• 한국경영과학회지
• /
• 제32권4호
• /
• pp.1-18
• /
• 2007

In this paper, we develop an adaptive genetic algorithm (aGA). The aGA has an adaptive scheme which can automatically determine the use of local search technique and adaptively regulate the rates of crossover and mutation operations during its search process. For the adaptive scheme, the ratio of degree of dispersion resulting from the various fitness values of the populations at continuous two generations is considered. For the local search technique, an improved iterative hill climbing method is used and incorporated into genetic algorithm (GA) loop. In order to demonstrate the efficiency of the aGA, i) a canonical GA without any adaptive scheme and ii) several conventional aGAs with various adaptive schemes are also presented. These algorithms, including the aGA, are tested and analyzed each other using various test problems. Numerical results by various measures of performance show that the proposed aGA outperforms the conventional algorithms.

• 대한기계학회논문집A
• /
• 제27권1호
• /
• pp.158-166
• /
• 2003

The paper describes the development and application of advanced evolutionary computing techniques referred to as micro genetic algorithms ($\mu$GA) in the context of engineering design optimization. The basic concept behind $\mu$GA draws from the use of small size of population irrespective of the bit string length in the representation of design variable. Such strategies also demonstrate the faster convergence capability and more savings in computational resource requirements than simple genetic algorithms (SGA). The paper first explores ten-bar truss design problems to see the optimization performance between $\mu$GA and SGA. Subsequently, $\mu$GA is applied to a realistic engineering design problem in the injection molding process optimization.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 춘계정기학술대회 e-Business를 위한 지능형 정보기술 / 한국지능정보시스템학회
• /
• pp.347-356
• /
• 2000

This paper compares four models of artificial neural networks (ANN) supported by genetic algorithms the prediction of stock price index. Previous research proposed many hybrid models of ANN and genetic algorithms(GA) in order to train the network, to select the feature subsets, and to optimize the network topologies. Most these studies, however, only used GA to improve a part of architectural factors of ANN. In this paper, GA simultaneously optimized multiple factors of ANN. Experimental results show that GA approach to simultaneous optimization for ANN (SOGANN3) outperforms the other approaches.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 하계종합학술대회 논문집(3)
• /
• pp.27-30
• /
• 2000

Many human inventions were inspired by nature. The artificial neural network is one example. Another example is Genetic Algorithms(GA). GAs search by simulating evolution, starting from an initial set of solutions or hypotheses, and generating successive "generations" of solutions. This particular branch of AI was inspired by the way living things evolved into more successful organisms in nature. To simulate the process of GA in a computer, we must simulate many times according to varying many GA parameters. This paper describes the implementation of Java Package for efficient applications on Genetic Algorithms, called "JavaGA". The JavaGA used as a application program as well as applet provides graphical user interface of assigning major GA parameters.

• 한국정보과학회논문지:시스템및이론
• /
• 제33권8호
• /
• pp.486-494
• /
• 2006

본 논문에서는 병렬처리에서 중요한 이슈인 부하균형 문제에 대한 새로운 솔루션을 소개한다. 솔루션으로 제안하는 MGA 기법은 평균장 어닐링 (MFA)과 유전자 알고리즘 (GA)의 장점을 효과적으로 결합한 휴리스틱 부하균형기법이다. 제안된 MGA을 다른 매핑 알고리즘 (MFA, GA-l, GA-2) 들과의 성능 향상비를 측정하는 멀티프로세서 매핑 시뮬레이션을 개발하였다. 휴리스틱 매핑 기법의 합성을 통하여 기존의 방법보다 수행시간은 오래 걸리는 대신 솔루션 품질, 즉 최대종료시간 및 통신부하에서 개선된 실험 결과를 얻을 수 있다는 것을 보였다.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2000년도 봄 학술발표회 논문집
• /
• pp.125-132
• /
• 2000

This study presents the application of genetic algorithms(GA) to the back analysis of tunnels. GA based on the theory of natural evolution, and have been evaluated very effective for their robust performances, particularly for optimizing structure problems. In the back analysis method, the selection of initial value and uncertainty of field measurements influence significantly on the analysis result. GA can improve this problems through a probabilistic approach. Besides, this technique have two other advantages over the back analysis. One is that it is not significantly affected by the form of problems. Another one is that it can consider two known parameter simultaneously. The propriety of this study is verified as the comparison in the same condition of the back analysis(Gens et al, 1987). In this study, it was performed to estimated the geotechnical parameters in the case of weak rock mass at the Kyung Bu Express railway tunnel. GA have been shown for effective application to a geotechnical engineering.

