• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 D
• /
• pp.2876-2878
• /
• 2005

In this paper, we propose Genetic Algorithms(GAs)-based Optimal Polynomial Neural Networks(PNN). The proposed algorithm is based on Group Method of Data Handling(GMDH) method and its structure is similar to feedforward Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and can be generated. The each node of PNN structure uses several types of high-order polynomial such as linear, quadratic and modified quadratic, and is connected as various kinds of multi-variable inputs. The conventional PNN depends on experience of a designer that select No. of input variable, input variable and polynomial type. Therefore it is very difficult a organizing of optimized network. The proposed algorithm identified and selected No. of input variable, input variable and polynomial type by using Genetic Algorithms(GAs). In the sequel the proposed model shows not only superior results to the existing models, but also pliability in organizing of optimal network. The study is illustrated with the ACI Distance Relay Data for application to power systems.

• 전력전자학회:학술대회논문집
• /
• 전력전자학회 2000년도 전력전자학술대회 논문집
• /
• pp.521-524
• /
• 2000

The switched reluctance motor(SRM) drive system provides a good adjustable speed characteristics. However higher torque ripple are one of the few disadvantages of the SRM drives. The SRM would have to operated with an MMF waveform specified for switching angle and phase voltage. This paper proposes control modelling method using ANN(Artificial Neural Network) and GA(Genetic Algorithm) that are used to control switch-on angles and input voltage.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 추계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.56-60
• /
• 2002

The paper presents the optimum design of a linear induction motor(LIM) using Genetic algorithm, Neural Network and SUMT. The design variables are optimized by three different optimization methods and the results are discussed.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권6호
• /
• pp.386-395
• /
• 2002

본 논문에서는, 인식될 데이타에서 최적 특징을 구성할 수 있는 새로운 신경망 구조인 동적 유전 트리맵(DGTM)을 제안한다. DGTM은 기존의 신경망(neural networks)에서 고려되지 못한 데이터의 특징(feature)에 대한 중요도를 유전 알고리즘(genetic algorithm)으로 구성하고, 특징의 우선순위에 따라 트리 구조를 도입한 GTM(genetic tree-map)을 적용한다. 데이타의 유사성에 따라서 신경망의 뉴런이 동적으로 분리되고 병합될 수 있도록 동적인 기능을 갖는 DGTM(dynamic GTM)으로 확장한 방식을 제안한다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1994년도 추계학술대회 논문집 학회본부
• /
• pp.408-410
• /
• 1994

This Paper Presents a learning strategy for neural networks based on genetic algorithms and evolution strategies. Genetic algorithms and evolution strategies are used to train weights of feedforward neural network to solve problems faster than neural network, especially backpropagation. Simulations are performed exclusive-OR problem, full-adder problem, sine function generator to demonstrate the effectiveness of neural-GA-ES.

• 전기학회논문지
• /
• 제62권5호
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.

• 한국정보통신학회논문지
• /
• 제3권2호
• /
• pp.383-388
• /
• 1999

본 논문에서는 정밀 제어와 온-라인 제어를 위하여 유전 알고리즘을 이용한 퍼지-신경망 제어기를 제안하였다. 제안된 제어기의 설계방법은 유전 알고리즘을 사용하여 불확실한 플랜트에 대한 근사적 퍼지 소속함수를 얻은 후, 퍼지-신경망 제어기의 적응학습에 의해 최적의 퍼지 소속함수를 조정할 수 있는 제어구조를 제안하였다. 제안된 제어기를 사용했을 때의 효율성과 정확성을 평가하기 위하여 DC 서보모터의 속도제어 실험을 통해 GA-Fuzzy 제어기를 사용했을 때와 비교분석 한다.

• 산업공학
• /
• 제25권3호
• /
• pp.319-326
• /
• 2012

To effectively predict financial crisis, this paper presents an early warning system based on artificial intelligence technologies. Both Genetic Algorithms and Neural Networks are utilized for the proposed system. First, a genetic algorithm has been developed for the effective selection of economic indices, which are used for monitoring financial crisis. Then, an optimum weight of the selected indices has been determined by a neural network method. To validate the effectiveness of the proposed system, a series of experiments has been conducted by using the Korean economic indices from 2005 to 2008.

• Journal of Advanced Marine Engineering and Technology
• /
• 제34권7호
• /
• pp.971-980
• /
• 2010

In this paper, an artificial neural network (ANN) was employed to build a predicting model for refrigerator structure. The predicting model includes three input variables of the plaque depth (D), width (W) and interval distance(S) on the inner wall. Finite element method was utilized to obtain the data, which would be necessary for the ANN training process. Finally, a genetic algorithm (GA) was applied to find the optimal parameters that leaded to the minimum inner case deformation under operating condition. The optimal combination found is the depth(D) of 2.63mm, the width(W) of 19.24mm and the interval distance(S) of 49.38mm which leaded to the smallest deformation of 1.88mm for the given refrigerator model.

• 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.