etc.Satisfaction curves express the probabilities that one component of substrates (i.e., aggregate size, cement content, etc) of concrete mixture will sustain different criterion value for a given concrete mixture design. This study presents a statistical analysis method for setting up concrete material parameter versus concrete criterion relationships in the form of satisfaction curves and for estimating confidence bounds on these satisfaction curves. This paper also presents an analysis method to combine multiple satisfaction curves to form one unique satisfaction curve that can relate the performance of concrete to a single evaluating value. Based on several evaluated mixture design examples for various material properties, the validity of the proposed method is discussed in detail.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1161-1164
• /
• 2002

We propose a simple method that can recognize human emotion from monocular dance image sequences. The method only exploits the information within image sequences and does not require cumbersome attachments like sensors. This makes the method a simple, human-friendly one. Moreover, the method is more robust and efficient by taking into account the statistical property of image sequences based on PCA (Principal Component Analysis). The correct recognition rate in real-time is about 75% in a variety of experiments.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2004.10a
• /
• pp.19-22
• /
• 2004

A numerical system to extract effective elastic properties of polycrystalline thin-films for MEMS devices is already developed. In this system, the statistical model based on lattice system is used for modeling the microstructure evolution simulation and the key kinetics parameters of given micrograph, grain distributions and deposition process can be extracted by inverse method proposed in the system. In this work, the effective elastic properties of polysilicon, $BaTiO_3\;and\;ZrTiO_4$ are extracted using this system and by employing the fraction of the potential site($f_P$) as a kinetics parameter for the microstructure evolution, the statistical tendency of these materials is studied.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.373-382
• /
• 2008

A method to investigate the design variable tolerance effects on the variances of the response, the characteristics, and the performance of a mechanical system is presented in this paper. The Monte-Carlo method has been conventionally employed to achieve such goals. However, the Monte-Carlo method has some serious drawbacks related to the computation time and the consistent solution convergence. To resolve the drawbacks of the method, a method employing sensitivity information is proposed. Sensitivity equations for a mechanical system are obtained analytically by differentiating the multi-body formulation with respect to a design variable. By using the chain rule along with the sensitivity information, the variances of the response, the characteristics, and the performance of a dynamic system can be calculated.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.942-946
• /
• 2010

As the major sources of interior noise of train at running condition are the wheel/rail contact noise, the traction motor's noise and the driving gear's noise and these noise sources are transmitted through the car body, the noises of HVAC and air duct can be ignored. But the interior noise of train at standstill condition is decided by HVAC's noise and noise from the diffuser through the air duct. the interior noise prediction of train at standstill condition should be performed considering the shape of air duct, the air velocity and noise reduction property inside the air duct. But it is hard to estimate the interior noise level by the numerical method. Therefore train maker predict the interior noise level using The commercial noise prediction program. This paper introduce the noise prediction method of the train at standstill condition using the commercial program appling the ray tracing method and statistical energy analysis.

• Journal of Korean Society for Quality Management
• /
• v.40 no.3
• /
• pp.337-346
• /
• 2012

Purpose: A Control chart is one of the important statistical process control tools that can improve processes by reducing variability and defects. Methods: In the present study, we propose the local $T^2$ multivariate control chart that can efficiently detect abnormal observations by considering the local pattern of the in-control observations. Results: A simulation study has been conducted to examine the property of the proposed control chart and compare it with existing multivariate control charts. Conclusion: The results demonstrate the usefulness and effectiveness of the proposed control chart.

• Communications for Statistical Applications and Methods
• /
• v.20 no.4
• /
• pp.259-270
• /
• 2013

This paper considers a penalized composite quantile regression (CQR) that performs a variable selection in the linear model with grouped variables. An adaptive sup-norm penalized CQR (ASCQR) is proposed to select variables in a grouped manner; in addition, the consistency and oracle property of the resulting estimator are also derived under some regularity conditions. To improve the efficiency of estimation and variable selection, this paper suggests the two-stage penalized CQR (TSCQR), which uses the ASCQR to select relevant groups in the first stage and the adaptive lasso penalized CQR to select important variables in the second stage. Simulation studies are conducted to illustrate the finite sample performance of the proposed methods.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.367-382
• /
• 2017

We consider an infinite-order long-memory heterogeneous autoregressive (HAR) model, which is motivated by a long-memory property of realized volatilities (RVs), as an extension of the finite order HAR-RV model. We develop bootstrap tests for structural mean or variance changes in the infinite-order HAR model via stationary bootstrapping. A functional central limit theorem is proved for stationary bootstrap sample, which enables us to develop stationary bootstrap cumulative sum (CUSUM) tests: a bootstrap test for mean break and a bootstrap test for variance break. Consistencies of the bootstrap null distributions of the CUSUM tests are proved. Consistencies of the bootstrap CUSUM tests are also proved under alternative hypotheses of mean or variance changes. A Monte-Carlo simulation shows that stationary bootstrapping improves the sizes of existing tests.