• 전산구조공학
• /
• 제8권2호
• /
• pp.123-132
• /
• 1995

Genetic Algorithms(GA)는 생명체의 자연진화 법칙에 기초한 최적화 방법으로 그 범용성이 높이 평가되어지고 있다. 기존의 GA는 대부분 설계변수로 2진수형 코드를 사용하는데, 이는 실수형 설계변수로 구성된 최적화 문제를 해결하기 위해 컴퓨터 주 기억용량을 많이 사용하여야 하며, 계산 시간 면에서도 비효율적이고 또한 국부탐색 능력도 떨어지는 단점이 있다. 따라서 본 연구에서는 GA에 의한 최적화과정에서 실수형 설계변수를 직접 사용할 수 있도록 교배와 돌연변이 과정을 새로이 정식화하였다. 그리고 여러 형태의 단일 및 다목적함수 최적화 문제에 대해 실수형 GA와 2진수형 GA의 결과를 비교 검토하였다. 비교 검토 결과, 실수형 GA의 성능이 2진수형 GA보다 우수함을 알 수 있었고, 일반 최적화 방법으로 실수형 GA를 사용하여도 무방하리라 본다.

• 제어로봇시스템학회논문지
• /
• 제17권12호
• /
• pp.1210-1218
• /
• 2011

GA (Genetic Algorithms) are efficient for searching for global optima but may have some problems such as premature convergence, convergence to local extremum and divergence. These phenomena are related to the evolutionary operators. As population diversity converges to low value, the search ability of a GA decreases and premature convergence or converging to local extremum may occur but population diversity converges to high value, then genetic algorithm may diverge. To guarantee that genetic algorithms converge to the global optima, the genetic operators should be chosen properly. In this paper, we analyze the effects of the selection operator, crossover operator, and mutation operator on convergence properties, and propose the sweeping method of mutation probability and elitist propagation rate to maintain the diversity of the GA's population for getting out of the premature convergence. Results of simulation studies verify the feasibility of using these sweeping operators to avoid premature convergence and convergence to local extrema.

• 한국전산구조공학회논문집
• /
• 제13권3호
• /
• pp.337-349
• /
• 2000

유전자 알고리즘(GA)은 어떠한 유형의 문제에도 적용가능하며 달리 방법이 없는 경우 최후의 수단으로 흔히 사용되는 방법이다. 강구조물 설계란 기본적으로 구조물을 이루는 부재로서 어떤 재료를 선택될 것인지를 결정하는 문제이다. 따라서 천문학적인 숫자의 설계가 존재하며 이들 중 최적의 설계를 탐색하는 것은 대체로 불가능한 일이다. 본 논문에서는 GA와 이와 관련된 여러 가지 기법들을 소개하고 강구조물 최적설계에 이들의 활용을 모색하였다. 작은 설계공간을 가지는 문제에서는 GA로 전역최적설계를 찾을 수 있었다. GA는 또한 연속변수 최적설계 문제에서도 최적설계를 찾았으며 구조물 최적설계에 적용될 수 있음을 보였다. 그러나 규모가 큰 현실문제에서는 GA가 최적 또는 최적에 근접한 설계를 항상 찾을 수 있을 것이라고 기대하기는 어려울 것으로 생각된다. GA에 G bit improvement를 추가하여 수행한 경우에 더 좋은 최적설계 결과를 보여주었으며 앞으로 이 부분의 연구가 활발해 질 것이다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.183-186
• /
• 2003

Hybrid genetic algorithms (HGAs) have been studied as various ways. These HGAs usually use both the global search property of genetic algorithm (GA) and the local search one of local search techniques. One of the general types, when constructing HGAs, is to incorporate a local search technique into GA loop, and then the local search technique is repeated as many iteration number as the loop. This paper proposes a new HGA with a conditional local search technique (c-HGA) that does not be repeated as many iteration number as GA loop. For effectiveness of the proposed c-HGA, a conventional HGA and GA are also suggested, and then these algorithms are compared with each other in numerical examples,