• 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.

• International Journal of Precision Engineering and Manufacturing
• /
• 제5권4호
• /
• pp.21-27
• /
• 2004

In this paper, data acquisition and analysis of a measuring machine for marine engine's cams are discussed. A rotary encoder and linear scale of the machine to measure angular and linear displacement, respectively, are interfaced to the PC via an encoder board with 2 channels. The design and measuring data are interpolated by cubic spline curves to compute the precision error which is defined by the maximum and minimum distances between two curves. The minimum zone fit of ISO is employed to evaluate the geometric deviation. The developed system takes only 5 minutes to measure and analyze the precision error while the CMM takes over I hours even with a skilled operator.

• 한국정밀공학회지
• /
• 제17권1호
• /
• pp.192-197
• /
• 2000

In CNC machining, a free curve is cut into small linear segments using the linear interpolation(G01) method. Therefore, the interpolation error along the curve is not constant due to the changing curvature. This paper presents a NURBS (Non-Uniform Rational B-Spline) interpolation algorithm for machining free curves with high precision and high speed. The proposed NURBS interpolation defines the tool path with NURBS parameters and limits the interpolation error to any desired level by adjusting the feed rate considering the curvature of the shape and sampling time. Both linear and NURBS interpolations are compared to show the validity of the proposed algorithm.

• Communications for Statistical Applications and Methods
• /
• 제26권1호
• /
• pp.69-78
• /
• 2019

A structured model with both single-index and varying coefficients is a powerful tool in modeling high dimensional data. It has been widely used because the single-index can overcome the curse of dimensionality and varying coefficients can allow nonlinear interaction effects in the model. For high dimensional index vectors, variable selection becomes an important question in the model building process. In this paper, we propose an efficient estimation and a variable selection method based on a smoothing spline approach in a partially linear single-index-coefficient regression model. We also propose an efficient algorithm for simultaneously estimating the coefficient functions in a data-adaptive lower-dimensional approximation space and selecting significant variables in the index with the adaptive LASSO penalty. The empirical performance of the proposed method is illustrated with simulated and real data examples.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(2)
• /
• pp.71-74
• /
• 2000

The purpose of format conversion is to convert a wide range of personal computer video formats into a target format. Circuits for the conversion have been developed by means of interpolation techniques, such as zero-order interpolation, bilinear interpolation, and bisigmoidal interpolation. This paper proposes a scan converter using cubic splines. The converter was modeled in VHDL on Max+PlusII and implemented with an FPGA chip. The circuit gives much better conversion performance than a scan converter with zero-order or linear interpolation.

• 품질경영학회지
• /
• 제27권2호
• /
• pp.152-162
• /
• 1999

In this paper we develope a new nonparametric estimator of the reliability in strength-stress model. This estimator is constructed using the maximum likelihood estimate of cumulative failure rate in the class of distributions which have piecewise linear failure rate functions between each pair of observations. Large sample properties of our estimator are examined. The proposed estimator is compared with previously known estimator by Monte Carlo study.

• 한국시뮬레이션학회논문지
• /
• 제9권4호
• /
• pp.11-23
• /
• 2000

The purpose of format conversion is to convert a wide range of personal computer video formats into a target format. Circuits for the conversion have been developed by means of interpolation techniques, such as zero-order interpolation, bilinear interpolation, and bisigmoidal interpolation. This paper proposes a scan converter using cubic splines. The converter was modeled in VHDL, simulated on Max+plus Ⅱ , and implemented with an FPGA chip. The circuit gives much better conversion performance than a scan converter with zero-order or linear interpolation techniques according to simulation results and implementation.

• 한국시뮬레이션학회:학술대회논문집
• /
• 한국시뮬레이션학회 2000년도 춘계학술대회 논문집
• /
• pp.91-95
• /
• 2000

The purpose of format conversion is to convert a wide range of personal computer video formats to a target format. Circuits for the conversion has been developed by means of interpolation techniques, such as zero-order interpolation, bilinear interpolation, and bisigmoidal interpolation. This paper proposes a scan converter using cubic splines. The converter was modeled in VHDL on Max+Plus II and implemented with an FPGA cpip. The circuit gives much better conversion performance than a scan converter with zero-order or linear interpolation.

• 한국정보과학회논문지:데이타베이스
• /
• 제29권6호
• /
• pp.441-452
• /
• 2002

데이타베이스를 이용하여 연속적인 이동 객체를 관리할 경우 매 시간마다 변경된 모든 위치 정보를 저장하는 것은 불가능하다. 그러므로, 일정한 비율의 시간 주기를 결정한 후 매 주기마다 이동 객체의 위치 정보를 이산적으로 저장하게 된다. 그러나 연속적인 모델의 이동 객체를 이산적인 형태로 관리하게 될 경우, 데이타베이스에 저장되지 않은 불확실한 과거 및 미래의 위치 정보에 대한 질의에 적절히 응답할 수 없는 문제점이 발생된다. 이러한 문제점을 해결하기 위해 이 논문에서는 동일한 데이터베이스에 저장된 이력정보를 이용한 이동 객체 외 과거 및 미래의 위치 추정 방법과 알고리즘을 제안한다. 이 때 3차 스플라인 보간법을 적용하여 이동 객체의 과거 위치를 추정하고, 이력정보의 평균 이동 값을 구하여 미래의 위치를 추정한다. 결국, 가상 이동경로 및 위치 샘플을 이용한 위치 추정 실험을 통해 제안한 3차 스플라인 함수가 선형 함수보다 더 적은 오차를 발생시킴을 보였다.

• 한국컴퓨터그래픽스학회논문지
• /
• 제22권5호
• /
• pp.1-16
• /
• 2016

본 논문에서는 최소자승법에 기반한 효율적인 곡선 복구 기법을 제안한다. 구체적으로는, 법선 벡터를 포함한 평면상의 샘플포인트가 주어졌을 때 계층적인 ZP(Zwart-Powell)-스플라인의 레벨로 곡선을 복구하는데, 세밀한 부문을 복구하면서도 비교적 큰 구멍도 효율적으로 메꾸고 있다. 정규화를 위해서는, (1) 선형시스템의 특이성을 피하기 위한 티코노프 정규항과 (2) 아이소커브를 부드럽게 하기 위한 이산 라플라스 정규항 두 가지를 사용하고 있다. 정량적인 벤치마크 테스트를 통해 비교한 결과, 본 방법은 다항식에 기반한 기법들에 비해 훨씬 우수한 결과를 보여준다는 것을 확인할 수 있다. 구멍이 있는 데이터의 경우, 계층적인 B-스플라인과 비교해본 결과 엇비슷한 품질을 보이지만 약 90%의 계산량만을 필요로 한다.