• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2002년도 춘계종합학술대회
• /
• pp.590-593
• /
• 2002

본 논문은 그레이영상에 대해 2D 스플라인 보간법과 2D 웨이블릿 변환을 적용하여 영상모핑을 실현한 연구이다. 프레임 간 특징 점 지정에 스플라인 함수로 B-스플라인 보간법을, 생성되는 중간 영상에 웨이블릿 변환 기법을 적용하였다. 그 결과 스플라인에 의해 유동적인 곡선변형과 웨이블릿 변환에 의해 블럭킹 열화가 제거되어 중간 영상들의 자연스러운 모핑이 이뤄졌다.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1047-1058
• /
• 2008

Prediction of total sales in information security industry is considered. Exponential smoothing and spline smoothing is applied to the time series of annual sales data. Due to the different survey items of every year, we recollect the original survey data by some basic criterion and predict the sales to 2014. We show the total sales in infonnation security industry are increasing gradually by year.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1990년도 추계학술대회
• /
• pp.38-41
• /
• 1990

A new spline function for resampling discrete signal adaptively is proposed. In general, B-spline function is used for an image interpolation because of its smoothness and continuity, but accompanies a large amount of blurring effect. Hence, we developed a new spline function to remedy this effect, with two procedures ; deblurring of Gaussian blurring and diminishing of aliasing effect caused by deblurring procedure. The proposed function has a parametric expression with $\alpha$ which is related to the variance of Gaussian blurring model. Locally adaptive resampling scheme is obtained by changing a according to statistical characteristics of an image. The proposed, interpolation function shows edge-sharpening effect as well as noise smoothing, with comparison to the conventional schemes.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.249-254
• /
• 1987

This paper presents a new method for generating smooth free-form surface by local correction. B-spline surface is used for its convenience of local correction, and the direction of surface correction is fixed to the average-surface-normal direction. The surface to be corrected is approximated into a uniform cubic B-spline surface. Then, the smoothness (curvature arrows, iso-parametric lines) of the approximated surface is displayed with B-spline control points. When a control point near the region that needs correction is selected, a new point 1 mm higher than the original control point in the direction of the average surface normal is displayed. And the surface is corrected by giving the amount of control point movement interactively. Since the direction of correction is given by the program and the amount of correction is selected by the user, the method is called semiautomatic. sufficiently smooth surface can be obtained by this method. Examples are given to illustrate the method.

• Communications for Statistical Applications and Methods
• /
• 제19권6호
• /
• pp.809-817
• /
• 2012

We propose a semiparametric inference for a generalized varying coefficient partially linear model(VCPLM) for negative binomial data. The VCPLM is useful to model real data in that varying coefficients are a special type of interaction between explanatory variables and partially linear models fit both parametric and nonparametric terms. The negative binomial distribution often arise in modelling count data which usually are overdispersed. The varying coefficient function estimators and regression parameters in generalized VCPLM are obtained by formulating a penalized likelihood through smoothing splines for negative binomial data when the shape parameter is known. The performance of the proposed method is then evaluated by simulations.

• 응용통계연구
• /
• 제11권2호
• /
• pp.363-376
• /
• 1998

선형 평활스플라인 추정은 경계 편의의 영향력을 제거 하기위해 수정된 것이다. 제시된 추정량은 적합된 값들과 관련있는 평활 모수 선택 기준의 계산을 개선시킨 O(n) 얄고리즘을 사용하여 효과적으로 계산할 수 있게 하였다. 추정량의 점근적 성질들이 균일 계획의 경우에 대하여 연구되었다. 이 경우에 경계수정 선형 평활스플라인들의 평균 제곱 오차의 성질들은 표준 이차 커널 평활들에 대한 평균제곱오차들과 점근적 특성으로 비교하였다.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• 한국항공우주학회지
• /
• 제39권12호
• /
• pp.1124-1132
• /
• 2011

본 논문에서는 2차원 공간에서 기동하는 고정익 무인항공기의 장애물 회피를 위한 부드러운 경로궤적을 생성하는 문제를 다룬다. 2차원 장애물맵의 이산화 모델링을 위해 육각형 격자를 채택하였고, 이는 사각형 격자에 비해 연결성이 높아 부드러운 경로궤적 생성이 가능하도록 하였다. 특히 본 논문에서 제안된 경로템플릿 기법은 일정거리 단위로 조합 가능한 대표경로들(경로템플릿)을 사용하여 무인항공기의 기준경로를 생성하는 방법이고, 온라인 경로궤적 생성에서 계산량을 줄여 메모리 및 연산리소스가 제한되는 소형 오토파일럿에서도 적용이 가능하다는 장점이 있다.

• Journal of Mechanical Science and Technology
• /
• 제14권5호
• /
• pp.518-529
• /
• 2000

A detailed and thorough parametric study of digital image correlation method is presented. A theoretical background and development of the method were introduced and the effects of various parameters on the determination of displacement outputs from the raw original and deformed image information were examined. Use of the normalized correlation coefficient, the use of 20 to 40 pixels for a searching window side, 6 variables searching, bi-cubic spline sub pixel interpolations and the use of coarse-fine search are some of the key choices among the results of parametric studies. The displacement outputs can be further processed with two dimensional curve fitting for the data noise reduction as well as displacement gradient calculation.

• Communications for Statistical Applications and Methods
• /
• 제16권4호
• /
• pp.713-722
• /
• 2009

The estimation of odds ratio and corresponding confidence intervals for case-control data have been done by traditional generalized linear models which assumed that the logarithm of odds ratio is linearly related to risk factors. We adapt a lower-dimensional approximation of Gu and Kim (2002) to provide a faster computation in nonparametric method for the estimation of odds ratio by allowing flexibility of the estimating function and its Bayesian confidence interval under the Bayes model for the lower-dimensional approximations. Simulation studies showed that taking larger samples with the lower-dimensional approximations help to improve the smoothing spline estimates of odds ratio in this settings. The proposed method can be used to analyze case-control data in medical studies.