• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.121-130
• /
• 1990

In this study, the coefficients of ultrasound attenuation for human liver were determined in 6 normal humans and in 38 patients with diffuse liver disease. The coefficients with linear frequency dependency as well as nonlinear frequency dependency were evaluated. Gaussian pulse propagating in a lossy medium suffers downshifting of a center frequency and decreasing in the bandwidth. Such changes in frequency domain spectrum were quantified in terms of changes in the attenuation coefficients with nonlinear dependency, which in turn improve clinical Implications of the coefficients. Statistical analysis shows that the attenuation coefficients evaluated with nonlinear dependency reflect an improved accuracy for the diffuse liver disease than those with linear dependency. The discriminant analysis also indicate the improved classification with nonlinear dependency(75%) than with linear dependency(61%).

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.3
• /
• pp.148-155
• /
• 2003

In this paper, a nonlinear anisotropic filtering method without the loss of important information happened due to the repeated filtering in magnetic resonance images is proposed. First of all original images are divided into four regions, e.g., SPR(Strong Plain Region), EPR(Easy Plain Region), SER(Strong Edge Region), and EER(Easy Edge Region). An optimal template among multiple templates is selected, then the nonlinear anisotropic filtering based on the template is applied in pixel by pixel basis. In the proposed algorithm, filtering strength of EER containing important information is adjusted very weak and filtering strength for remaining regions is also adjusted according to the degree of the importance. In spite of repeated filtering, resulting images by the proposed method could still preserve anatomy information of original images without any degradation. Compared to the existing nonlinear anisotropic filtering, the proposed filtering method with multiple templates provides higher reliability for filtered images.

• Selected Papers of The Society of Naval Architects of Korea
• /
• v.1 no.1
• /
• pp.91-100
• /
• 1993

A displacement-based finite element method Is presented for the geometrically nonlinear analysis of eccentrically stiffened plates. A nonlinear degenerated shell element and a nonlinear degenerated eccentric isoparametric beam (isobeam) element are formulated on the basis of Total Agrangian and Updated Lagrangian descriptions. In the formulation of the isobeam element, some additional local decrees of freedom are implementd to describe the stiffener's local plate buckling modes. Therefore this element can be effectively employed to model the eccentric stiffener with fewer D.O.F's than the case of a degenerated shell element. Some detailed buckling and nonlinear analyses of an eccentrically stiffened plate are performed to estimate the critical buckling loads and the post buckling behaviors including the local plate buckling of the stiffeners discretized with the degenerated shell elements and the isobeam elements. The critical buckling loads are found to be higher than the analytical plate buckling load but lower than Euler buckling load of the corresponding column, i.e, buckling strength requirements of the Classification Societies for the stiffened plates.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.25 no.4
• /
• pp.55-65
• /
• 2000

This paper presents a linear programming based algorithm for pattern classification. Pattern classification is being considered to be critical in the area of artificial intelligence and business applications. Previous methods employing linear programming have been aimed at two-group discrimination with one or more linear discriminant functions. Therefore, there are some limitations in applying available linear programming formulations directly to general multi-class classification problems. The algorithm proposed in this manuscript is based on quadratic or polynomial discriminant functions, which allow more flexibility in covering the class regions in the N-dimensional space. The proposed algorithm is compared with other competitive methods of pattern classification in experimental results and is shown to be competitive enough for a general purpose classifier.

• Communications for Statistical Applications and Methods
• /
• v.29 no.2
• /
• pp.193-202
• /
• 2022

Semi-supervised learning has gained significant attention in recent applications. In this article, we provide a selective overview of popular semi-supervised methods and then propose a simple but effective algorithm for semi-supervised classification using support vector machines (SVM), one of the most popular binary classifiers in a machine learning community. The idea is simple as follows. First, we apply the dimension reduction to the unlabeled observations and cluster them to assign labels on the reduced space. SVM is then employed to the combined set of labeled and unlabeled observations to construct a classification rule. The use of SVM enables us to extend it to the nonlinear counterpart via kernel trick. Our numerical experiments under various scenarios demonstrate that the proposed method is promising in semi-supervised classification.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.7-12
• /
• 2011

In this papwer, we propose a new feature extraction method, named as Class-augmented Kernel Principal Component Analysis (CA-KPCA), which can extract nonlinear features for classification. Among the subspace method that was being widely used for feature extraction, Class-augmented Principal Component Analysis (CA-PCA) is a recently one that can extract features for a accurate classification without computational difficulties of other methods such as Linear Discriminant Analysis (LDA). However, the features extracted by CA-PCA is still restricted to be in a linear subspace of the original data space, which limites the use of this method for various problems requiring nonlinear features. To resolve this limitation, we apply a kernel trick to develop a new version of CA-PCA to extract nonlinear features, and evaluate its performance by experiments using data sets in the UCI Machine Learning Repository.

• Journal of information and communication convergence engineering
• /
• v.9 no.5
• /
• pp.591-596
• /
• 2011

Image denoising is a key issue in all image processing researches. Generally, the quality of an image could be corrupted by a lot of noise due to the undesired conditions of image acquisition phase or during the transmission. Many approaches to image restoration are aimed at removing either Gaussian or impulse noise. Nevertheless, it is possible to find them operating on the same image, which is called mixed noise and it produces a hard damage. In this paper, we proposed noise type classification method and a mixed nonlinear filter for mixed noise suppression. The proposed filtering scheme applies a modified adaptive switching median filter to impulse noise suppression and an efficient nonlinear filer was carried out to remove Gaussian noise. The simulation results based on Matlab show that the proposed method can remove mixed Gaussian and impulse noise efficiently and it can preserve the integrity of edge and keep the detailed information.

• Nonlinear Functional Analysis and Applications
• /
• v.29 no.2
• /
• pp.333-360
• /
• 2024

This paper is concerned with the radial solutions of a nonlinear elliptic equation ∆_pu + |x|^𝑙₁ |u|^q₁-1 u + |x|^𝑙₂ |u|^q₂-1 u = 0, x ∈ ℝ^N, where p > 2, N ≥ 1, q₂ > q₁ ≥ 1, -p < 𝑙₂ < 𝑙₁ ≤ 0 and -N < 𝑙₂ < 𝑙₁ ≤ 0. We prove the existence of global solutions, we give their classification and we present the explicit behavior of positive solutions near the origin and infinity.

• Journal of applied mathematics & informatics
• /
• v.8 no.1
• /
• pp.45-57
• /
• 2001

A parametric scheme is proposed for the numerical solution of the nonlinear Boussinesq equation. The numerical method is developed by approximating the time and the space partical derivatives by finite-difference re placements and the nonlinear term by an appropriate linearized scheme. The resulting finite-difference method is analyzed for local truncation error and stability. The results of a number of numerical experiments are given for both the single and the double-soliton wave. AMS Mathematics Subject Classification : 65J15, 47H17, 49D15.

• Journal of applied mathematics & informatics
• /
• v.7 no.1
• /
• pp.29-40
• /
• 2000

We provide semilocal convergence theorems for Newton-like methods in Banach space using outer and generalized inverses. In contrast to earlier results we use hypotheses on the second instead of the first Frechet-derivative. This way our Newton-Kantorovich hypotheses differ from earlier ones. Our results can be used to solve undetermined systems, nonlinear least square problems and ill-posed nonlinear operator equations.