• 한국정보시스템학회:학술대회논문집
• /
• 한국정보시스템학회 2004년도 추계학술대회
• /
• pp.37-41
• /
• 2004

The existing network can be expanded with addition of new nodes and multiple choices of link type for each nossible link. In this paper, the design problem of network expansion is defined as finding the network topology minimizing cost subject to reliability constraint. To efficiently solve the problem, an genetic algorithm approach is suggested.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권1호
• /
• pp.33-38
• /
• 2006

In this paper, we propose a new architecture of Fuzzy Polynomial Neural Networks(FPNN) by means of genetically optimized Fuzzy Polynomial Neuron(FPN) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially Genetic Algorithms(GAs). The conventional FPNN developed so far are based on mechanisms of self-organization and evolutionary optimization. The design of the network exploits the extended Group Method of Data Handling(GMDH) with some essential parameters of the network being provided by the designer and kept fixed throughout the overall development process. This restriction may hamper a possibility of producing an optimal architecture of the model. The proposed FPNN gives rise to a structurally optimized network and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. It is shown that the proposed advanced genetic algorithms based Fuzzy Polynomial Neural Networks is more useful and effective than the existing models for nonlinear process. We experimented with Medical Imaging System(MIS) dataset to evaluate the performance of the proposed model.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.946-949
• /
• 2005

It is very a time-consuming and error-prone process to obtain the optimal injection condition, which can produce good injection molding products in some operational variation of facilities, from a seed injection condition. This study proposes a new approach to search the optimal injection molding condition using a neural network and a genetic algorithm. To estimate the defect type of unknown injection conditions, this study forces the neural network into learning iteratively from the injection molding conditions collected. Major two parameters of the injection molding condition - injection pressure and velocity are encoded in a binary value to apply to the genetic algorithm. The optimal injection condition is obtained through the selection, cross-over, and mutation process of the genetic algorithm. Finally, this study compares the optimal injection condition searched using the proposed approach. with the other ones obtained by heuristic algorithms and design of experiment technique. The comparison result shows the usability of the approach proposed.

• 한국컴퓨터정보학회논문지
• /
• 제11권4호
• /
• pp.119-125
• /
• 2006

네트워크를 통하여 서로 연결된 컴퓨팅 자원들의 집합을 분산 시스템이라고 정의할 수 있다. 최적화 문제 영역에서 가장 중요한 해결 기법 중에 하나인 병렬 유전자 알고리즘은 분산 시스템을 기반으로 하고 있다. 인터넷과 이동 컴퓨팅과 같은 동적 네트워크 환경 하에서 네트워크의 상태는 가변적으로 변할 수 있어 기존의 병렬 유전자 알고리즘을 분산 시스템에서 최적화 문제를 해결하기 위하여 그대로 사용하기에는 비효율적이다. 본 논문에서는 동적 네트워크 환경 하에서 분산 에이전트를 사용하여 병렬 유전자 알고리즘을 효율적으로 사용할 수 있는 기법을 제시한다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 추계학술대회 학술발표 논문집
• /
• pp.255-258
• /
• 2001

This paper is implementation of cellular automata neural network system which is a living creatures' brain using evolving hardware concept. Cellular automata neural network system is based on the development and the evolution, in other words, it is modeled on the ontogeny and phylogeny of natural living things. The proposed system developes each cell's state in neural network by CA. And it regards code of CA rule as individual of genetic algorithm, and evolved by genetic algorithm. In this paper we implement this system using evolving hardware concept Evolving hardware is reconfigurable hardware whose configuration is under the control of an evolutionary algorithm. We design genetic algorithm process for evolutionary algorithm and cells in cellular automata neural network for the construction of reconfigurable system. The effectiveness of the proposed system is verified by applying it to time-series prediction.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 제37회 하계학술대회 논문집 D
• /
• pp.2075-2076
• /
• 2006

In this paper, we propose a new architecture of Genetic Algorithms(GAs)-based Backpropagation(BP). The conventional BP does not guarantee that the BP generated through learning has the optimal network architecture. But the proposed GA-based BP enable the architecture to be a structurally more optimized network, and to be much more flexible and preferable neural network than the conventional BP. The experimental results in BP neural network optimization show that this algorithm can effectively avoid BP network converging to local optimum. It is found by comparison that the improved genetic algorithm can almost avoid the trap of local optimum and effectively improve the convergent speed.

