• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.43-54
• /
• 2004

This study analyzes characteristics and applicability of genetic algorithms and genetic operators to optimize highway alignments. Genetic algorithms, one of artificial intelligence techniques, are fast and efficient search algorithms for generating, evaluation and finding optimal highway alignment alternatives. The performance of genetic algorithms as an optimal search tool highly depends on genetic operators that are designed as a problem-specific. This study adopts low mutation operators(uniform mutation operator, straight mutation operator, non-uniform mutation operator whole non-uniform mutation operator) to explore whole search spaces, and four crossover operators(simple crossover operator, two-point crossover operator, arithmetic crossover operator, heuristic crossover operator) to exploit food characteristics of the best chromosome in previous generations. A case study and a sensitivity analysis have shown that the eight problem-specific operators developed for optimizing highway alignments enhance the search performance of genetic algorithms, and find good solutions(highway alignment alternatives). It has been also found that a mixed and well-combined use of mutation and crossover operators is very important to balance between pre-matured solutions when employing more crossover operators and more computation time when adopting more mutation operators.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10a
• /
• pp.744-746
• /
• 1998

외판원(Traveling Salesman Problem)는 계산 복잡도가 매우 높으므로 이를 해결하려는 다양한 방법들이 제시되어 왔다. 최근에는 특히 휴리스틱(Heuristic) 에 기반한 유전 알고리즘(Genetic Algorithm)에 위한 방법이 관심을 집중시키고 있고, 이를 위한 다양한 교잡(Crossiver)연산자와 돌연변이(Mutation) 연산자들이 발표되고 있다. 돌연변이연산자는 지역해에 빠지는 것을 방지하며, 유용한 유전 특성을 잃어버릴 위험이 있는 교잡 연산자의 단점을 보완할 수 있다. 본 논문에서는 새로운 돌연변이 연산자를 개발하여 적용한 유전 알고리즘으로 외판원 문제를 해결한다.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.85-92
• /
• 2005

In this Paper, we develope an effective web-based learning contents using interactive genetic algorithms with modified mutation operation. In the interactive genetic algorithm, reciprocal exchange mutation is used. But. we modify the mutation operator to improve the learning effects. The new web-based learning contents using interactive genetic algorithm provide the dynamic learning contents providing and real-time test system. Especially, learners can execute the interactive genetic algorithm according to the learners' characters and interests to select the efficient learning environments and contents sequences.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.55-61
• /
• 2020

Genetic Algorithm(GA) is applied to a problem that could not figure out its solution in a straightway. It is called as NP-hard problem. GA requires a high-performance system to be run on since the high-cost operations are needed such as crossover, selection, and mutation. Moreover, the scale of the problem domain is normally huge. That is why the straightway cannot be applied. To reduce the drawback of high-cost requirements, we try to answer if all the operations including mutation are necessary for all cases. In the experiment, we set up two cases of with/without mutation operations and gather the number of generations and the fitness of a solution. The subject in the experiment is Travelling Salesman Problem(TSP), which is one of the popular problems solved by GA. As a result, the cases with mutation operation are not faster and the solution is fitter than the case with mutation operation. From the result, the conclusion is that mutation operation does not always need for a better solution in a faster way.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.35-38
• /
• 2000

본 논문에서는 퍼지 제어기의 설계를 위한 다중 돌연변이 연산자를 갖는 Niche Meta 유전 알고리즘을 제안한다. 제안된 알고리즘에서 유전자는 유전 알고리즘에 사용되는 교배율이나 돌연변이율과 같은 구조 매개변수와 퍼지 제어기의 입, 출력 소속함수를 나타내는 매개변수로 구성된다. 제안된 알고리즘은 부개체군들에 대해 퍼지 제어기의 소속함수의 매개변수를 최적화시키는 지역적 탐색을 수행하면서 전체 개체군에 대해서 최적의 구조 매개변수에 대한 전역적인 탐색을 수행한다. 다중 돌연변이 연산자는 지역적 진화의 결과에 따라 진화에 가장 적합한 돌연변이 방법으로 선택된다. 제안된 알고리즘의 효율성을 입증하기 위해 2 자유도를 구륜이동 로봇에 대한 모의 실험을 수행한다.

