• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.41 no.3
• /
• pp.55-65
• /
• 2004

When a neural network is used to solve a given problem it is necessary to match the complexity of the network to that of the problem because the complexity of the network significantly affects its learning capability and generalization performance. Thus, it is desirable to have an algorithm that can find appropriate network structures in a self-organizing way. This paper proposes algorithms which automatically organize feed forward multi-layer neural networks with sigmoid hidden neurons for given problems. Using both constructive procedures and pruning procedures, the proposed algorithms try to find the near optimal network, which is compact and shows good generalization performance. The performances of the proposed algorithms are tested on four function regression problems. The results demonstrate that our algorithms successfully generate near-optimal networks in comparison with the previous method and the neural networks of fixed topology.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.165-187
• /
• 2004

Constraint Programming in AS and Optimization in OR started and have grown in different backgrounds to solve common decision-making problems in real world. This paper tries to integrate results from those different fields by suggesting a hybrid solver as an integration framework. Starting with an integrating modeling language, a way to implement a hybrid solver will be discussed using Warren's abstract machine and an finite domain constraint programming solver structures. This paper will also propose some issues rising when implementing the hybrid solver and provide their solutions.

• Journal of the Korean School Mathematics Society
• /
• v.13 no.2
• /
• pp.205-224
• /
• 2010

This paper examined what structural relationship metacognition and flow, which are identified as major variables that positively influence creative problem solving ability, had with mathematics creative problem solving ability. For this purpose, the Mathematics Creative Problem Solving Ability Test (MCPSAT) was given go 196 general second-year middle school students, and their cognitive and affective states were measured with metacognition and flow tests. The three variables' relationships were examined through a correlation analysis and, through structural equation modeling, the mediating effect of flow was tested in the structural relationships between the three variables and in the relationship between metacognition and mathematics creative problem solving ability. The results of the research show that metacognition did not directly influence mathematics creative solving ability, but exerted influence through the mediating variable of flow. A more detailed examination shows that while metacognition did not influence fluency and originality from among the measured variables for mathematics creative problem solving ability, it did directly influence flexibility. In particular, metacognition's indirect influence through the mediating variable of flow was shown to be much stronger than its direct influence on flexibility. This research showed that the students' high metacognition ability increased flow degree in the problem solving process, and problem solving in this state of flow increased their mathematics creative problem solving ability.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.10
• /
• pp.3113-3118
• /
• 2000

A framework proposed in this paper includes representations of multi-objectives rule-basd constraint satisfaction problem(RCSP) and especially, flexible structure of RCSP which provides adequate solution sithin an expectation time and adaptively considers some change of constratraints on the RCSP. In this study, the power system implemented by above framework is entirely programmed by using a modeling system for the quantitative model and a rule-based constraint programming tool for the qualitative model. The results of an exemplary cse show how the structure that involves the problem representation gives the scheduler an effective decision and what are the advantages of the easy and diverse representation for considering the techmical characteristics of the units on the RCSP over the traditional problem.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2004.11a
• /
• pp.184-187
• /
• 2004

TFT LCD 생산 공정에 사용되는 정밀측정/검사/생산장비가 위치하는 바닥의 진동문제는 크게 장비자체의 가동에 의한 것과 장비외부의 가진원에 의해서 정밀장비의 바닥에 진동이 발생하게 된다. 이러한 진동문제는 건물을 설계 시공하는 건축자의 입장에서는 장비 가동전 건물 인수시 진동문제에 관심이 있으나 장비를 운영하는 사용자의 입장에서는 장비 가동전의 진동문제와 더불어 장비 가동시 장비내부의 진동원에 대해서도 진동대책을 요구하게 된다. 따라서 양자의 진동문제 해결을 위해서는 정밀장비 주변의 진동원에 대한 동하중 설계자료와 함께 장비 가동시 바닥에 진동을 발생시키는 진동원인 장비에 대해서 동하중을 파악하여야 한다. 장비기초의 단위하중에 대한 진동응답을 표현하는 주파수 전달함수는 이러한 동하중과 바닥의 진동허용규제치를 동시에 표현하는 요소로 기존의 정밀장비가 요구하는 장비바닥의 진동허용규제치와 함께 동하중을 유발하는 장비기초에서는 반드시 구조물의 동강성 허용규제치를 이용한 구조물의 동적설계가 요구된다.

