• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.99-103
• /
• 2007

본 논문은 최적 탐색 알고리즘중의 하나인 실수 표현 진화 알고리즘에 자가 적용 세대차 조절을 이용하여 보다 빠른 연산으로 우수해에 접근하기 위한 새로운 방식을 소개한다. 알고리즘의 성능에 영향을 끼치는 진화 속도를 기존 진화 방식과 유전연산자의 수정을 통해 조절하여 탐색 성능을 개선 한다. 조기 수렴의 방지 및 탐색성능의 향상을 위하여 선택과 대치를 포함한 진화방식을 개선하고, 유전 연산자에 의하여 생성된 자손의 대치확률에 따라서 자손의 생성범위를 자가 적응적으로 조절하여, 보다 적은 계산량으로 전역 최적화를 찾고자 한다. 제안된 방법을 벤치마크 테스트 문제에 적용하여 G3 알고리즘, CMA-ES 그리고 DE 등과 성능을 비교하였다.

• Progress in Superconductivity and Cryogenics
• /
• v.18 no.3
• /
• pp.10-20
• /
• 2016

The Cable-In-Conduit-Conductor (CICC) for the ITER tokamak Central Solenoid (CS) has undergone design change since the first prototype conductor sample was tested in 2010. After tests showed that the performance of initial conductor samples degraded rapidly without stabilization, an alternate design with shorter sub-cable twist pitches was tested and discovered to satisfy performance requirements, namely that the minimum current sharing temperature ($T_{cs}$) remained above a given limit under DC bias. With consistent successful performance of ITER CS conductor CICC samples using the alternate design, an attempt is made here to revisit the internal electromagnetic properties of the CICC cable design to identify any correlation with conductor performance. Results of this study suggest that there may be a simple link between the $Nb_3Sn$ CICC internal self-field and its $T_{cs}$ performance. The study also suggests that an optimization process should exist that can further improve the performance of $Nb_3Sn$ based CICC.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.12
• /
• pp.3236-3245
• /
• 1994

The nesting of two-dimensional patterns onto a given raw sheet has applications in a number industries. It is a common problem often faced by designers in the shipbuilding, garment making, blanking die design, glass and wood industries. This paper presents a multi-stage layout approach for nesting two-dimensional patterns by using artificial intelligence techniques with a relatively short computation time. The raw material with irregular boundaries and internal defects which must be considered in various cases of nesting was also investigated in this study. The proposed nesting approach consists of two stages : initial layout stage and layout improvement stage. The initial layout configuration is achieved by the self-organizing assisted layout(SOAL) algorithm while in the layout improvement stage, the simulated annealing(SA) is adopted for a finer optimization.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.2
• /
• pp.71-79
• /
• 1998

In this paper, we propose a new mART(modified ART) neural network by combining the winner neuron definition method of SOM(self-organizing map) and the real-time adaptive clustering function of ART(adaptive resonance theory) and construct it in a modular structure, for the purpose of organizing the feature maps of three dimensional targets. Being constructed in a modular structure, the proposed modular mART can effectively prevent the clusters from representing multiple classes and can be trained to organze two dimensional distortion invariant feature maps so as to recognize targets with three dimensional distortion. We also present the recognition result and self-organization perfdormance of the proposed modular mART neural network after carried out some experiments with 14 tank and fighter target models.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.288-291
• /
• 2004

기존의 SOFPNN은 데이터 수가 적고 비선형 요소가 많은 시스템에 대한 체계적이고 효율적인 최적 모델 을 구축할 수 있었으며 각 층 노드의 선택 입력을 변화시킴으로써 네트워크 구조 전체의 적응능력을 향상 시켰다. SOFPNN의 구조는 퍼지 다항식 뉴론(FPN)들로 구성되어 있으며, 층이 진행하는 동안 모델 스스로 노드의 선택과 제거를 통해 최적의 네트워크 구조를 생성할 수 있는 유연성을 가지고 있다. 그러나, 노드의 입력변수의 수와 규칙 후반부 다항식 차수 그리고 입력변수는 설계자의 경험 또는 반복적인 학습을 통해 선호된 네트워크 구조를 선택하였으나, 최적의 네트워크 구조를 구축하는데는 어려옴이 내재되어 있었다. 본 논문에서는 자기구성 퍼지 다항식 뉴럴네트워크(Self-Organizing Fuzzy Polynomial Neural Networks： SOFPNN)을 최적화시키기 위해 유전자 알고리즘을 이용하여 자기구성 퍼지 다항식 뉴럴 네트워크의 입력변수의 수와 이에 해당되는 입력변수 그리고 규칙 후반부 다항식의 차수를 탐색하여 최적 의 자기구성 퍼지 다항식 뉴럴 네트워크를 구축한다. 따라서 모델 구축에 있어서 유연성과 정확성을 가지며 객관적이고 좀 더 정확한 예측 능력을 가진 SOFPNN 모델 구조를 구축할 수가 있다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.297-300
• /
• 2005

