• 전기전자학회논문지
• /
• 제20권3호
• /
• pp.226-234
• /
• 2016

전기 저항 단층촬영법(ERT)은 대상체 내부 단면의 저항률 분포를 추정하고 이를 영상화하는 기술이다. ERT의 영상복원은 매우 비정치성이 강한 역문제의 일종으로 의미있는 영상을 얻기 위해서는 조정기법이 사용된다. 대표적으로 l2-norm 조정기법, l1-norm 조정기법, Total Variation 조정기법이 사용되며, 조정기법에 따라 ERT의 영상복원 성능이 달라진다. 즉, 상황에 맞는 적절한 조정기법의 사용은 ERT 영상 복원을 개선할 수 있다. 따라서, 본 논문에서는 모의실험을 통하여 상황에 따른 세 가지 조정기법의 영상복원 성능을 비교하였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.313-316
• /
• 2004

Model selection is the process that sets up the regularization parameter in the support vector machine or regularization network by using the external methods such as general cross validation or L-curve criterion. This paper suggests that the regularization parameter can be obtained simultaneously within the learning process of neural networks without resort to separate selection methods. In this paper, extended kernel method is introduced. The relationship between regularization parameter and the bias term in the extended kernel is established. Experimental results show the effectiveness of the new model selection method.

• Nuclear Engineering and Technology
• /
• 제37권2호
• /
• pp.177-184
• /
• 2005

The Multivariate State Estimation Technique (MSET) is being used in Nuclear Power Plants for sensor and equipment condition monitoring. This paper presents the use of regularization methods for optimizing MSET's predictive performance. The techniques are applied to a simulated data set and a data set obtained from a nuclear power plant currently implementing empirical, on-line, equipment condition monitoring techniques. The results show that regularization greatly enhances the predictive performance. Additionally, the selection of prototype vectors is investigated and a local modeling method is presented that can be applied when computational speed is desired.

• 전기전자학회논문지
• /
• 제19권1호
• /
• pp.33-40
• /
• 2015

전기 임피던스 단층촬영법(EIT)에서 역문제는 매우 높은 비정치성이므로 이것을 완화시키기 위해서 사전정보가 사용되고 EIT 역문제를 푸는 과정에서 만족스러운 복원성능을 갖기 위해 조정 기법은 적용된다. 반복적 Gauss-Newton 방법은 정확성과 빠른 수렴속도로 인해서 일반적으로 역문제를 푸는데 사용되지만 항상 좋은 성능을 내는 것은 아니며 조정 인자 선택에 따라 성능이 좌지우지된다. 비록 L-곡선과 같이 조정 인자를 결정하는데 이용할 수 있는 여러 가지 방법들이 존재하지만 이러한 방법들이 모든 경우에 적용할 수 있는 것은 아니다. 게다가 조정 인자는 스칼라이고 반복 연산동안 변하지 않는다. 그러므로 이 논문에서는 복원 성능을 향상시키기 위해서 조정 인자를 결정해주는 새로운 방법을 사용하였다. 각각의 반복 연산과정에서 도전율의 norm을 구하고 이것을 대각 행렬형태인 조정 인자를 구하는데 사용한다. 제안한 방법을 인체 흉부 영상 복원에 적용하였고, 기존의 방법들과 복원 성능을 비교하였다. 모의실험 결과, 기존의 방법들과 비교해서 개선된 성능을 확인할 수 있었다.

• 한국지능시스템학회논문지
• /
• 제7권3호
• /
• pp.89-95
• /
• 1997

This paper examines the relation between multidimensional linear interpolation (MDI) and regularization net-works, and shows that an MDI is a special form of regularization networks. For this purpose we propose a triangular basis function(TBF) network. Also we verified the condition when our proposed TBF becomes a well-known radial basis function (RBF).

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2003년도 춘계학술대회논문집
• /
• pp.339-342
• /
• 2003

This paper newly proposes a mesh regularization method for the enhancement of the efficiency in sheet metal forming analysis. The regularization method searches for distorted elements with appropriate searching criteria and constructs patches including the elements to be modified. Each patch is then extended to a three-dimensional surface in order to obtain the information of the continuous coordinates. In constructing the surface enclosing each patch, NURBS(Non-Uniform Rational B-Spline) surface is employed to describe a three-dimensional free surface. On the basis of the constructed surface, each node is properly arranged to form unit elements as close as to a square. The analysis results with the proposed method are compared to the results from the direct forming analysis without mesh regularization in order to confirm the validity of the method.

• Structural Engineering and Mechanics
• /
• 제44권5호
• /
• pp.585-600
• /
• 2012

This paper presents a Modified Tikhonov Regularization (MTR) method in model updating for damage identification with model errors and measurement noise influences consideration. The identification equation based on sensitivity approach from the dynamic responses is ill-conditioned and is usually solved with regularization method. When the structural system contains model errors and measurement noise, the identified results from Tikhonov Regularization (TR) method often diverge after several iterations. In the MTR method, new side conditions with limits on the identification of physical parameters allow for the presence of model errors and ensure the physical meanings of the identified parameters. Chebyshev polynomial is applied to approximate the acceleration response for moderation of measurement noise. The identified physical parameter can converge to a relative correct direction. A three-dimensional unsymmetrical frame structure with different scenarios is studied to illustrate the proposed method. Results revealed show that the proposed method has superior performance than TR Method when there are both model errors and measurement noise in the structure system.

• 대한수학회지
• /
• 제55권4호
• /
• pp.849-875
• /
• 2018

The purpose of this paper is to present an operator method of regularization for the problem of finding a solution of a system of nonlinear ill-posed equations with a monotone hemicontinuous mapping and N inverse-strongly monotone mappings in Banach spaces. A regularization parameter choice is given and convergence rate of the regularized solutions is estimated. We also give the convergence and convergence rate for regularized solutions in connection with the finite-dimensional approximation. An iterative regularization method of zero order in a real Hilbert space and two examples of numerical expressions are also given to illustrate the effectiveness of the proposed methods.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권2호
• /
• pp.95-100
• /
• 2010

This paper proposes a new spatial regularization of Fisher linear discriminant analysis (LDA) to reduce the overfitting due to small size sample (SSS) problem in face recognition. Many regularized LDAs have been proposed to alleviate the overfitting by regularizing an estimate of the within-class scatter matrix. Spatial regularization methods have been suggested that make the discriminant vectors spatially smooth, leading to mitigation of the overfitting. As a generalized version of the spatially regularized LDA, the proposed regularized LDA utilizes the non-uniformity of spatial correlation structures in face images in adding a spatial smoothness constraint into an LDA framework. The region-dependent spatial regularization is advantageous for capturing the non-flat spatial correlation structure within face image as well as obtaining a spatially smooth projection of LDA. Experimental results on public face databases such as ORL and CMU PIE show that the proposed regularized LDA performs well especially when the number of training images per individual is quite small, compared with other regularized LDAs.

• 분석과학
• /
• 제8권4호
• /
• pp.707-714
• /
• 1995

Two types of regularization method (singular system and HMP approaches) for generating depth-concentration profiles from angle-resolved XPS data were evaluated. Both approaches showed qualitatively similar results although they employed different numerical algorithms. The application of the regularization method to simulated data demonstrates its excellent utility for the complex depth profile system. It includes the stable restoration of the depth-concentration profiles from the data with considerable random error and the self choice of smoothing parameter that is imperative for the successful application of the regularization method. The self choice of smoothing parameter is based on generalized cross-validation method which lets the data themselves choose the optimal value of the parameter.