• Journal of the Korean Data and Information Science Society
• /
• 제20권2호
• /
• pp.357-367
• /
• 2009

현대 의학이 나날이 발전해 가는데 따라 관련 연구들도 활발히 진행되고 있다. 연구자가 원하는 연구의 결과를 얻기 위해서는 연구 설계, 연구 진행과 결과 분석까지 객관적이며 합리적인 방법으로 행해져야 할 것이다. 이를 위해 통계적 분석 방법이 다양하고 널리 사용 되고 있다. 본 논문은 현재 발행되고 있는 여러 의학 학술지중 네 개의 학회지를 대상으로 2004년부터 2007년까지 출판된 의학 논문에서 통계적 기법의 사용에 대해 조사하여 의학 연구에서 어떻게 적용되고 있는지 살펴보고자 한다.

• 응용통계연구
• /
• 제19권2호
• /
• pp.369-377
• /
• 2006

현재 발생중인 시계열 데이터에 분산변화가 일어날 경우 이동 분산비를 사용하여 분산 변화점을 빠른 시간 내에 탐지하는 문제를 다룬다. 이동 분산비의 분포로서 F분포와 데이터에 의존하여 추정되는 실증적 분포를 제안한 후 상호비교를 통하여, 어느 방법이 시계열 데이터에서 분산의 변화점을 잘 탐지하는지 연구하였다.

• Communications for Statistical Applications and Methods
• /
• 제3권3호
• /
• pp.113-123
• /
• 1996

Data-dependent (adaptive) choice of asymptotically efficient score functions for rank estimators and M-estimators of regression parameters in a linear regression model with left-truncated and right-censored data are developed herein. The locally adaptive smoothing techniques of Muller and Wang (1990) and Uzunogullari and Wang (1992) provide good estimates of the hazard function h and its derivative h' from left-truncated and right-censored data. However, since we need to estimate h'/h for the asymptotically optimal choice of score functions, the naive estimator, which is just a ratio of estimated h' and h, turns out to have a few drawbacks. An altermative method to overcome these shortcomings and also to speed up the algorithms is developed. In particular, we use a subroutine of the PPR (Projection Pursuit Regression) method coded by Friedman and Stuetzle (1981) to find the nonparametric derivative of log(h) for the problem of estimating h'/h.

• 한국정보보호학회:학술대회논문집
• /
• 한국정보보호학회 2006년도 하계학술대회
• /
• pp.649-653
• /
• 2006

In this paper, we propose a hybrid feature extraction method in which Principal Components Analysis is combined with optimized k-Means clustering technique. Our approach hierarchically reduces the redundancy of features with high explanation in principal components analysis for choosing a good subset of features critical to improve the performance of classifiers. Based on this result, we evaluate the performance of intrusion detection by using Support Vector Machine and a nonparametric approach based on k-Nearest Neighbor over data sets with reduced features. The Experiment results with KDD Cup 1999 dataset show several advantages in terms of computational complexity and our method achieves significant detection rate which shows possibility of detecting successfully attacks.

• 응용통계연구
• /
• 제27권7호
• /
• pp.1197-1205
• /
• 2014

일반적으로 약제 용량 결정 연구는 대조군과 여러 용량 수준을 비교하여 유효성과 안전성을 동시에 만족하는 약물의 치료 범위(therapeutic window)를 찾아내는 데에 관심이 있다. 이 논문에서는 안전성과 유효성을 동시에 만족하는 용량 결정을 위하여 선형 위치(linear placement)에 점수함수(score function)를 이용한 비모수적 검정법을 제안하였다. 또한 Monte Carlo 모의실험을 통하여 기존의 모수적 방법들과 검정력(power)과 FWE(family-wise error rate)를 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제20권1호
• /
• pp.203-209
• /
• 2009

Frailty models are useful for the analysis of correlated and/or heterogeneous survival data. However, the inferences of fixed parameters, rather than random effects, have been mainly studied. The prediction (or estimation) of random effects is also practically useful to investigate the heterogeneity of the hospital or patient effects. In this paper we propose how to extend the prediction method for random effects in HGLMs (hierarchical generalized linear models) to log-normal semiparametric frailty models with nonparametric baseline hazard. The proposed method is demonstrated by a simulation study.

• Structural Engineering and Mechanics
• /
• 제54권2호
• /
• pp.363-378
• /
• 2015

Estimation of geotechnical properties is an essential but challenging task since they are major components governing the safety and reliability of the entire structural system. However, due to time and budget constraints, reliable geotechnical properties estimation using traditional site characterization approach is difficult. In view of this, an alternative efficient and cost effective approach to address the overall uncertainty is necessary to facilitate an economical, safe and reliable geotechnical design. In this paper a probabilistic approach is proposed for real-time updating by incorporating new geotechnical information from the underlying project site. The updated model obtained from the proposed method is advantageous because it incorporates information from both existing database and the site of concern. An application using real data from a site in Hong Kong will be presented to demonstrate the proposed method.

• Industrial Engineering and Management Systems
• /
• 제14권3호
• /
• pp.318-324
• /
• 2015

This paper proposes a dynamic short-term load forecasting method that utilizes a new sequential learning algorithm based on Relevance Vector Machine (RVM). The method performs general optimization of weights and hyperparameters using the current relevance vectors and newly arriving data. By doing so, the proposed algorithm is trained with the most recent data. Consequently, it extends the RVM algorithm to real-time and nonstationary learning processes. The results of application of the proposed algorithm to prediction of electrical loads indicate that its accuracy is comparable to that of existing nonparametric learning algorithms. Further, the proposed model reduces computational complexity.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1019-1026
• /
• 2008

The goal of this paper is to analysis the trend of stream quality about the upstream, middle stream and high areas of Nakdong River measurement points from January 1998 to December 2006. and to suggest some policy alternatives in Nakdong river. It used the three different monthly time series data such as BOD (biochemical oxygen demand), TN (Total Nitrogen) and TP(Total Phosphorus), of the three of Nakdong River measurement points. BOD, TN and TP data are analyzed with the LOWESS(Locally Weighted Scatter plot Smoother) nonparametric method.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.1021-1024
• /
• 2000

In this paper we describe a nonparametric Wilcoxon test and a parametric Z test based on statistical hypothesis testing for the detection of edges. We use the threshold determined by specifying significance level $\alpha$, while Bovik, Huang and Munson[4] consider the range of possible values of test statistics for the threshold. From the experimental results of edge detection, the Z method performs sensitively to the noisy image, while the Wilcoxon method is robust over both noisy nd noise-free images. Comparison with our statistical tests and Sobel operator shows that our tests perform more effectively in both noisy and noise-free images.