• The Journal of Information Technology
• /
• v.5 no.4
• /
• pp.73-79
• /
• 2002

In this paper, I will propose the Niche-Meta Genetic Algorithm that has a multi-mutation operator for design of fuzzy controller. The gene in the proposed algorithm is formed by several parameters that represent the crossover rate, mutation rate and input-output membership functions. The optimization of fuzzy membership function is performed with local search on sub-population and the optimal structure is constructed with global search on total-population. The multi-mutation is selected under basis of the result of local evolution. A simulation for 2 D.O.F wheeled-mobile robot is showed to prove the efficiency of the proposed algorithm

• Journal of Intelligence and Information Systems
• /
• v.8 no.2
• /
• pp.189-203
• /
• 2002

In this paper we compare the performances of adaptive operators in genetic algorithm. For the adaptive operators, the crossover and mutation operators of genetic algorithm are considered. One fuzzy logic controller is developed in this paper and two heuristics is presented from conventional works for constructing the operators. The fuzzy logic controller and two conventional heuristics adaptively regulate the rates of the operators during genetic search process. All the algorithms are tested and analyzed in numerical examples. Finally, the best algorithm is recommended.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1998.10a
• /
• pp.209-213
• /
• 1998

Job-Shop Scheduling 문제는 전형적인 NP-hard 문제로서 효율적인 발견적 기법을 필요로 한다. 본 연구에서는 이 문제에 대한 유전알고리즘들의 성능을 비교 분석한다. 유전 알고리즘의 주요 구성 요소들로는 크게 선별, 교차, 돌연변이 등이 존재하는데, 특히 선별은 적자 생존의 자연 법칙에 기초하여, 환경에 대한 적응도에 의해 현 세대의 모집단으로부터 다음 세대에 생존할 개체를 선택하는 과정으로 해의 산출에 중요한 역할을 하는 부분이다. 기존의 많은 연구들이 유전 연산자인 교차, 돌연변이 방법들에 대한 성능 비교에 초점을 맞추었는데, 본 연구에서는 선별 과정에 초점을 맞추어 기존의 알려진 여러 선별 방법 들을Job-Shop Scheduling 문제에의 적용을 통해 비교 분석하고 새로운 선별 방법을 제안한다.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.11 no.2 s.54
• /
• pp.1-9
• /
• 2007

The method of generating the artificial acceleration time histories for seismic analysis based on genetic algorithms is presented. For applying to the genetic algorithms, the frequencies are selected as the decision variables eventually to be genes. An arithmetic average crossover operator and an arithmetic ratio mutation operator are suggested in this study. These operators as well as the typical simple crossover operator are utilized in generating the artificial acceleration time histories corresponding to the specified design response spectrum. Also these generated artificial time histories are checked whether their outward features are to be coincident with the recorded earthquake motion or not. The features include envelope shape, correlation condition between 2 horizontal components of motion, and the relationship of max. acceleration, max. velocity and max. displacement of ground.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.673-680
• /
• 2002

This paper proposes a method for detecting edge using an evolutionary programming and a momentum back-propagation algorithm. The evolutionary programming does not perform crossover operation as to consider reduction of capability of algorithm and calculation cost, but uses selection operator and mutation operator. The momentum back-propagation algorithm uses assistant to weight of learning step when weight is changed at learning step. Because learning rate o is settled as less in last back-propagation algorithm the momentum back-propagation algorithm discard the problem that learning is slow as relative reduction because change rate of weight at each learning step. The method using EP-MBP is batter than GA-BP method in both learning time and detection rate and showed the decreasing learning time and effective edge detection, in consequence.