• 한국컴퓨터정보학회논문지
• /
• 제25권12호
• /
• pp.55-61
• /
• 2020

유전자 알고리즘은 명료한 방식으로 답을 찾기 어려운 문제, 즉 NP 문제의 경우 효과적인 솔루션을 찾을 수 있다. 단 유전자 알고리즘의 실행 비용은 기존 프로그래밍 방식에 비하여 높은 비용을 요구하게 되므로, 높은 성능의 실행환경을 전제로 한다. 이러한 문제를 조금이나마 줄여보기 위하여 본 연구는 유전자 알고리즘의 돌연변이 연산자를 초점을 맞추고, 돌연변이 연산의 복잡한 실행을 위한 비용을 고려하여, 과연 해당 연산자가 모든 문제 영역에서 반드시 요구될까를 분석하기 위한 실험을 진행한다. 우리 실험 주체는 유전자 알고리즘을 적용하는 대표적인 문제 중의 하나인 TSP(Travelling Salesman Problem)으로 하였다. 돌연변이 연산을 적용하는 경우와 적용하지 않는 경우에 대한 결과값들을 세대수와 적합도 값을 수집하여 분석한다. 그 결과 돌연변이 연산자를 적용하는 경우가 세대수 감소와 적합도 향상의 효과적인 결과를 반드시 보이지는 않았다.

• 한국컴퓨터정보학회논문지
• /
• 제10권6호
• /
• pp.85-92
• /
• 2005

본 논문에서는 변형된 돌연변이 연산자를 적용한 대화형 유전자 알고리즘을 사용해서 웹-기반 학습 콘텐츠를 개발하였다. 대화형 유전자 알고리즘은 주로 상호 교환(reciprocal exchange) 돌연변이를 사용한다. 그러나 본 논문에서는 학습자의 학습 효과를 높이기 위해 돌연변이 연산자를 변형하였다. 그리고, 대화형 유전자 알고리즘을 이용한 웹 기반 학습 콘텐츠는 동적인 학습 내용과 실시간 테스트 시스템을 제공한다. 특히 학습자가 자신의 특성과 흥미에 따라 대화형 유전자 알고리즘을 수행하면서 효율적인 학습 환경과 콘텐츠 배열 순서를 선택할 수 있다.

• 한국자동차공학회논문집
• /
• 제12권3호
• /
• pp.51-58
• /
• 2004

Optimization of engine desist and operation parameters using a genetic algorithm was demonstrated for direct injection diesel engine combustion. A micro genetic algorithm and a modified KIVA-3V code were used for the analysis and optimization of the engine combustion. At each generation of the optimization step the micro genetic algorithm generated five groups of parameter sets, and the five cases of KIVA-3V analysis were to be performed either in series or in parallel. The micro genetic algorithm code was also parallelized by using MPI programming, and a multi-CPU parallel supercomputer was used to speed up the optimization process by four times. An example case for a fixed engine speed was performed with six parameters of intake swirl ratio, compression ratio, fuel injection included angle, injector hole number, SOI, and injection duration. A simultaneous optimization technique for the whole range of engine speeds would be suggested for further studies.

• Journal of Electrical Engineering and Technology
• /
• 제3권1호
• /
• pp.125-129
• /
• 2008

A new genetic algorithm for the solution of a multi-tasking problem is presented in this paper. The approach introduces innovative genetic operation that guides the genetic algorithm more directly towards better quality of the population. A wide variety of standard genetic parameters are explored, and results allow the comparison of performance for cases both with and without the new operator. The proposed algorithm improves the convergence speed by reducing the number of generations required to identify a near-optimal solution, significantly reducing the convergence time in each instance.

• 산업경영시스템학회지
• /
• 제36권3호
• /
• pp.17-24
• /
• 2013

Release planning in a software product line (SPL) is to select and assign the features of the multiple software products in the SPL in sequence of releases along a specified planning horizon satisfying the numerous constraints regarding technical precedence, conflicting priorities for features, and available resources. A greedy genetic algorithm is designed to solve the problems of release planning in SPL which is formulated as a precedence-constrained multiple 0-1 knapsack problem. To be guaranteed to obtain feasible solutions after the crossover and mutation operation, a greedy-like heuristic is developed as a repair operator and reflected into the genetic algorithm. The performance of the proposed solution methodology in this research is tested using a fractional factorial experimental design as well as compared with the performance of a genetic algorithm developed for the software release planning. The comparison shows that the solution approach proposed in this research yields better result than the genetic algorithm.