In this study, we proposed genetically optimized self-organizing fuzzy polynomial neural network based on information granulation and evolutionary algorithm (gdSOFPNN), develop a comprehensive design methodology involving mechanisms of genetic optimization. The proposed gdSOFPNN gives rise to a structural Iy and parametrically optimized network through an optimal parameters design available within FPN (viz. the number of input variables, the order of the polynomial, input variables, the number of membership functions, and the apexes of membership function). Here, with the aid of the information granulation, we determine the initial location (apexes) of membership functions and initial values of polynomial function being used in the premised and consequence part of the fuzzy rules respectively. The performance of the proposed gdSOFPNN is quantified through experimentation that exploits standard data already used in fuzzy modeling.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.8 no.2
• /
• pp.132-139
• /
• 2008

This paper proposes a scatternet topology formation, self-healing, and self-routing path optimization algorithm based on Relative Neighborhood Graph. The performance of the algorithm using ns-2 and extensible Bluetooth simulator called blueware shows that even though RNG-FHR does not have superior performance, it is simpler and easier to implement in deploying the Ad-Hoc network in the distributed dynamic environments due to the exchange of fewer messages and the only dependency on local information. We realize that our proposed algorithm is more practicable in a reasonable size network than in a large scale.

• Proceedings of the Korea Committee for Ocean Resources and Engineering Conference
• /
• 2003.05a
• /
• pp.69-71
• /
• 2003

This paper introduces TRIZ. TRIZ is the theory of inventive problem solving which haws started by G.Altschuler since 1946, Russia. TRIZ is applicable for not only mechanical engineering, but also science, economic and pedagogy fields. Characteristics of some kind of softwares for TRIZ method are briefly reviewed Especially Catia with IMC TechOptimizer is studied in detail and it is expected to be applicable well for the Ocean Engineering fields, if applicably applied for IM-Principles, IM-Predictions and IM-Effects, even though it will need much efforts and time to study. As an application example of TRIZ, Self-expandable anchor which is pending for patent is presented briefly.

• Research in Community and Public Health Nursing
• /
• v.30 no.3
• /
• pp.271-280
• /
• 2019

Purpose: This study evaluates the efficacy of a Self-Care Reinforcement Program (SCRP) based on the Selection Optimization Compensation (SOC) model, in socially vulnerable elderly women with metabolic syndrome. Methods: This study adopts a pretest-posttest nonequivalent control group design. The participants were 64 socially vulnerable elderly Korean women with metabolic syndrome (experimental group: 31, control group: 33). Participants' body composition analysis, nutrient intake, risk factors of metabolic syndrome, depressive symptoms, and social network were measured. Data were analyzed with an independent t-test; statistical significance levels were set at p<.05. The SCRP, including metabolic syndrome education, nutritional education, exercise, and social network, was performed three times a week for 8 weeks. Results: There were statistically significant differences between the experimental and control groups in terms of systolic blood pressure, diastolic pressure, fasting blood sugar, triglycerides, sodium intake, depressive symptoms, and social networks. Conclusion: The SCRP is effective and can be recommended as a community health nursing intervention for socially vulnerable elderly women with metabolic syndrome.

• Wind and Structures
• /
• v.35 no.2
• /
• pp.121-130
• /
• 2022

In this paper, the issue of pitch control in a vertical axis wind turbine was tackled. Programming the Actuator Cylinder model in MATLAB, a theoretical optimum pitch solution was found and then a classic four-bar mechanism was adapted to that theoretical solution to achieve a simple and elegant control of the pitch in the turbine. A simulation using the mechanism worked to find the optimum pitch cycles, where it was found that the mechanism would, in fact, increase the efficiency of the VAWT, by at least 11% and in the best case, over 35%. Another aspect that is studied is the possibility of self-start of the turbine by only changing the pitch on the blades. This analysis, however, proved that a further individual pitch control must be used to surpass the cogging torque. All analyses conducted were done for a specific wind turbine that is 2 m² in the swept area.