• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2006년도 추계학술발표논문집
• /
• pp.186-190
• /
• 2006

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 제38회 하계학술대회
• /
• pp.1574-1575
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.

• Transactions on Control, Automation and Systems Engineering
• /
• 제1권1호
• /
• pp.54-61
• /
• 1999

FCM(Fuzzy Cognitive Map) is proposed for representing causal reasoning. Its structure allows systematic causal reasoning through a forward inference. By using the FCM, authors have proposed FCM-based fault diagnostic algorithm. However, it can offer multiple interpretations for a single fault. In process engineering, as experience accumulated, some form of quantitative process knowledge is available. If this information can be integrated into the FCM-based fault diagnosis, the diagnostic resolution can be further improved. The purpose of this paper is to propose an enhanced FCM-based fault diagnostic scheme. Firstly, the membership function of fuzzy set theory is used to integrate quantitative knowledge into the FCM-based diagnostic scheme. Secondly, modified TAM recall procedure is proposed. Considering that the integration of quantitative knowledge into FCM-based diagnosis requires a great deal of engineering efforts, thirdly, an automated procedure for fusing the quantitative knowledge into FCM-based diagnosis is proposed by utilizing self-learning feature of neural network. Finally, the proposed diagnostic scheme has been tested by simulation on the two-tank system.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 하계학술대회 논문집 C
• /
• pp.1046-1049
• /
• 1998

This paper deals with the new fault detection technique for transmission line using Neuro-fuzzy Scheme. Neuro-fuzzy Scheme is ANFIS(Adaptive-network Fuzzy Inference System) based on fusion of fuzzy logic and neural networks. The proposed scheme has five layers. Each layer is the component of fuzzy Inference system and performs different action. Using learning method of neural network, fuzzy premise and consequent parameters is tuned properly.

• 전자공학회논문지B
• /
• 제29B권8호
• /
• pp.1-6
• /
• 1992

This paper proposed a neural computer architecture for the learning of script character pattern recognition categories. Oriented filter with complex cells preprocess about the input script character, abstracts contour from the character. This contour normalized and inputed to the ART. Top-down attentional and matching mechanisms are critical in self-stabilizing of the code learning process. The architecture embodies a parallel search scheme that updates itself adaptively as the learning process unfolds. After learning ART self-stabilizes, recognition time does not grow as a function of code complexity. Vigilance level shows the similarity between learned patterns and new input patterns. This character recognition system is designed to adaptable. The simulation of this system showed satisfied result in the recognition of the hand written characters.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.552-563
• /
• 2005

In this paper, we propose a wavelet based fuzzy neural network (WFNN) based direct adaptive control scheme for the solution of the tracking problem of mobile robots. To design a controller, we present a WFNN structure that merges the advantages of the neural network, fuzzy model and wavelet transform. The basic idea of our WFNN structure is to realize the process of fuzzy reasoning of the wavelet fuzzy system by the structure of a neural network and to make the parameters of fuzzy reasoning be expressed by the connection weights of a neural network. In our control system, the control signals are directly obtained to minimize the difference between the reference track and the pose of a mobile robot via the gradient descent (GD) method. In addition, an approach that uses adaptive learning rates for training of the WFNN controller is driven via a Lyapunov stability analysis to guarantee fast convergence, that is, learning rates are adaptively determined to rapidly minimize the state errors of a mobile robot. Finally, to evaluate the performance of the proposed direct adaptive control system using the WFNN controller, we compare the control results of the WFNN controller with those of the FNN, the WNN and the WFM controllers.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.111-114
• /
• 1997

Usually, Evolutionary Algorithms are considered more efficient for optimal system design, However, the performance of the system is determined by fitness function and system environment. In this paper, in order to overcome the limitation of the performance by this factor, we propose a co-evolutionary method that two populations constantly interact and coevolve. In this paper, we apply coevolution to neural network's evolving. So, one population is composed of the structure of neural networks and other population is composed of training patterns. The structure of neural networks evolve to optimal structure and, at the same time, training patterns coevolve to feature patterns. This method prevent the system from the limitation of the performance by random design of neural network structure and inadequate selection of training patterns. In this time neural networks are trained by evolution strategies that are able to apply to the unsupervised learning. And in the coding of neural networks, we propose the method to maintain nonredundancy and character preservingness that are essential factor of genetic coding. We show the validity and the effectiveness of the proposed scheme by applying it to the visual servoing of RV-M2 robot manipulators.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1293-1302
• /
• 1999

