• 한국수자원학회논문집
• /
• 제34권5호
• /
• pp.567-575
• /
• 2001

관망해석 시뮬레이션과 유전자 알고리즘에 기초한 최적화 모형을 이용하여 최소비용의 배수관망을 설계하는 방법론이 개발되었다. 유전자 알고리즘은 추계학적 최적화 기법의 하나로, 비선형적이고 계산량이 많은 관망설계 문제에 적용하기에 적합한 장점을 가지고 있다. 기존의 연구가 대부분 전체 관망의 신설 혹은 기존 관망의 병렬확장에만 적용하던 것에 비해 본 연구에서는 개발된 모형을 수지상(tree-type) 신설관 및 loop형 병렬증설관이 공존하는 시스템에 적용하였다. 개발된 모형을 백련 배수관로를 대상으로 적용한 결과, 수리학적 제약조건을 만족시키면서 사업비를 최대 5.37% 절감할 수 있는 설계를 제공하는 것으로 나타났다.

• International Journal of Control, Automation, and Systems
• /
• 제4권5호
• /
• pp.601-614
• /
• 2006

In this paper, a study on task assignment strategies for a complex real-time network system is presented. Firstly, two task assignment strategies are proposed to improve previous strategies. The proposed strategies assign tasks with meeting end-to-end real-time constraints, and also with optimizing system utilization through period modulation of the tasks. Consequently, the strategies aim at the optimizationto optimize of system performance with while still meeting real-time constraints. The proposed task assignment strategies are devised using the genetic algorithmswith heuristic real-time constraints in the generation of new populations. The strategies are differentiated by the optimization method of the two objectives-meeting end-to-end real-time constraints and optimizing system utilization: the first one has sequential genetic algorithm routines for the objectives, and the second one has one multiple objective genetic algorithm routine to find a Pareto solution. Secondly, the performances of the proposed strategies and a well-known existing task assignment strategy using the BnB(Branch and Bound) optimization are compared with one other through some simulation tests. Through the comparison of the simulation results, the most adequate task assignment strategies are proposed for some as system requirements-: the optimization of system utilization, the maximization of running tasktasks, and the minimization of the number of network node nodesnumber for a network system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.145-146
• /
• 2006

본 논문은 부분방전(PD: Partial Discharge)의 패턴인식 확률 극대화를 목적으로 신경망(NN: Neural Network) 파라미터 중에서 은닉층 뉴런의 수, 모멘텀(momentum)의 Step size와 Decay rate 를 최적화하기 위하여 유전 알고리즘(GA: Genetic Algonthm)을 적응하였다. 실험적 연구의 대상으로서, GIS(Gas Insulated Switchgear)사고의 주요 원인으로 보고되어있는 결함들을 인위적으로 모의한 16개 Test cell을 이용하여 부분방전을 발생시켰다. 부분방전 신호는 본 연구팀이 개발한 센서를 이용하여 검출되어 데이터베이스가 구축되어 그로부터 추출된 학습 데이터들의 학습에 다음과 같은 5가지 신경망 모델이 적응되었다: Multilayer Perception (MLP), Jordan-Elman Network (JEN), Recurrent Network (RN), Self-Organizing Feature Map (SOFM), Time-Lag Recurrent Network (TLRN). 유전 알고리즘 적용 효율성을 분석하기 위하여 동일한 데이터를 이용하여 다음과 같은 두 가지 방법을 적용한 결과를 상호 비교하였다. 우선 상기 선택된 모델만 적용하였고 다근 하나는 상기 모델과 Genetic Algorithm이 동시에 적용되었다. 모든 모델에 대하여 학습오차와 패턴 분류 확률을 비교한 결과, 유전 알고리즘 적응 시 부분방전 패턴인식 확률이 향상되었음이 확인되어 향후 신뢰성 있는 GIS 부분방전 진단기술에 활용될 수 있을 것으로 사료된다.

• 한국정보통신학회논문지
• /
• 제3권1호
• /
• pp.105-111
• /
• 1999

본 논문은 유전 알고리즘과 신경망을 이용하여 PID 제어기의 최적의 파라메터를 추출하는데 있다. 유전 알고리즘에 의한 제어는 off-line 동작으로서 외란이나 부하변동에 약한 면을 가지고 있다. 따라서 신경망을 제어기에 추가하여 on-line화하여 다음과 같이 개선하고자 한다. 첫째, 신경망의 순방향 동작에서 유전 알고리즘에 의해 적합한 PID 파라메터를 찾아 세대수의 증가에 따른 최적의 출력조건을 설정하고 둘째 신경망의 학습능력을 이용하여 역전파 학습에 의한 파라메터를 수정하여 외란이나 다양한 부하 변동에 대한 적응력을 시뮬레이션으로 나타낸다.

