• 대한산업공학회지
• /
• 제27권1호
• /
• pp.1-10
• /
• 2001

In the reverse engineering, surfaces are modeled for new products by interpolating the digitized data points obtained by measuring the existing shapes. However, many measuring or deviation errors are happened during the measuring process. If these errors are ignored, designers could get undesirable results. Therefore, it is important to handle such errors and fairing procedure with the esthetics criteria is needed during surface modeling process. This paper presents algorithms for the fairing of B-spline surfaces. The algorithms are based on automatic repositioning of control points for B-spline surfaces. New positions of the control points are determined by solving a non-linear programming of which the objective functions are derived variously using derived surfaces and constraints are established by distance measures between the original and the modified control points. Changes in surface shapes are analyzed by illustrations of their shapes and continuous plotting of gaussian and mean curvatures.

• Journal of Information Processing Systems
• /
• 제7권4호
• /
• pp.595-612
• /
• 2011

Most organizations use performance appraisal system to evaluate the effectiveness and efficiency of their employees. In evaluating staff performance, performance appraisal usually involves awarding numerical values or linguistic labels to employees performance. These values and labels are used to represent each staff achievement by reasoning incorporated in the arithmetical or statistical methods. However, the staff performance appraisal may involve judgments which are based on imprecise data especially when a person (the superior) tries to interpret another person's (his/her subordinate) performance. Thus, the scores awarded by the appraiser are only approximations. From fuzzy logic perspective, the performance of the appraisee involves the measurement of his/her ability, competence and skills, which are actually fuzzy concepts that can be captured in fuzzy terms. Accordingly, fuzzy approach can be used to handle these imprecision and uncertainty information. Therefore, the performance appraisal system can be examined using Fuzzy Logic Approach, which is carried out in the study. The study utilized a Cascaded fuzzy inference system to generate the performance qualities of some University non-teaching staff that are based on specific performance appraisal criteria.

• 한국건강관리협회지
• /
• 제2권1호
• /
• pp.1-8
• /
• 2004

Background : Since 2001 the Korean Association of Health Promotion has attempted to establish her own reference valves that can be used in her all fifteen branch laboratories instead of using those adapted from the published data or there commended data by the reagent companies supplied as inserts. However, the previous two reference values derived from the statistics(year 2001 and 2002) were need to adjust to apply to actual practice. Besides there was an unavoidable situation that the reagent has to be changed to other companies in 2002 that creates another statistical problem. Subsequently, the third attempt to derive the reference ranges of tests in KAHP to solve those problems and define common)v acceptable reference ranges was done and and reported here. Methods : Al1 the results performed during January 2, 2003 through September 30, 2003 were collected in Excel tile format. All the data include dthe necessary information such as age and sex. The age was grouped in six; baby(0-3y), children(4-l2y), adolescent(13-l8y), adult(19-S4y), younger elderly (65-79y),old elderly(oyer 80y), with references of statistics in medical informatics and WHO classification. The data were statistically analyzed with SAS 6.04 for-Gaussian distribution as the previous two occasions. None of the tests showed Gaussian distribution. These procedures had been repeated twice or three times after trimming out the results lying outside three standard deviations. Though, all the tests showed non-Gaussian distribution. Subsequently, the reference ranges were defined in the range from the point of lower 2.5% to the point of higher 97.5 %. And in case the lower range could be "0", the reference ranges were defined in the range of 0 to 95%.Results : The reference ranges of most of 56 test items were newly assigned. Also with adaptation of the recommendation of WHO etc. on fasting blood sugar, hemoglobin, cholesterol. Among these there were eight tests that needed reference ranges by the age groups and nine tests by the sex. Conclusions : The third attempt will credit more the reference range of all15 laboratories of Korean Association of Health Promotion, which will be essential part of the better service to the patient and clients to visit KAHP.

• 한국통신학회논문지
• /
• 제41권8호
• /
• pp.851-858
• /
• 2016

본 논문은 비음수 행렬 인수분해(NMF)의 확률적 해석에 근거한 새로운 통계적 음성검출기법을 제안한다. NMF의 기저와 부호화 행렬들이 주어졌을 때, 데이터 행렬의 분포를 Poisson 분포로 가정한 로그 우도는 Kullback-Leibler 발산을 이용한 NMF의 목적 함수와 일치한다. 이러한 NMF의 확률모델에 근거하여 음성검출을 위해 DFT영역에서 잡음과 음성의 크기 스펙트럼을 Poisson 분포로 모델링하여 새로운 우도비 검출 규칙을 유도한다. 실험 결과를 통해 제안된 기법이 0-15dB 신호 대 잡음비의 시뮬레이션 환경에서 기존 Gaussian과 NMF을 사용한 기법보다 향상된 음성검출 결과를 보여준다.

• 한국지능시스템학회논문지
• /
• 제24권5호
• /
• pp.529-535
• /
• 2014

본 논문에서는 interval type-2 possibilistic fuzzy C-means(IT2PFCM) 클러스터링 방법에 multiple Gaussian kernels을 기반으로 한 possibilistic fuzzy C-means multiple kernels(PFCM-MK) 알고리즘을 결합하여 적응적인 하이브리드 클러스터링 방법인 multiple kernels interval type-2 possibilistic fuzzy C-means(IT2PFCM-MK) 방법을 제안 하였다. 일반적으로 possibilistic fuzzy C-means(PFCM) 알고리즘은 fuzzy C-means(FCM) 알고리즘의 단점인 노이즈 민감성 및 특이점 문제와 알고리즘 초기 클러스터의 Prototype에 따라 위치가 겹치는 문제를 해결하기 위해 제안 되었다. 하지만 이 방법 역시 퍼지화 파라미터 값에 따라 위와 같은 문제를 여전히 가지고 있기 때문에 이와 같은 문제를 보완하기 위해 interval type-2 퍼지 접근 방법을 이용 하는 interval type-2 possibilistic fuzzy C-means(IT2PFCM) 알고리즘을 제안 하였다. 또한 multiple kernels 함수를 interval type-2 possibilistic fuzzy C-means(IT2PFCM) 알고리즘에 적용하여 분류하기 복잡한 형태의 데이터와 노이즈가 있는 데이터에 대하여 보다 정확하고, 향상된 클러스터링을 수행할 수 있다.

