• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 추계 학술발표회 논문집
• /
• pp.137-141
• /
• 2003

LS-SVM(least squares support vector machine) is a widely applicable and useful machine learning technique for classification and regression analysis. LS-SVM can be a good substitute for statistical method but computational difficulties are still remained to operate the inversion of matrix of huge data set. In modern information society, we can easily get huge data sets by on line or batch mode. For these kind of huge data sets, we suggest an on line pruning regression method by LS-SVM. With relatively small number of pruned support vectors, we can have almost same performance as regression with full data set.

• 한국윤활학회:학술대회논문집
• /
• 한국윤활학회 1998년도 제27회 춘계학술대회
• /
• pp.314-320
• /
• 1998

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• 한국마린엔지니어링학회:학술대회논문집
• /
• 한국마린엔지니어링학회 2006년도 전기학술대회논문집
• /
• pp.277-278
• /
• 2006

This paper presents circuit models and control algorithms of distributed generation system(DGS) which consists of Z-type converter and PWM inverter Z-type converter which employs both the L and C passive components and shoot-through zero vectors instead of the conventional DC/DC converter in order to step up DC-link voltage. Discrete time sliding mode control with the asymptotic observer is used for current control.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(2)
• /
• pp.125-128
• /
• 2001

In this paper, we propose a low power Scan-based Built-ln Self Test based on circuit partitioning and pattern suppression using modified test control unit. To partition a CUT(Circuit Under Testing), the MHPA(Multilevel Hypergraph Partition Algorithm) is used. As a result of circuit partition, we can reduce the total length of test pattern, so that power consumptions are decreased in test mode. Also, proposed Scan-based BIST architecture suppresses a redundant test pattern by inserting an additional decoder in BIST control unit. A decoder detects test pattern with high fault coverage, and applies it to partitioned circuits. Experimental result on the ISCAS benchmark circuits shows the efficiency of proposed low power BIST architecture.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2010년도 춘계학술대회 논문집
• /
• pp.1464-1469
• /
• 2010

In this paper, the dynamic stability evaluation of special bridge for high speed railway under ground excitation is performed. The mass, damping, stiffness matrices of bridge are derived from the modal frequencies and mode shape vectors which can be obtained by commercial program. And the high speed train is modeled as multi-single d.o.f models for the sake of vehicle-bridge interaction analysis. In the vehicle-bridge interaction analysis, the vertical directional interaction is only considered. As a numerical example, the 3 span Extradosed bridge which is expected to be installed in Ho-Nam high speed railroad is considered. The analysis results show that the example bridge satisfies the criteria of dynamic stability.

• Tribology and Lubricants
• /
• 제15권2호
• /
• pp.206-211
• /
• 1999

Wear debris morphology is closely related to the wear mode and mechanism occured. Image recognition of wear debris is, therefore, a powerful tool in wear monitoring. But it has usually required expert's experience and the results could be too subjective. Development of automatic tools for wear debris recognition is needed to solve this problem. In this work, an algorithm for automatic wear debris recognition was suggested and implemented by PC base software. The presented method defined a characteristic 3-dimensional feature space where typical types of wear debris were separately located by the knowledge-based system and compared the similarity of object wear debris concerned. The 3-dimensional feature space was obtained from multiple feature vectors by using a multi-dimensional scaling technique. The results showed that the presented automatic wear debris recognition was satisfactory in many cases application.

• 한국소음진동공학회논문집
• /
• 제17권1호
• /
• pp.80-87
• /
• 2007

In this paper, a method for identifying the location and extent of a damage in a structure using residual forces was presented. Element stiffness matrix reduction parameters in a finite element model were used to describe the damaged structure mathematically. The element stiffness matrix reduction parameters were determined by minimizing a global error derived from dynamic residual vectors, which were obtained by introducing a simulated experimental data into the eigenvalue problem. Genetic algorithm was used to get the solution set of element stiffness reduction parameters. The proposed scheme was verified using Euler-Bernoulli beam. The results were presented in the form of tables and charts.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1995년도 가을 학술발표회 논문집
• /
• pp.95-102
• /
• 1995

Procedures for estimation of axial or flexural rigidities of bridge members by neural networks are shown. To treat large scale structures containing many unkwon parameters, substructuring concept is introduced. The measurement points are selected considering the sensitivity of the element stiffnesses of interest. Utilization of relative mode vectors is found to be very effective for the local parameter estimation. Then, the study focuses on the method to obtain the training set enough to represent structures. It is shown that noise injection is effective to reduce the estimation errors caused by measurement noise. Verification of the present method is carried out using a cable-stayed bridge model.

• ETRI Journal
• /
• 제28권5호
• /
• pp.574-582
• /
• 2006

In this paper, a new error concealment algorithm is proposed for the H.264 standard. The algorithm consists of two processes. The first process uses a fuzzy logic method to select the size type of lost blocks. The motion vector of a lost block is calculated from the current frame, if the motion vectors of the neighboring blocks surrounding the lost block are discontinuous. Otherwise, the size type of the lost block can be determined from the preceding frame. The second process is an error concealment algorithm via a proposed adapted multiple-reference-frames selection for finding the lost motion vector. The adapted multiple-reference-frames selection is based on the motion estimation analysis of H.264 coding so that the number of searched frames can be reduced. Therefore the most accurate mode of the lost block can be determined with much less computation time in the selection of the lost motion vector. Experimental results show that the proposed algorithm achieves from 0.5 to 4.52 dB improvement when compared to the method in VM 9.0.

• 한국컴퓨터정보학회논문지
• /
• 제12권5호
• /
• pp.163-170
• /
• 2007

본 논문에서는 압축된 비디오 신호의 움직임 벡터 및 DCT 계수로부터 움직임 객체를 추출하는 새로운 기법을 제시한다. 움직임 객체 추출에 관한 기술은 내용 기반 검색, 타겟트래킹 등 다양한 분야에서 필요로 한다. 움직임 객체 블록의 추출을 위해서 움직임 벡터와 DCT계수 가 선택적으로 이용되는 2-모드 방식의 기법이 제시된다. 또한, 제시된 기법은 DCT 변환 영역상의 계수들만을 이용하기 때문에 완전히 복호화된 정보를 필요로 하지 않는 장점을 갖는다. 제시된 기법을 바탕으로 몇 가지 테스터 영상에 대해 모의 실험을 실시한 결과 양호한 결과를 얻을 수 있었다.