• Bulletin of the Korean Chemical Society
• /
• 제29권4호
• /
• pp.833-841
• /
• 2008

Principal component-genetic algorithm-multiparameter linear regression (PC-GA-MLR) and principal component-genetic algorithm-artificial neural network (PC-GA-ANN) models were applied for prediction of melting point for 323 drug-like compounds. A large number of theoretical descriptors were calculated for each compound. The first 234 principal components (PC’s) were found to explain more than 99.9% of variances in the original data matrix. From the pool of these PC’s, the genetic algorithm was employed for selection of the best set of extracted PC’s for PC-MLR and PC-ANN models. The models were generated using fifteen PC’s as variables. For evaluation of the predictive power of the models, melting points of 64 compounds in the prediction set were calculated. Root-mean square errors (RMSE) for PC-GA-MLR and PC-GA-ANN models are 48.18 and $12.77{^{\circ}C}$, respectively. Comparison of the results obtained by the models reveals superiority of the PC-GA-ANN relative to the PC-GA-MLR and the recently proposed models (RMSE = $40.7{^{\circ}C}$). The improvements are due to the fact that the melting point of the compounds demonstrates non-linear correlations with the principal components.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2016년도 추계학술대회
• /
• pp.729-731
• /
• 2016

본 논문에서는 제안한 알고리즘은 이전 유전 알고리즘의 분산처리를 위해 라우터 그룹 단위인 셀을 도입하였다. 기존 최적경로 알고리즘인 Dijkstra 알고리즘에서 네트워크가 손상되었을 경우 제안한 알고리즘에는 대체 경로 설정의 연산시간이 단축되었으며 손상된 네트워크의 셀 안에서 2순위의 경로를 가지고 있으므로 Dijkstra 알고리즘보다 신속하게 대체경로를 설정하도록 설계되었다. 이는 제안한 알고리즘이 네트워크상에서 Dijkstra 알고리즘이 손상되었을 경우 대체 경로설정을 보완할 수 있음을 확인하였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1994년도 Proceedings of the Korea Automatic Control Conference, 9th (KACC) ; Taejeon, Korea; 17-20 Oct. 1994
• /
• pp.737-741
• /
• 1994

We show an application of a genetic algorithm to, control systems including neural networks. Genetic algorithms are getting more popular nowadays because of their simplicity and robustness. Genetic algorithms are global search techniques for optimization and many other problems. A feed-forward neural network which is widely used in control applications usually learns by error back propagation algorithm(EBP). But, when there exist certain constraints, EBP can not be applied. We apply a modified genetic algorithm to such a case. We show simulation examples of two cart-pole nonlinear systems: single pole and double pole.

• 전기학회논문지
• /
• 제67권6호
• /
• pp.767-772
• /
• 2018

Recently, some meta-heuristic algorithms, such as GA(Genetic Algorithm) and GP(Genetic Programming), have been used to optimize CNN(Convolutional Neural Network). The CNN, which is one of the deep learning models, has seen much success in a variety of computer vision tasks. However, designing CNN architectures still requires expert knowledge and a lot of trial and error. In this paper, the recent attempts to automatically construct CNN architectures are investigated and analyzed. First, two GA based methods are summarized. One is the optimization of CNN structures with the number and size of filters, connection between consecutive layers, and activation functions of each layer. The other is an new encoding method to represent complex convolutional layers in a fixed-length binary string, Second, CGP(Cartesian Genetic Programming) based method is surveyed for CNN structure optimization with highly functional modules, such as convolutional blocks and tensor concatenation, as the node functions in CGP. The comparison for three approaches is analysed and the outlook for the potential next steps is suggested.

• Journal of Positioning, Navigation, and Timing
• /
• 제11권2호
• /
• pp.99-107
• /
• 2022

Urban Air Mobility (UAM) such as a drone taxi is one of the future transportations that have recently been attracting attention. Along with the construction of an urban terminal, an accurate landing system for UAM is also essential. However, in urban environments, reliable Global Navigation Satellite Systems (GNSS) signals cannot be received due to obstacles such as high-rise buildings which causes multipath and non-line of sight signal. Thus, the positioning result in urban environments from the GNSS signal is unreliable. Consequently, we propose the Ultra-Wideband (UWB) network to assist the soft landing of UAM on a vertiport. Since the positioning performance of UWB network depends on the layout of UWB anchors, it is necessary to optimize the layout of UWB anchors. In this paper, we propose a two-steps genetic algorithm that consists of binary genetic algorithm involved multi objectives fitness function and integer genetic algorithm involved robust solution searching fitness function in order to optimize taking into account Fresnel hole effects.

• Bioinformatics and Biosystems
• /
• 제2권2호
• /
• pp.71-74
• /
• 2007

Cell phenotypes are determined by groups of functionally related genes. Microarray profiling of gene expression provides us response of cellular state to its perturbation. Several methods for uncovering a cellular network show reliable network reconstruction. In this study, we present reconstruction of genetic regulatory network of inflammation bowel disease in human peripheral blood mononuclear cell. The microarray based on Affymetrix Gene Chip Human Genome U133 Array Set HG-U133A is processed and applied network reconstruction algorithm, ARACNe. As a result, we will show that inferred network composed of 450 nodes and 2017 edges is roughly scale-free network and hierarchical organization. The major hub, CCNL2 (cyclin A2), in inferred network is shown to be associated with inflammatory function as well as apoptotic function.