• Communications for Statistical Applications and Methods
• /
• 제5권2호
• /
• pp.277-285
• /
• 1998

The smoothing parameter $\lambda$ in smoothing spline regression is usually selected by minimizing cross-validation (CV) or generalized cross-validation (GCV). But, simple CV or GCV is poor candidate for estimating prediction error. We defined MGCV (Multifold Generalized Cross-validation) as a criterion for selecting smoothing parameter in smoothing spline regression. This is a version of cross-validation using $leave-\kappa-out$ method. Some numerical results comparing MGCV and GCV are done.

• 한국통신학회논문지
• /
• 제22권1호
• /
• pp.185-192
• /
• 1997

We propose a method of paramete estimation using order-of-magnitude analysis for optimal boundary smoothing in Mean Field Annealing(MFA) technique in this paper. We previously proposed two boundary smoothing methods for consistent object representation in the previous paper, one is using a constratined regulaization(CR) method and the other is using a MFA method. The CR method causes unnecessary smoothing effects at corners. On the other hand, the MFA method method smooths our the noise without losing sharpness of corners. The MFA algorithm is influenced by several parameters such as standard deviation of the noise, the relativemagnitude of prior ter, initial temperature and final temperature. We propose a general parameter esimation method for optimal boundary smoothing using order-of-magnitude analysis to be used for consistent object representation in this paper. In addition, we prove the effectiveness of our parameter estimation and also show the temperature parameter sensitivities of the algorithm.

• Journal of the Korean Data and Information Science Society
• /
• 제7권2호
• /
• pp.257-262
• /
• 1996

본 논문은 스플라인 희귀모형에서 평활모수를 추정할 때 사전 작업으로 영향력 진단을 하는 문제를 다룬다. 평활모수의 추정방법으로 일반화최대우도함수법을 사용할 때, 얻어지는 추정 치에 영향을 주는 관측치를 진단하는 측도를 제안하고, 찾아낸 영향력 관측치를 수정하여 올바른 평활모수 추정치를 찾는 방법을 소개한다.

• Journal of the Korean Statistical Society
• /
• 제24권2호
• /
• pp.495-506
• /
• 1995

We present formula for detecting influential observations on the smoothing parameter in smoothing spline. Further, we express them as functions of basic building blocks such as residuals and leverage, and compare it with the local influence approach by Thomas (1991). An example based on a real data set is given.

• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.23-32
• /
• 2007

We consider penalized likelihood regression with data from the negative binomial distribution with unknown shape parameter. Smoothing parameter selection and asymptotically efficient low dimensional approximations are employed for negative binomial data along with shape parameter estimation through several different algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.273-273
• /
• 2000

We present a new scheme to increase the performance of edge-preserving image smoothing from the parameter tuning of a Markov random field (MRF) function. The method is based on automatic control of the image smoothing-strength in MRF model ing in which an introduced parameter function is based on control of enforcing power of a discontinuity-adaptive Markov function and edge magnitude resulted from discontinuities of image intensity. Without any binary decision for the edge magnitude, adaptive control of the enforcing power with the full edge magnitude could improve the performance of discontinuity-preserving image smoothing.

• 대한의용생체공학회:의공학회지
• /
• 제38권5호
• /
• pp.219-226
• /
• 2017

Penalized-likelihood (PL) reconstruction methods for transmission tomography are known to provide improved image quality for reduced dose level by efficiently smoothing out noise while preserving edges. Unfortunately, however, most of the edge-preserving penalty functions used in conventional PL methods contain at least one free parameter which controls the shape of a non-quadratic penalty function to adjust the sensitivity of edge preservation. In this work, to avoid difficulties in finding a proper value of the free parameter involved in a non-quadratic penalty function, we propose a new adaptive method of space-variant smoothing with a simple quadratic penalty function. In this method, the smoothing parameter is adaptively selected for each pixel location at each iteration by using the image roughness measured by a pixel-wise standard deviation image calculated from the previous iteration. The experimental results demonstrate that our new method not only preserves edges, but also suppresses noise well in monotonic regions without requiring additional processes to select free parameters that may otherwise be included in a non-quadratic penalty function.

• Communications for Statistical Applications and Methods
• /
• 제15권2호
• /
• pp.283-292
• /
• 2008

커널밀도함수의 추정을 이용한 분류 문제에서 평활모수(smoothing parameter, bandwidth)의 선택은 핵심적으로 중요한 역할을 한다. 본 논문에서는 분류에서 베이즈 리스크를 최적화하기 위한 평활모수의 선택이 각 개별 확률밀도함수를 추정하기 위한 최적의 평활모수와 어떤 관계가 있는지 살펴보았다. 실제 상황에서 사용할 수 있는 평활모수의 선택 방법으로 붓스트랩(bootstrap)과 교차확인법(cross-validation)을 이용하는 것을 비교한 결과, 붓스트랩 방법은 Hall과 Kang (2005)에서 밝혀진 이론적인 성질에 부합하는 반면 교차확인법은 그렇지 못함을 확인하였다. 또한, 각 방법으로 정한 평활모수를 사용하여 오분류율을 조사해 본 결과에서도 붓스트랩 방법이 우월함을 알 수 있었다.

• Communications for Statistical Applications and Methods
• /
• 제12권3호
• /
• pp.743-758
• /
• 2005

This paper consider penalized likelihood regression with data from exponential family. The fast computation method applied to Gaussian data(Kim and Gu, 2004) is extended to non Gaussian data through asymptotically efficient low dimensional approximations and corresponding algorithm is proposed. Also smoothing parameter selection is explored for various exponential families, which extends the existing cross validation method of Xiang and Wahba evaluated only with Bernoulli data.

• 품질경영학회지
• /
• 제25권4호
• /
• pp.106-114
• /
• 1997

The smoothing parameter or bandwidth is crucial to performance of the kernel based regression estimator. So the choice of a "optimal" smoothing parameter produce a single curve estimate. If a single estimate is replaced by a family of estimates, it become easy that we understand what varies with choice of the smoothing parameter. This paper suggests the threshold of the maximum bandwidth and the number of the family members in the regression context.n context.