• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.77-80
• /
• 1998

The theoretical foundations of simple genetic algorithm(SGA) are the Schema Theorem and the Building Block Hypothesis. Although SGA does well in many applications as an optimization method, still it does not guarantee the convergence of a global optimum in GA-hard problems and deceptive problems. Therefore as an alternative scheme, there is a growing interest in a co-evolutionary system, where two populations constantly interact and cooperate each other. In this paper we show why the co-evolutionary algorithm works better than SGA in terms of an extended schema theorem. Also the experimental results show a co-evolutionary algorithm works well in optimization problems.

• Journal of Electrical Engineering and Technology
• /
• 제7권3호
• /
• pp.288-296
• /
• 2012

The method proposed by the author is intended for assistance in decision-making (concerning changes of connections) by operators of complex distribution systems during states of malfunction (particularly in the events of malfunctions, for which the consequences encompass extended parts of the network), through designation of connection action scenarios (creating substitute configurations). It is the use by the classifying system working with the co-evolution algorithm that enables the effective creation of substitute scenarios for the Medium Voltage electric power distribution network. The author also completed works concerning the possibility of using cooperation of the evolutionary algorithm and the co-evolutionary algorithm with local search algorithms. The method drawn up may be used in current systems managing the work of distribution networks to assist network operators in taking decisions concerning connection actions in supervised electric power systems.

• International Journal of Control, Automation, and Systems
• /
• 제2권2호
• /
• pp.247-255
• /
• 2004

The majority of real-world problems encountered by engineers involve simultaneous optimization of competing objectives. In this case instead of single optima, there is a set of alternative trade-offs, generally known as Pareto-optimal solutions. The use of evolutionary algorithms Pareto GA, which was first introduced by Goldberg in 1989, has now become a sort of standard in solving Multiobjective Optimization Problems (MOPs). Though this approach was further developed leading to numerous applications, these applications are based on Pareto ranking and employ the use of the fitness sharing function to maintain diversity. Another scheme for solving MOPs has been presented by J. Nash to solve MOPs originated from Game Theory and Economics. Sefrioui introduced the Nash Genetic Algorithm in 1998. This approach combines genetic algorithms with Nash's idea. Another central achievement of Game Theory is the introduction of an Evolutionary Stable Strategy, introduced by Maynard Smith in 1982. In this paper, we will try to find ESS as a solution of MOPs using our game model based co-evolutionary algorithm. First, we will investigate the validity of our co-evolutionary approach to solve MOPs. That is, we will demonstrate how the evolutionary game can be embodied using co-evolutionary algorithms and also confirm whether it can reach the optimal equilibrium point of a MOP. Second, we will evaluate the effectiveness of our approach, comparing it with other methods through rigorous experiments on several MOPs.

• International Journal of Aeronautical and Space Sciences
• /
• 제3권1호
• /
• pp.50-60
• /
• 2002

A new co-evolutionary algorithm, of which the convergence speed is accelerated by neural networks, is proposed and verified in this paper. To reduce computational load required for co-evolutionary optimization processes, the cost function and constraint information is stored in the neural networks, and the extra offspring group, whose cost is computed by the neural networks, is generated. It increases the offspring population size without overloading computational effort; therefore, the convergence speed is accelerated. The proposed algorithm is applied to attitude control design of flexible satellites, and it is verified by computer simulations and experiments using a torque-free air bearing system.

• 한국지능시스템학회논문지
• /
• 제12권6호
• /
• pp.491-496
• /
• 2002

다목적 함수 최적화 문제(Multi-objective Optimization Problems : MOPs)는 공학적인 문제를 풀고자 할 때 자주 접하게 되는 대표적인 문제 중 하나이다. 공학자들이 다루는 실세계 최적화 문제들은 몇 개의 경합하는 목적 함수(objective function) 들로 이루어진 문제일 경우가 많다. 본 논문에서는 다목적 함수 최적화 문제의 정의를 소개하고 이 문제를 풀기 위한 몇 가지 접근법을 소개한다. 먼저 서론에서는 파레토 최적해(Pareto optimal solution) 의 개념을 이용한 기존의 최적화 알고리즘과 이와는 달리 게임 이론(Game Theory) 으로부터 도출된 최적화 알고리즘인 내쉬 유전자 알고리즘(Nash Genetic Algorithm Nash GA) 그리고 본 논문에서 제안하는 공진화 알고리즘의 기반이 되는 진화적 안정 전략 (Evolutionary Stable Strategy : ESS) 의 이론적 배경을 소개한다. 또 본론에서는 다목적 함수 최적화 문제와 파레토 최적 해의 정의를 소개하고 다목적 함수 최적화 문제를 풀기 위하여 유전자 알고리즘을 진화적 게임 이론(Evolutionary Game Theory : EGT) 에 적용시킨 내쉬 유전자 알고리즘과 본 논문에서 새로이 제안하는 공진화 알고리즘의 구조를 설명하고 이 두 가지 알고리즘을 대표적인 다목적 함수 최적화 문제에 적용하고 결과를 비교 검토함으로써 진화적 게임 이론의 두 가지 아이디어 내쉬의 균형(Equilibrium) 과 진화적 안정전략 에 기반한 최적화 알고리즘들이 다목적 함수 문제의 최적해 를 탐색할 수 있음을 확인한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2007년도 추계학술대회 학술발표 논문집
• /
• pp.104-107
• /
• 2007