• The Mathematical Education
• /
• v.26 no.1
• /
• pp.21-30
• /
• 1987

• Journal of Korean Association for Spatial Structures
• /
• v.4 no.2 s.12
• /
• pp.63-71
• /
• 2004

The structural space is gradually wide and is wanting agreeable environment by the requirement and necessity of people who lives modem stage. The building coincides with such requirements and is the high rise building actual circumstances which is doing ultra-large. The confirmed report of the technology to organize great merit is becoming currently considerably important issue in constructing a building field. Thus, this paper examine closely for nonlinear unstable taking a picture uneasiness height of prosperity considering to initial imperfection by a numerical method with a space frame structure of discrete system in large space structure. Based on previous investigation method, this paper induce nodal stiffness matrix of solid truss elements considering geometrical nonlinear using finite element method. In this paper, three types of space structure considered; i) 1-free node space structure, ii) 2-free node space structure, iii) multi-free node space structure. It apply the above examples to a nonlinear program, next, grasp the characteristic of an unstable conduct and the result was a clearing low.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.5-8
• /
• 2011

3차원 멀티코어 프로세서는 기존의 멀티코어 프로세서에서 문제가 되던 연결망 지연시간과 전력문제를 해결할 수 있는 새로운 프로세서 설계기술이다. 하지만, 전력밀도의 증가로 인해 발생하는 열섬현상은 3차원 멀티코어 프로세서의 새로운 문제점으로 두드러지고 있다. 이러한 문제를 해결하기 위해서 동적 온도 관리 기법이 사용되지만, 동적 온도 관리 기법을 적용하면 시스템에 성능 저하가 발생하게 된다. 따라서 본 논문에서는 3차원 멀티코어 프로세서에서 문제가 되는 열섬현상을 해결하기 위해 고온의 유닛을 대상으로 동적 온도 관리 기법을 적용하고자 한다. 실험대상으로는 시스템 성능에 많은 영향을 미치고 높은 접근 때문에 고온이 발생하는 TLB 유닛을 사용하고자 한다. 특히, 시스템의 성능 저하를 줄이기 위해서 기존의 시스템보다 낮은 성능을 보이는 마이크로 TLB 구조를 적용해 보고자 한다. 성능이 낮은 구조의 경우 일반적으로 더 낮은 온도 분포를 보이며 동적 온도 관리 기법에 영향을 덜 받기 때문에 동적 온도 관리 기법만 적용한 구조보다 더 낮은 성능 저하를 보일 수 있다. 실험결과 동적 온도 관리 기법을 적용한 경우 기존의 시스템에 비해 23.4%의 성능 저하가 발생하고 마이크로 TLB 구조를 적용한 경우 27.1%의 성능 저하가 발생함을 알 수 있다.

• Journal of the Society of Naval Architects of Korea
• /
• v.33 no.2
• /
• pp.44-55
• /
• 1996

Since the use of computer for the ship structural design around mid 1960``s, specially many researches on the midship section optimum design were carried out from 1980. For a rule-based optimum design case, there has been a problem of handling a discrete design variable such as plate thickness for a practical use. To deal with the discrete design variable problems and to develop an effective new method using artificial neural network for the ship structural design applications, Neuro-Optimizer combing Hopfield Neural Network and other Simulated Annealing is proposed as a new optimization method and then applied to the fundamental skeletal structures and Midship section of Tanker. From the numerical results, it is confirmed that Neuro-Optimizer could be used effectively as a new optimization method for the structural design.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1996.05d
• /
• pp.333-338
• /
• 1996

강진에 의한 원전구조물의 동적해석시 지반의 비선형특성은 반드시 고려해야 할 사항이다. 지반의 비선형특성은 지반-구조계의 동적응답을 구하는 과정에서 가장 중요한 요소중의 하나며 이를 고려한 비선형 지진해석은 일반적으로 매우 복잡하고 정해를 구하기가 매우 어려운 문제다. 본 연구에서는 비선형 해법으로 널리 사용되고 있는 등가선형화방법을 사용하여 계측결과가 있는 TEPSCO 비선형 지진문제를 해석하였으며 이 방법의 정확도와 적용성을 분석하였다. 아울러 축대칭기법을 사용하여 비선형지진해석을 수행할때의 문제점에 관해서도 검토하였다.