• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.5
• /
• pp.15-24
• /
• 2008

For high-dimensional classification tasks, such as face recognition, the number of samples is smaller than the dimensionality of the samples. In such cases, a problem encountered in linear discriminant analysis-based methods for dimension reduction is what is known as the small sample size (SSS) problem. Recently, to solve the SSS problem, a way of employing a dissimilarity-based classification(DBC) has been investigated. In DBC, an object is represented based on the dissimilarity measures among representatives extracted from training samples instead of the feature vector itself. In this paper, we propose a new method of optimizing DBCs using multi-level fusion strategies(MFS), in which fusion strategies are employed to represent features as well as to design classifiers. Our experimental results for benchmark face databases demonstrate that the proposed scheme achieves further improved classification accuracies.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.108-113
• /
• 2002

This paper presents a multi-step structural design optimization method fur machine tool structures using a genetic algorithm with dynamic penalty. The first step is a sectional topology optimization, which is to determine the best sectional construction that minimize the structural weight and the compliance responses subjected to some constraints. The second step is a static design optimization, in which the weight and the static compliance response are minimized under some dimensional and safety constraints. The third step is a dynamic design optimization, where the weight static compliance, and dynamic compliance of the structure are minimized under the same constraints. The proposed design method was examined on the 10-bar truss problem of topology and sizing optimization. And the results showed that our solution is better than or just about the same as the best one of the previous researches. Furthermore, we applied this method to the topology and sizing optimization of a crossbeam slider for a high-speed machining center. The topology optimization result gives the best desirable cross-section shape whose weight was reduced by 38.8% than the original configuration. The subsequent static and dynamic design optimization reduced the weight, static and dynamic compliances by 5.7 %, 2.1% and 19.1% respectively from the topology-optimized model. The examples demonstrated the feasibility of the suggested design optimization method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.215-215
• /
• 2012

사회는 우리의 예상보다 빠르게 혹은 느리게 발전할 수 있고, 정부의 법령이나 규정은 때때로 수정되며, 대중의 선호도나 정서 등도 시시각각 변화한다. 이러한 불확실하고 변화가 많은 환경하에서 수자원기술자들은 시스템의 구축에 있어서 종종 딜레마에 직면하게 된다. 즉, 언제(when), 얼마만한(how big) 규모의 시스템을 구축해야 불투명한 미래에 충분히 대비할 수 있을까란 의문이 바로 그것이다. 시스템의 계획단계(planning stage)에서 시스템과 관련된 여러 가지 불확실성을 고려할 수 있는 가장 강력하면서 또한 직감적인 방법은 바로 여러 가지 미래에 대한 가상 시나리오(scenario)를 구성하여 그것에 대비하는 방법이다. 최근 들어 시나리오에 기반한 시스템 플래닝 기법이 수자원분야에서 주목을 받고 있다. 미래에 발생 가능한 여러 가지 시나리오를 고려하여 구축된 시스템은 그 자체로 유연성을 발휘하여 미래에 발생할 수 있는 (예측에 어긋난) 다양한 변화에도 큰 사회적인 혼란 없이 최소의 추가비용만으로도 본래의 역할을 수행해 나갈 수 있다. 본 연구에서는 최적화 기법을 시나리오 플래닝 기법 (scenario planning technique)과 접목하여 분산형 용수공급 시스템(decentralized water supply system)의 최적설계에 적용하였다. 대상지역은 미국의 대표적인 준사막지역의 하나인 애리조나주에 위치한 투산시의 통합 물공급시스템으로 향후 20년을 대비한 시스템의 최적화에 본 연구에서 제안된 기법을 적용하여, 그 결과를 정리하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.9
• /
• pp.700-704
• /
• 2009

In this paper, we propose a method for combining MR image with histopathology image of the prostate using image correction and multi-stage registration. Our method consists of four steps. First, the intensity of prostate bleeding area on T2-weighted MR image is substituted for that on T1-weighted MR image. And two or four tissue sections of the prostate in histopathology image are combined to produce a single prostate image by manual stitching. Second, rigid registration is performed to find the affine transformations that to optimize mutual information between MR and histopathology images. Third, the result of affine registration is deformed by the TPS warping. Finally, aligned images are visualized by the intensity intermixing. Experimental results show that the prostate tumor lesion can be properly located and clearly visualized within MR images for tissue characterization comparison and that the registration error between T2-weighted MR and histopathology image was 0.0815mm.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.3
• /
• pp.685-697
• /
• 1997

A Viedo-on-Demand(VOD) service is a multimedia service that is realized by the rapid advance of computer and data communication techmologies. Basically, a VOD system is composed of a server and a number fo clients.The server stores and manages a large amount of digital moving picture data. Each slient sends an on-line requwet to the server and receives data for real-time displying. Many researches are performed on a VOD server using hard disks for the permanent video fata storage. However, a hard disk is less reliable and requires more storage cost than a massive storage device. Due to these resasons, a multi-level VOD system is proposed for using teh jukeboxes of optical disks as the permanent video storage,device. In this paper, we prpose the necessary software modules and protocols between the server and its clients for the implementation of the multi-level VOD server.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.9 no.3 s.43
• /
• pp.23-32
• /
• 2005