다목적 함수의 최적화 문제(Multiobjective optimization problems)의 경우에는 하나의 최적해가 존재하는 것이 아니라 '파레토 최적해 집합(Pareto optimal set)'이라고 알려진 해들의 집합이 존재한다. 이러한 이상적 파레토 최적해 집합과 가까운 최적해를 찾기 위한 다양한 해탐색 능력은 진화 알고리즘의 성능을 결정한다. 본 논문에서는 게임 모텔에 기반한 공진화 알고리즘(GCEA:Game model based Co-Evolutionary Algorithm)에서 해집단의 다양성을 유지하여, 다양한 비지배적 파레토 대안해(non-dominated alternatives)들을 찾기 위한 방법을 제안한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.185-190
• /
• 2002

In distributed autonomous robotic systems (DARS), each robot must behave by itself according to its states ad environments, and if necessary, must cooperate with other robots in order to carry out their given tasks. Its most significant merit is that they determine their behavior independently, and cooperate with other robots in order to perform the given tasks. Especially, in DARS, it is essential for each robot to have evolution ability in order to increase the performance of system. In this paper, a schema co-evolutionary algorithm is proposed for the evolution of collective autonomous mobile robots. Each robot exchanges the information, chromosome used in this algorithm, through communication with other robots. Each robot diffuses its chromosome to two or more robots, receives other robot's chromosome and creates new species. Therefore if one robot receives another robot's chromosome, the robot creates new chromosome. We verify the effectiveness of the proposed algorithm by applying it to cooperative search problem.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 춘계학술대회 학술발표 논문집
• /
• pp.123-126
• /
• 1998

The theoretical foundations of GA are the Schema Theorem and the Building Block Hypothesis. In the Meaning of these foundational concepts, simple genetic algorithm(SGA) allocate more trials to the schemata whose average fitness remains above average. Although SGA does well in many applications as an optimization method, still it does not guarantee the convergence of a global optimum. Therefore as an alternative scheme, there is a growing interest in a co-evolutionary system, where two populations constantly interact and co-evolve in contrast with traditional single population evolutionary algorithms. In this paper, we propose a new design method of an optimal fuzzy logic controller using co-evolutionary concept. In general, it is very difficult to find optimal fuzzy rules by experience when the input and/or output variables are going to increase. So we propose a co-evolutionary method finding optimal fuzzy rules. Our algorithm is that after constructing two population groups m de up of rule vase and its schema, by co-evolving these two populations, we find optimal fuzzy logic controller. By applying the proposed method to a path planning problem of autonomous mobile robots when moving objects exist, we show the validity of the proposed method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.281-285
• /
• 2005

Learning and evolving are two basics for data mining. As compared with classical learning theory based on objective function with minimizing training errors, the recently evolutionary computing has had an efficient approach for constructing optimal model without the minimizing training errors. The global search of evolutionary computing in solution space can settle the local optima problems of learning models. In this research, combining co-evolving algorithm into statistical learning theory, we propose an co-evolutionary computing for statistical learning theory for overcoming local optima problems of statistical learning theory. We apply proposed model to classification and prediction problems of the learning. In the experimental results, we verify the improved performance of our model using the data sets from UCI machine learning repository and KDD Cup 2000.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.553-559
• /
• 1998

Simple Genetic Algorithm(SGA) proposed by J. H. Holland is a population-based optimization method based on the principle of the Darwinian natural selection. The theoretical foundations of GA are the Schema Theorem and the Building Block Hypothesis. Although GA goes well in many applications as an optimization method, still it does not guarantee the convergence to a global optimum in some problems. In designing intelligent systems, specially, since there is no deterministic solution, a heuristic trial-and error procedure is usually used to determine the systems' parameters. As an alternative scheme, therefore, there is a growing interest in a co-evolutionary system, where two populations constantly interact and co-evolve. In this paper we review the existing co-evolutionary algorithms and propose co-evolutionary schemes designing intelligent systems according to the relation between the system's components.