• The Korean Journal of Physiology and Pharmacology
• /
• 제13권5호
• /
• pp.367-371
• /
• 2009

The estimation of 90% parametric confidence intervals (CIs) of mean AUC and Cmax ratios in bioequivalence (BE) tests are based upon the assumption that formulation effects in log-transformed data are normally distributed. To compare the parametric CIs with those obtained from nonparametric methods we performed repeated estimation of bootstrap-resampled datasets. The AUC and Cmax values from 3 archived datasets were used. BE tests on 1,000 resampled data sets from each archived dataset were performed using SAS (Enterprise Guide Ver.3). Bootstrap nonparametric 90% CIs of formulation effects were then compared with the parametric 90% CIs of the original datasets. The 90% CIs of formulation effects estimated from the 3 archived datasets were slightly different from nonparametric 90% CIs obtained from BE tests on resampled datasets. Histograms and density curves of formulation effects obtained from resampled datasets were similar to those of normal distribution. However, in 2 of 3 resampled log (AUC) datasets, the estimates of formulation effects did not follow the Gaussian distribution. Bias-corrected and accelerated (BCa) CIs, one of the nonparametric CIs of formulation effects, shifted outside the parametric 90% CIs of the archived datasets in these 2 non-normally distributed resampled log (AUC) datasets. Currently, the 80~125% rule based upon the parametric 90% CIs is widely accepted under the assumption of normally distributed formulation effects in log-transformed data. However, nonparametric CIs may be a better choice when data do not follow this assumption.

• 지구물리와물리탐사
• /
• 제15권4호
• /
• pp.177-189
• /
• 2012

복합 물리탐사(전기비저항, MT)와 지질(시추 자료 및 코어 물성)정보에 대해 지구통계학적 복합해석 기법을 적용하여 3차원 광체 모델링 평가를 수행하였다. 우선, 복합 물리탐사를 통해 시추공 및 그 외의 전체적인 지역에 대한 비저항대 분포를 파악할 수 있었으며, 코어 물성 시험을 통해 연구지역의 자철석(광체)이 코어 내부의 밀도가 높은 전도성 성분(Fe)에 의해 밀도의 증가에 따라 비저항이 감소하는 상관관계를 나타냄을 파악하였다. 3차원 광체 모델링을 수행하기 위해 사용된 자료는 전기비저항 탐사, MT 탐사, 물성 자료와 시추 자료 등이며, 전체 획득 자료 및 시추 자료에서 추출한 광체의 품위 자료를 이용하였다. 본 연구에서는 자료의 복합 해석을 위해 지구통계학적 기법 중에서, 부족한 실제 측정 자료의 평균 및 분산을 잘 재생시키는 실현 값을 통해 지역적으로 변화하는 불균질성을 잘 묘사하는 순차 가우시안 시뮬레이션(sequential Gaussian simulation)을 사용하였다. 획득된 전체 자료와 품위 자료만을 이용하여 도출한 시뮬레이션 결과, 광체가 기존에 연구되어 존재하는 잔광체의 일정 부분에서 유사한 분포를 나타냈으며, 추가적으로 하부 깊은 심도에 대해 광체의 분포 양상을 추정할 수 있었다.

• Journal of Advanced Marine Engineering and Technology
• /
• 제25권5호
• /
• pp.1058-1064
• /
• 2001

In this paper, the development of probability distribution estimation program for fatigue crack growth lives was summarize. The probability distribution estimation program of life was developed to increase the reliability of life estimation. In this study, it is considered that the cause of scatter in fatigue crack growth data is due to material inhomogeneity. The material resistance to fatigue crack growth is modelled as a spatial stochastic process, which varies randomly along the crack path. We developed the GUI program to estimate the probability distribution and reliability using the non-Gaussian stochastic process method. This program can be used for the reliability assessment.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2001년도 추계학술대회 논문집
• /
• pp.232-237
• /
• 2001

The evaluation of specimen thickness effect of fatigue crack growth life by the simulation of probabilistic fatigue crack growth is presented. In this paper, the material resistance to fatigue crack growth is treated as a spatial stochastic process, which varies randomly on the crack surface. Using the previous experimental data, the non-Gaussian(eventually Weibull, in this report) random fields simulation method is applied. This method is useful to estimate the probability distribution of fatigue crack growth life and the variability due to specimen thickness by simulating material resistance to fatigue crack growth along a crack path.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권4호
• /
• pp.221-227
• /
• 2007

This paper introduces an on-line particle-filtering-based framework for failure prognosis in nonlinear, non-Gaussian systems. This framework uses a nonlinear state-space model of the plant(with unknown time-varying parameters) and a particle filtering(PF) algorithm to estimate the probability density function(pdf) of the state in real-time. The state pdf estimate is then used to predict the evolution in time of the fault indicator, obtaining as a result the pdf of the remaining useful life(RUL) for the faulty subsystem. This approach provides information about the precision and accuracy of long-term predictions, RUL expectations, and 95% confidence intervals for the condition under study. Data from a seeded fault test for a UH-60 planetary carrier plate are used to validate the proposed methodology.