• Journal of the Korean Data and Information Science Society
• /
• 제22권5호
• /
• pp.951-959
• /
• 2011

The proposed method is based on a penalized censored regression model with L1-penalty. We use the iteratively reweighted least squares procedure to solve L1 penalized log likelihood function of censored regression model. It provide the efficient computation of regression parameters including variable selection and leads to the generalized cross validation function for the model selection. Numerical results are then presented to indicate the performance of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• 제25권4호
• /
• pp.951-959
• /
• 2014

Recently Hazelton and Turlach (2009) proposed a weighted kernel density estimator for the deconvolution problem. In the case of Gaussian kernels and measurement error, they argued that the weighted kernel density estimator is a competitive estimator over the classical deconvolution kernel estimator. In this paper we consider weighted kernel density estimators when sample observations are contaminated by double exponentially distributed errors. The performance of the weighted kernel density estimators is compared over the classical deconvolution kernel estimator and the kernel density estimator based on the support vector regression method by means of a simulation study. The weighted density estimator with the Gaussian kernel shows numerical instability in practical implementation of optimization function. However the weighted density estimates with the double exponential kernel has very similar patterns to the classical kernel density estimates in the simulations, but the shape is less satisfactory than the classical kernel density estimator with the Gaussian kernel.

• 한국통신학회논문지
• /
• 제16권3호
• /
• pp.284-290
• /
• 1991

가산성 잡음이 접여 있는 확률 신호를 순위 통계량에 바탕을 두고 검파하는 방식을 얻었다. 이 검파기가 확률신호 국소 최적 검파기와 비슷하다는 것과 알려진 신호 국소 최적 순위 검파기를 일반화한 것이라는 것을 보였다. 뿐만 아니라 이 검파기의 성능을 다른 검파기들과 간주이 보았다.

• Journal of the Korean Data and Information Science Society
• /
• 제27권3호
• /
• pp.835-844
• /
• 2016

We develop the testing procedures about the homogeneity of the shape parameters of several inverse Gaussian distributions in our paper. We propose default Bayesian testing procedures for the shape parameters under the reference priors. The Bayes factor based on the proper priors gives the successful results for Bayesian hypothesis testing. For the case of the lack of information, the noninformative priors such as Jereys' prior or the reference prior can be used. Jereys' prior or the reference prior involves the undefined constants in the computation of the Bayes factors. Therefore under the reference priors, we develop the Bayesian testing procedures with the intrinsic Bayes factors and the fractional Bayes factor. Simulation study for the performance of the developed testing procedures is given, and an example for illustration is given.

• Journal of the Korean Data and Information Science Society
• /
• 제21권3호
• /
• pp.561-567
• /
• 2010

Multiclassification is typically performed using voting scheme methods based on combining a set of binary classifications. In this paper we use multiclassification method with a hat matrix of least squares support vector machine (LS-SVM), which can be regarded as the revised one-against-all method. To tackle multiclass problems for large data, we use the $Nystr\ddot{o}m$ approximation and the quadratic Renyi entropy with estimation in the primal space such as used in xed size LS-SVM. For the selection of hyperparameters, generalized cross validation techniques are employed. Experimental results are then presented to indicate the performance of the proposed procedure.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1993년도 정기총회 및 추계학술대회 논문집 학회본부
• /
• pp.287-289
• /
• 1993

In this paper, we improve feedforward neural network performance by eliminating the effect of gross error using classifier structure. At first, we prove the output of classifier converges to the posteriori probability of each pattern given input x, $f_0({\theta}_1|x)$. And we apply filtering approach based on the robust statistics before reconstructing continuous output. The data distorted with noise can be rejected by this process. Finally, we suggest neurofilter structure. Simulation result shows that our structure yields consistent estimates even in the presence of noise.

• 통합자연과학논문집
• /
• 제11권2호
• /
• pp.76-81
• /
• 2018

Robust design is an approach to reducing performance variation of quality characteristic values in quality engineering. Product array approach which is used in the Taguchi parameter design has a number of advantages by considering the noise factor. Taguchi has an idea that mean and variation are handled simultaneously to reduce the expected loss in products and processes. Taguchi has used the signal-to-noise ratio (SN) to achieve the appropriate set of operating conditions where variability around target is low in the Taguchi parameter design. Many Statisticians criticize the Taguchi techniques of analysis, particularly those based on the SN. In this paper we propose a substantially simpler optimization procedure for robust design using desirability function without resorting to SN.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2000년도 춘계학술대회논문집
• /
• pp.1127-1132
• /
• 2000

Impulsive acoustic and vibration signals within rotating machinery are often induced by irregular impacting. The detection of these impulses can be useful for fault diagnosis purposes. Recently there has been an increasing trend towards the use of higher order statistics for fault detection within mechanical systems based on the observation that impulsive signals tend to increase the kurtosis values. This paper considers the use of the third and fourth order Wigner moment spectra, called the Wigner bi- and tri- spectra receptively, for analysing such signals. Expressions for the auto-and cross-terms in these distributions are presented and discussed. It is shown that the Wigner trispectrum is a more suitable analysis tool and it performance is compared to its second order counterpart for detecting impulsive signals. These methods are also applied to measured data sets from an industrial gearbox.

• Communications for Statistical Applications and Methods
• /
• 제18권1호
• /
• pp.147-153
• /
• 2011

In this paper a new sampling procedure for estimating the population mean is introduced. The performance of the new population mean estimator is discussed, along with its properties, and it is shown that the proposed method generates an unbiased estimator. The relative efficiency of the suggested estimator is computed, in regards to the simple random sample(SRS), and comparisons are made to the ranked set sampling(RSS) and extreme ranked set sampling(ERSS) estimators used for asymmetric distributions. The results indicate that the proposed estimator is more efficient than the estimators based on the ERSS. In addition, the folded ranked set sampling(FRSS) procedure has an advantage over the RSS and ERSS in that it reduces the number of unused sampling units.

• Communications for Statistical Applications and Methods
• /
• 제19권5호
• /
• pp.663-671
• /
• 2012

In the present study, a combined ratio cum regression estimator is proposed to estimate the population mean of the study variable in the presence of a non-response using an auxiliary variable under double sampling. The expressions of bias and mean squared error(MSE) based on the proposed estimator is derived under double (or two stage) sampling to the first degree of approximation. Some estimators are also derived from the proposed class by allocating the suitable values of constants used. A comparison of the proposed estimator with the usual unbiased estimator and other derived estimators is carried out. An empirical study is carried out to demonstrate the performance of the suggested estimator and of others; it is endow that the empirical results backing the theoretical study.