In this paper, an on-line process scheme is presented for implementation of a intelligent on-line modeling of nonlinear complex system. The proposed on-line process scheme is composed of FNN-based model algorithm and PLC-based simulator, Here, an adaptive fuzzy-neural networks and HCM(Hard C-Means) clustering method are used as an intelligent identification algorithm for on-line modeling. The adaptive fuzzy-neural networks consists of two distinct modifiable sturctures such as the premise and the consequence part. The parameters of two structures are adapted by a combined hybrid learning algorithm of gradient decent method and least square method. Also we design an interface S/W between PLC(Proguammable Logic Controller) and main PC computer, and construct a monitoring and control simulator for real process system. Accordingly the on-line identification algorithm and interface S/W are used to obtain the on-line FNN model structure and to accomplish the on-line modeling. And using some I/O data gathered partly in the field(plant), computer simulation is carried out to evaluate the performance of FNN model structure generated by the on-line identification algorithm. This simulation results show that the proposed technique can produce the optimal fuzzy model with higher accuracy and feasibility than other works achieved previously.

• 한국항행학회논문지
• /
• 제24권1호
• /
• pp.47-52
• /
• 2020

도래각추정은 표적으로부터 생성, 혹은 반사된 신호를 분석하여 표적의 방향을 추정하는 것으로 다양한 분야에 활용되고 있다. 인공신경망은 생물의 신경망을 모방한 기계학습의 한 분야로 패턴인식에서 좋은 성능을 보인다. 이러한 인공신경망을 도래각 추정에 활용하는 연구가 진행되어왔으나, 다양한 신호대잡음비 환경에 대응하는데에 제한이 있는 상황이다. 본 논문에서는 도래각 추정을 위한 3단계 인공신경망 알고리듬을 제안한다. 제안하는 알고리듬은 잡음제거과정을 통해 단일 신호대잡음비 환경에서 학습한 모델을 다양한 환경에 적용해도 성능감소를 최소화할 수 있다. 또한 도래각 시프트 과정을 통해 학습 난이도를 낮출 수 있고 효율적인 추정이 가능하다. 우리는, 제안하는 알고리듬과 다른 부공간 기법, Cramer-Rao bound (CRB)와의 성능 비교를 통해 제안하는 알고리듬이 낮은 신호대잡음비 환경, 표적들의 도래각이 가까운 환경 등 특정한 열악한 관측환경에서 타 기법에 비해 좋은 성능을 보이는 것을 확인하였다.

• 전자공학회논문지CI
• /
• 제46권2호
• /
• pp.65-74
• /
• 2009

신경망의 구조를 최적화하기 위해서는 노드 또는 연결을 잘라내는 가지치기 방법과 노드를 추가해 나가는 구조 증가 방법이 있다. 이 논문은 신경망의 구조 최적화를 위해 가지치기 방법을 사용하며, 최적의 노드 가지치기를 찾기 위해 유전 알고리즘을 사용한다. 기존 연구에서는 입력층과 은닉층의 노드를 따로 최적화 대상으로 삼았다 우리는 두 층의 노드를 하나의 염색체에 표현하여 동시 최적화를 꾀하였다. 자식은 부모의 가중치를 상속받는다 학습을 위해서는 기존의 오류 역전파 알고리즘을 사용한다. 실험은 UCI Machine Learning Repository에서 제공한 다양한 데이터를 사용하였다. 실험 결과 신경망 노드 가지치기 비율이 평균 $8{\sim}25%$에서 좋은 성능을 얻을 수 있었다. 또한 다른 가지치기 및 구조 증가 알고리즘과의 교차검증에 대한 t-검정 결과 그들에 비해 우수한 성능을 보였다.