• 한국공간구조학회논문집
• /
• 제5권3호
• /
• pp.117-122
• /
• 2005

This paper investigated the optimum design of truss structures based on Genetic Algorithms (GA's). With GA's characteristic of running side by side, the overall optimization and feasible operation, the optimum design model of truss structures was established. Elite models were used to assure that the best units of the previous generation had access to the evolution of current generation. Using of non-uniformity mutation brought the obvious mutation at earlier stage and stable mutation in the later stage; this benefited the convergence of units to the best result. In addition, to avoid GA's drawback of converging to local optimization easily, by the limit value of each variable was changed respectively and the genetic operation was performed two times, so the program could work more efficiently and obtained more precise results. Finally, by simulating evolution process of nature biology of a kind self-organize, self-organize, artificial intelligence, this paper established continuous structural optimization model for ten bars cantilever truss, and obtained satisfactory result of optimum design. This paper further explained that structural optimization is practicable with GA's, and provided the theoretic basis for the GA's optimum design of structural engineering.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1430-1434
• /
• 2003

In this paper, for the fuzzy-reaching law method which has the characteristic of elimination of chattering at sliding mode as well as the characteristic of fast response at the design of variable structure controller with reaching law, optimal solutions for the determination of parameters of fuzzy membership functions by using genetic algorithm are proposed. Generally, the design of fuzzy controller has difficulties in determining the parameters of fuzzy membership functions by using a tedious trial-and-error process. To overcome these difficulties, this paper develops genetic algorithm of an optimal searching method based on genetic operation, and to verify the validity of this proposed method it is simulated through 2 link robot manipulator.

• 산업공학
• /
• 제15권3호
• /
• pp.241-246
• /
• 2002

Some extensions of minimum spanning tree problem are NP-hard problem in which polynomial-time solutions for them do not exist. Because of their complexity, recently some researcher have used the genetic algorithms to solve them. In genetic algorithm approach the Prufer number is usually used to represent a tree. In this paper we discuss the problem of the Prufer number encoding method and propose an improved genetic operation. Using a numerical comparison we demonstrate the excellence of the proposed method.

• 전기학회논문지P
• /
• 제64권4호
• /
• pp.315-320
• /
• 2015

Proposal algorithm in this paper introduced cells, units of router group, for distributed processing of previous genetic algorithm. This paper presented ways to reduce search delay time of overall network through cell-based genetic algorithm. As a result of performance analysis comparing with existing genetic algorithm through experiments, the proposal algorithm was verified superior in terms of costs and delay time. Furthermore, time for routing an alternative path was reduced in proposal algorithm, in case that a network was damaged in existing optimal path algorithm, Dijkstra algorithm, and the proposal algorithm was designed to route an alternative path faster than Dijkstra algorithm, as it has a 2nd shortest path in cells of the damaged network. The study showed that the proposal algorithm can support routing of alternative path, if Dijkstra algorithm is damaged in a network.

• 정보처리학회논문지A
• /
• 제13A권1호
• /
• pp.53-56
• /
• 2006

유전 알고리즘은 자연 선택과 유전적 성질에 기반을 둔 알고리즘으로 기존 방법으로는 쉽게 해결할 수 없는 어려운 문제에서도 성공적으로 적용되었다. 기존의 유전 알고리즘은 해 집단이 큰 경우 시간이 많이 걸리는 문제점이 있다. 병렬 유전 알고리즘은 이러한 문제를 해결하기 위하여 제안된 기존의 유전 알고리즘의 확장이라 할 수 있다. 병렬 유전 알고리즘에서 중요한 요소는 이주와 유전 연산으로 이를 적절하게 설계함으로서 좋은 결과를 얻을 수 있다. 본 논문에서는 퍼지 논리를 이용하여 기존의 병렬 유전 알고리즘을 개선하고자 한다.