• 자원환경지질
• /
• 제28권6호
• /
• pp.553-558
• /
• 1995

본 논문에서는 깊이에 따라 밀도값과 (종파)속도값이 변하는 지하 하부층들의 반사계수로부터 밀도와 속도 주상도를 구하는 알고리즘을 개발하고자 하였다 하향연속(下向連續) 혹은 박층(剝層 layer stripping) 방식 알고리즘은 적분방정식을 이용한 계산법보다 계산 과정을 상당히 줄일 수 있다. 본 논문에서는 여러 방향으로의 입사파에 의한 반사계수를 개선된 하향연속 알고리즘을 이용하여 처리하였으며, 각 깊이에서 최소자승 맞춤(fitting)을 실행하였다. 본 연구결과는 다른 하향연속 알고리즘에 비하여 상당한 성과를 보여주고 있다.

• Communications for Statistical Applications and Methods
• /
• 제24권4호
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.

• 한국전자파학회논문지
• /
• 제27권4호
• /
• pp.388-394
• /
• 2016

안테나 배열을 통한 방향 탐지는 여러 분야에서 활발하게 이루어지고 있는 연구 분야이다. Beamforming, Capon's method, maximum likelihood(ML), MUSIC 등과 같은 방향 탐지 알고리즘이 대표적이다. 최근 방향 탐지 이론은 압축센싱기법을 이용하여 신호의 희소도를 이용한 방법의 연구가 수행되고 있다. 본 논문에서는 그 중 하나인 신호의 데이터 행렬을 fitting하는 L1-SVD 알고리즘의 성능을 알아보기 위해 MUSIC 알고리즘과 비교하여 장단점을 알아본다.

• Journal of Welding and Joining
• /
• 제14권5호
• /
• pp.78-86
• /
• 1996

Vision sensor was used to track the weld line of the compressor case. The compressor case was fixed in jig equipped with the rotating system, and two torches having one degree of freedom was applied in automatic welding system. The radius of rotation for the compressor case is varying with each rotating angle, while, the angle velocity is constant Therefore, an algorithm to extract the feature of the compressor case for varying rotation angle is needed. To over come the avove difficulties, the curve fitting and composite curve were used. The experiment to verify the proposed algorithm showed desirable results for tracking the welding line of compressor case.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회A
• /
• pp.1564-1569
• /
• 2007

This study concerns an advanced NURBS surface reconstruction method, which is based on the NURBS surface model fitting to the unstructured point cloud measured from an arbitrary complex shape. The concept of generating a simple triangular mesh model was introduced to generate a quadrilateral mesh model well-representing the topological characteristics of point cloud. The NURBS surface reconstruction processes required the use of the various methodologies such as QEM algorithm, merging scheme of pair-wise triangular mesh, creation algorithm of $G^1$ continuous tensor product NURBS surface patch, and so on. The effectiveness and reliability of the proposed NURBS surface reconstruction method were validated through the simulation results for the geometrically and topologically complex shapes.

• Steel and Composite Structures
• /
• 제7권5호
• /
• pp.355-376
• /
• 2007

The purpose of this study is to predict and investigate the time-dependent creep behavior of composite materials. For this, firstly the evaluation method for the modulus of elasticity of whole fiber and matrix is presented from the limited information on fiber volume fraction using the singular value decomposition method. Then, the effects of fiber volume fraction on modulus of elasticity of GFRP are verified. Also, as a creep model, the nonlinear curve fitting method based on the Marquardt algorithm is proposed. Using the existing Findley's power creep model and the proposed creep model, the effect of fiber volume fraction on the nonlinear creep behavior of composite materials is verified. Then, for the time-dependent analysis of a composite material subjected to uniaxial tension and simple shear loadings, a user-provided subroutine UMAT is developed to run within ABAQUS. Finally, the creep behavior of center loaded beam structure is investigated using the Hermitian beam elements with shear deformation effect and with time-dependent elastic and shear moduli.

• 공학논문집
• /
• 제1권1호
• /
• pp.31-40
• /
• 1997

ATM망의 모델링에서 발생되어지는 D-BMAP/Geo/1/K queue의 departure 프로세스를 k-state MMBP로 특성화하는 근사화방법을 제시하고, 그 근사화방법과 decomposition algorithm을 이용하여 셀손실을 갖는 tandem 구조의 한정용량 대기 네트워크를 분석하였다.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.680-681
• /
• 2015

This study develops an algorithm that automatically performs reverse engineering on three-dimensional (3D) sweeping shapes using a user's pre-defined feature templates and 3D point cloud data (PCD) of sweeping shapes. Existing methods extract 3D sweeping shapes by extracting points on a PCD cross section together with the center point in order to perform curve fitting and connect the center points. However, a drawback of existing methods is the difficulty of creating a 3D sweeping shape in which the user's preferred feature center points and parameters are applied. This study extracts shape features from cross-sectional points extracted automatically from the PCD and compared with pre-defined feature templates for similarities, thereby acquiring the most similar template cross-section. Fitting the most similar template cross-section to sweeping shape modeling makes the reverse engineering process automatic.

• 한국전자통신학회논문지
• /
• 제8권8호
• /
• pp.1187-1193
• /
• 2013

본 논문은 사실적인 3D 얼굴 모델링과 얼굴 표정 생성 시스템을 제안한다. 사실적인 3D 얼굴 모델링 기법에서 개별적인 3D 얼굴 모양과 텍스쳐 맵을 만들기 위해 Generic Model Fitting 기법을 적용하였다. Generic Model Fitting에서 Deformation Function을 계산하기 위해 개별적인 얼굴과 Generic Model 사이의 대응점을 결정하였다. 그 후, Calibrated Stereo Camera로부터 캡쳐 된 영상들로부터 특징점을 3D로 복원하였다. 텍스쳐 매핑을 위해 Fitted된 Generic Model을 영상으로 Projection하였고 사전에 정의된 Triangle Mesh에서 텍스쳐를 Generic Model에 매핑 하였다. 잘못된 텍스쳐 매핑을 방지하기 위해, Modified Interpolation Function을 사용한 간단한 방법을 제안하였다. 3D 얼굴 표정을 생성하기 위해 Vector Muscle기반 알고리즘을 사용하고, 보다 사실적인 표정 생성을 위해 Deformation 과 vector muscle 기반의 턱 rotation을 적용하였다.

• 제어로봇시스템학회논문지
• /
• 제14권5호
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.