Torsional behavior of eccentric structure under seismic leading may cause the stress and/or deformation concentration, which arouse the failure of the structure in an unexpected manner. This study suggests D-R relationship which shows the overall displacement and rotation of the system based on the ultimate displacement capacity of the each lateral load resistant member. Using the suggested D-R relationship and displacement spectrum, the seismic assessment is conducted and verified in comparison with the time history analysis result. Multi-level seismic assessment Is considered which takes multiple seismic hazard levels and respective performance levels into account. Finally, based on the seismic assessment result, seismic rehabilitation process is presented. In this research, two rehabilitation methods are considered. One is done by means of stiffening/strengthening the seismic resistant members, and the other is based on the member ductility. Especially, in the first method, to optimize the rehabilitation result, the rehabilitation problem is modeled as an optimization problem, and solved using BFGS quasi-Newton optimization method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.9 no.1
• /
• pp.33-40
• /
• 1989

In the design of reinforced concrete framed structures, which consist of various design variables, the objective and the constraint functions are formulated in complicated forms. Usually iterative methods have been used to optimize the design variables. In this paper, multilevel formulation is adopted, and design variables are selected in reduced numbers at each level, to reduce the iterative cycle and to accelerate the convergence rate. At level 1, elastic analysis is performed to get the upper and lower bounds of the redistributed design moments due to inelastic behavior of the frame. Then the design moments are taken as design variables and optimized at level 2, and the sizing variables are optimized at level 3. The optimization of redistributed moments is performed using the design sensitivity obtained at the level 2, and force approximation technique is used to reflect the variation of design variables in the lower level to the upper level. The design variables are selected in reduced numbers at each level, and the optimization formulation is simplified effectively. A cost function is taken as the objective function, and the constraints of the stress of the structures are derived from BSI CP 110 following limit state theory. Numerical examples are included to prove the effectiveness of the developed algorithm.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.636-636
• /
• 2012

우리나라에서 가장 심각한 자연재해가 홍수재해이므로, 홍수기에 홍수예보를 하는 것은 매우 중요한 일이다. 홍수예보를 위한 예측 과정은 강우예측과 유출해석부분으로 크게 나눌 수가 있는데, 강우를 정확하게 예측하는 일은 주로 정교한 강우모형과 기상학자들의 몫으로 남겨놓는다고 하더라도 정확한 유출해석은 오랜 동안 수문학자들에게 중요한 고민거리였으며, 특히 우리나라와 같이 홍수재해에 취약한 지역에서는 더욱 간절한 문제가 되었다. 우리나라에서는 국가하천을 대상으로 홍수예보모형을 개발하여 하천의 주요지점에 대한 홍수예보를 시행하고 있으며, 매년 보다 정확하고 신속한 예보를 통해 피해를 줄이기 위해 많은 노력을 기울이고 있다. 본 연구에서는 전역최적화기법인 SCE-UA방법을 이용하여 홍수예보모형의 매개변수의 최적화를 수행하였다. 그러나 최적화기법에 의해 제안된 매개변수들이 강우-유출모형이나 유역의 물리적인 특성을 반영하지 못한다는 비판을 피하기 위해 다단계의 최적화를 통해 유역의 물리적인 특성을 반영하면서도 유출수문곡선을 성공적으로 재현하는 매개변수를 제안하고, 각 매개변수가 가지는 의미를 평가하여 실무에서 홍수예보업무의 효율을 높이는데 도움을 주는 것을 목적으로 하였다. 연구를 위해 매개변수의 민감도 분석을 수행하고, 민감도에 따라 최적화 하는 방법을 다르게 적용하였다. 또한 유역의 물리적인 특성을 나타내는 매개변수와 강우의 특성에 따라 변화하는 매개변수를 구분하여, 유역별 다른 매개변수의 범위를 제안하였다. 제안된 매개변수는 검증을 통하여 적용성을 확인하였으며, 유역별 다양한 특성을 성공적으로 나타내었다.

• IE interfaces
• /
• v.21 no.4
• /
• pp.444-455
• /
• 2008

In the present manufacturing environment, the appropriate decision making strategy has a significance and it should count on the fast-changing demand of customers. This research derives the optimal levels of the decision variables affecting the inventory related performance in multi-stage supply chain by using simulation and genetic algorithm. Simulation model helps analyze the customer service level of the supply chain computationally and the genetic algorithm searches the optimal solutions by interaction with the simulation model. Our experiments show that the integration approach of the genetic algorithm with a simulation model is effective in finding the solutions that achieve predefined target service levels.

• Journal of Korean Society for Quality Management
• /
• v.9 no.2
• /
• pp.31-36
• /
• 1981

This paper deals with the reliability optimization of parallel - in - series system subject to several linear constraints. The model of nonlinear constrained optimization is transformed to a saddle point problem by using Lagrange multipliers. Then Newton - Raphson method is used to solve the resulting problem and these step - by - step solution procedures are programmed in Basic Level II of micro - computer TRS-80. An example which has two linear constraints is solved and the results are analyzed.