• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.137-148
• /
• 2001

Compositional data found in many practical applications consist of non-negative vectors of proportions with the constraint which the sum of the elements of each vector is unity. It is well-known that the statistical analysis of compositional data suffers from the unit-sum constraint. Moreover, the non-linear pattern frequently displayed by the data does not facilitate the application of the linear multivariate techniques such as principal component analysis. In this paper we develop new type of principal component analysis for compositional data using Box-Cox contrast transformation. Numerical illustrations are provided for comparative purpose.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10b
• /
• pp.1839-1844
• /
• 1991

For a single-input nonlinear system, the transformation which transposes the nonlinear system to a controllable-like canonical system has been proposed. However this method islimited by a single-input system and it is difficult to apply the method actually. In this paper we propose a method which transposes the nonlinear system with multi-input into an equivalent pseudo-linear system. And we apply the pseudo-linear system to a linear optimal regulator. To confirm the effectiveness of the proposed method, a transient stability control of the generator with an excitor and a governor is considered.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.494-498
• /
• 1996

Three fuzzy input space partitoining methods, which are grid, tree, and scatter method, are mainly used until now. These partition methods represent good performance in the modeling of the linear system and nonlinear system with independent modeling variables. But in the case of the nonlinear system with the coupled modeling variables, there should be many fuzzy rules for acquiring the exact fuzzy model. In this paper, it shows that the fuzzy model is acquired using transformed modeling vector by linear transformation of the modeling vector.

• Journal of Sensor Science and Technology
• /
• v.23 no.1
• /
• pp.66-71
• /
• 2014

Vision is the most important sensing capability for both men and sensory smart machines, such as intelligent robots. Sensed real 3D world and its 2D camera image can be related mathematically by a process called camera calibration. In this paper, we present a novel linear solution of camera calibration. Unlike most existing linear calibration methods, the proposed technique of this paper can identify camera parameters explicitly. Through the step-by-step procedure of the proposed method, the real physical elements of the perspective projection transformation matrix between 3D points and the corresponding 2D image points can be identified. This explicit solution will be useful for many practical 3D sensing applications including robotics. We verified the proposed method by using various cameras of different conditions.

• Journal of computational fluids engineering
• /
• v.5 no.1
• /
• pp.14-21
• /
• 2000

A method of two and three dimensional orthogonal grid generation with control of spacing by using the covariant Laplace equation is presented. An important feature of the methodology is its ability to control effectively the grid spacing especially near the boundaries still maintaining good orthogonality in whole field. The method is based on the concept of decomposition of the global transformation into consecutive transformation of an approximate conformal mapping and an auxiliary orthogonal mapping to have linear and uncoupled equations. Control of cell spacing is based on the concept of reference arc length, and orthogonal correction is peformed in the auxiliary domain. It is concluded that the methodology can successfully generate well controlled orthogonal grids around bodies of 2 and 3 dimensional configurations.

• Communications for Statistical Applications and Methods
• /
• v.13 no.2
• /
• pp.273-283
• /
• 2006

In bioassay, the response curve is usually assumed monotone increasing, but its exact form is unknown, so it is very difficult to select the proper functional form for the parametric model. Therefore, we should probably use the nonparametric regression model rather than the parametric model unless we have at least the partial information about the true response curve. However, it is well known that the nonparametric regression estimate is not necessarily monotone. Therefore the monotonizing transformation technique is of course required. In this paper, we compare the finite sample properties of the monotone transformation methods which can be applied to the local linear quasi-likelihood response curve estimate.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.50 no.9
• /
• pp.409-416
• /
• 2001

This paper deals with the design of delay-dependent $H_{\infty}$ control for time-delayed linear systems. We propose the two different model transformations to handle efficiently the time delay and derive conditions linear matrix inequalities (LMI's) of which are dependent on the size of time-delay and its time-derivative. The $H_{\infty}$ controller is obtained by checking the feasibility of these LMI's. Finally, we show the usefulness and applicability of our results by an example.

• Computers and Concrete
• /
• v.34 no.1
• /
• pp.79-91
• /
• 2024

In symmetric cryptography, a cryptographically secure Substitution-Box (S-Box) is a key component of a block cipher. S-Box adds a confusion layer in block ciphers that provide resistance against well-known attacks. The generation of a cryptographically secure S-Box depends upon its generation mechanism. In this paper, we propose a novel framework for the construction of cryptographically secure S-Boxes. This framework uses a combination of linear fractional transformation and permutation functions. S-Boxes security is analyzed against well-known security criteria that include nonlinearity, bijectiveness, strict avalanche and bits independence criteria, linear and differential approximation probability. The S-Boxes can be used in the encryption of any grayscale digital images. The encrypted images are analyzed against well-known image analysis criteria that include pixel changing rates, correlation, entropy, and average change of intensity. The analysis of the encrypted image shows that our image encryption scheme is secure.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.35 no.2
• /
• pp.41-48
• /
• 2023

In this study, simplified linear numerical method that can simulate wave generation and transformation by a moving bottom is introduced. Numerical analysis is conducted in wave number domain after continuity equation, linear dynamic and kinematic free surface boundary conditions and linear kinematic bottom boundary condition are Fourier transformed, and the results are expressed in space domain by an inverse Fourier transform. In the wavenumber domain, the dynamic free water surface boundary condition and the kinematic free water surface boundary condition are numerically calculated, and the velocity potential in the mean water level (z = 0) satisfies the continuity equation and the kinematic bottom boundary condition. Wave generation and transformation are investigated when the triangular and rectangular shape of bottoms move periodically. The results of the simplified numerical method are compared with the results of previous analytical solutions and agree well with them. Stability of numerical results according to the calculation time interval (Δt) and the calculation wave number interval (Δk) was also investigated. It was found that the numerical results were appropriate when Δt ≤ T(period)/1000 and Δk ≤ π/100.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.161-166
• /
• 2003

In this paper, a new form of generalized linear models is proposed. The proposed models consist of a distribution function of the mean response and a weighted linear combination of distribution functions of covariates. This form addresses a structural problem of the link function in the generalized linear models. Markov chain Monte Carlo methods are used to estimate the parameters within a Bayesian framework.