• 한국국방경영분석학회지
• /
• 제26권1호
• /
• pp.56-69
• /
• 2000

A frequency assignment problem on time division duplex system is considered. Republic of Korea Army (ROKA) has been establishing an infrastructure of tactical communication (SPIDER) system for next generation and it will be a core network structure of system. VHF system is the backbone network of SPIDER, that performs transmission of data such as voice, text and images. So, it is a significant problem finding the frequency assignment with no interference under very restricted resource environment. With a given arbitrary configuration of communications network, we find a feasible solution that guarantees communication without interference between sites and relay stations. We formulate a frequency assignment problem as an Integer Programming model, which has NP-hard complexity. To find the assignment results within a reasonable time, we take a genetic algorithm approach which represents the solution structure with available frequency order, and develop a genetic operation strategies. Computational result shows that the network configuration of SPIDER can be solved efficiently within a very short time.

• 한국산업정보학회논문지
• /
• 제19권4호
• /
• pp.87-104
• /
• 2014

본 연구에서는 지역적으로 집중화된 역물류네트워크(Regionally centralized multistage reverse logistics network: cmRL)와 지역적으로 분산회된 역물류네트워크(Regionally decentralized multistage reverse logistics network: dmRL)를 제안하고 있다. cmRL과 dmRL 각각은 고려되는 영역 전체와 지역적으로 분산된 세부영역에서의 RL 네트워크로 구성된다. 이들은 혼합정수계획법(Mixed integer programming: MIP) 모델로 공식화되며, 유전알고리즘(Genetic algorithm: GA)을 통해 해를 구하게 된다. 사례연구에서는 두 가지 형태의 RL네트워크를 제시하며 다양한 수행도 척도를 사용하여 cmRL과 dmRL의 효율성을 비교분석하였다. 분석결과 cmRL이 dmRL 보다 더 우수한 수행도를 나타내었다.

• 대한산업공학회지
• /
• 제28권1호
• /
• pp.14-24
• /
• 2002

We focus on resource allocation planning in container terminal operation planning problems and present network design model and genetic algorithm. We present a network design model in which arc capacities must be properly dimensioned to sustain the container traffic. This model supports various planning aspects of container terminal and brings in a very general form. The integer programming model of network design can be extended to accommodate vertical or horizontal yard configuration by adding constraints such as restricting the sum of yard cranes allocated to a block of yards. We devise a genetic algorithm for the network design model in which genes have the form of general integers instead of binary integers. In computational experiments, it is found that the genetic algorithm can produce very good solution compared to the optimal solution obtained by CPLEX in terms of computation time and solution quality. This algorithm can be used to generate many alternatives of a resource allocation plan for the container terminal and to evaluate the alternatives using various tools such as simulation.

• 대한산업공학회지
• /
• 제39권5호
• /
• pp.361-366
• /
• 2013

Prediction of process parameters is very important in parameter design. If predictions are fairly accurate, the quality improvement process will be useful to save time and reduce cost. The concept of dual response approach based on response surface methodology has widely been investigated. Dual response approach may take advantages of optimization modeling for finding optimum setting of input factor by separately modeling mean and variance responses. This study proposes an alternative dual response approach based on machine learning techniques instead of statistical analysis tools. A hybrid neural network-genetic algorithm has been proposed for the purpose of parameter design. A neural network is first constructed to model the relationship between responses and input factors. Mean and variance responses correspond to output nodes while input factors are used for input nodes. Using empirical process data, process parameters can be predicted without performing real experimentations. A genetic algorithm is then applied to find the optimum settings of input factors, where the neural network is used to evaluate the mean and variance response. A drug formulation example from pharmaceutical industry has been studied to demonstrate the procedures and applicability of the proposed approach.