• 한국정보처리학회논문지
• /
• 제3권5호
• /
• pp.1138-1146
• /
• 1996

퍼지 논리는 추론과정에서 일부의 정보가 무시되어 적절하지 못한 추론 결과를 초래할 수 있다. 한편, 신경망은 패턴 처리에는 적합하지만 인간의 지식을 모델링하기 위해서 필요한 논리적인 추론에는 부적합하다. 그러나 신경망의 변형인 신경논리망 (neural logic network)을 이용하면 논리적인 추론이 가능하다. 따라서 본 논문에서는 기존의 신경논리망을 기반으로 하는 추론 네트워크를 확장하여 퍼지추론 네트워크(fuzzy inference network)를 구성한다. 그리고 기존의 추론 네트워크에서 사용되는 전파규칙 (propagation rule)을 보완하여 적용한다. 퍼지추론 네트워크 상에서 퍼지 규칙의 실행부에 해당하는 명제의 믿음값을 결정하기 위해서는 추론하고자 하는 명제에 연결된 노드들을 탐색해야 한다. 이를 위해서 연결된 모든 노드들의 링크를 따라 순차적인 탐색을 하는 경우와 링크에 부여된 우선순위에 의해 탐색을 하는 경우의 탐색비용에 대하여 실험을 통해 비교·평가한다.

• 대한전자공학회논문지TE
• /
• 제39권4호
• /
• pp.363-369
• /
• 2002

본 논문은 적응성 뉴로-퍼지 인터페이스 시스템(Adaptive Neuro-Fuzzy Inference System : ANFIS)과 웨이브렛 변환 다중해상도 분해(multi-resolution Analysis : MRA)을 기반으로 한 웨이브렛 신경망을 가지고 임의의 비선형 함수 학습 근사화를 개선하는 것이다. ANFIS 구조는 벨형 퍼지 소속 함수로 구성이 되었으며, 웨이브렛 신경망은 전파 알고리즘과 역전파 신경망 알고리즘으로 구성되었다. 이 웨이브렛 구성은 단일 크기이고, ANFIS 기반 웨이브렛 신경망의 학습을 위해 역전파 알고리즘을 사용하였다. 1차원과 2차원 함수에서 웨이브렛 전달 파라미터 학습과 ANFIS의 벨형 소속 함수를 이용한 ANFIS 모델 기반 웨이브렛 신경망의 웨이브렛 기저 수 감소와 수렴 속도 성능이 기존의 알고리즘 보다 개선되었음을 확인하였다.

• International Journal of Aeronautical and Space Sciences
• /
• 제17권2호
• /
• pp.195-203
• /
• 2016

In order to overcome the influence of system stability and accuracy caused by uncertainty, estimation errors and external disturbances in Eight-Rotor MAV, L2 gain control method was proposed based on interval type II fuzzy neural network identification here. In this control strategy, interval type II fuzzy neural network is used to estimate the uncertainty and non-linearity factor of the dynamic system, the adaptive variable structure controller is applied to compensate the estimation errors of interval type II fuzzy neural network, and at last, L2 gain control method is employed to suppress the effect produced by external disturbance on system, which is expected to possess robustness for the uncertainty and non-linearity. Finally, the validity of the L2 gain control method based on interval type II fuzzy neural network identifier applied to the Eight-Rotor MAV attitude system has been verified by three prototy experiments.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
• /
• pp.399-403
• /
• 1998

In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.

• 한국멀티미디어학회논문지
• /
• 제16권11호
• /
• pp.1338-1347
• /
• 2013

Face recognition is a science of automatically identifying individuals based their unique facial features. In order to avoid overfitting and reduce the computational reduce the computational burden, a new face recognition algorithm using PCA-fisher linear discriminant (PCA-FLD) and fuzzy radial basis function neural network (RBFNN) is proposed in this paper. First, face features are extracted by the principal component analysis (PCA) method. Then, the extracted features are further processed by the Fisher's linear discriminant technique to acquire lower-dimensional discriminant patterns, the processed features will be considered as the input of the fuzzy RBFNN. As a widely applied algorithm in fuzzy RBF neural network, BP learning algorithm has the low rate of convergence, therefore, an improved learning algorithm based on Levenberg-Marquart (L-M) for fuzzy RBF neural network is introduced in this paper, which combined the Gradient Descent algorithm with the Gauss-Newton algorithm. Experimental results on the ORL face database demonstrate that the proposed algorithm has satisfactory performance and high recognition rate.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2000년도 춘계학술대회 학술발표 논문집
• /
• pp.114-117
• /
• 2000

In this paper, Fuzzy Self-organizing Neural Networks(FSONN) based on Fuzzy Neural Networks(FNN) is proposed to overcome some problems, such as the conflict between ovefitting and good generation, and low reliability. The proposed FSONN consists of FNN and SONN. Here, FNN is used as the premise part of FSONN and SONN is the consequnt part of FSONN. The FUN plays the preceding role of FSONN. For the fuzzy reasoning and learning method in FNN, Simplified fuzzy reasoning and backpropagation learning rule are utilized. The number of layers and the number of nodes in each layers of SONN that is based on the GMDH method are not predetermined, unlike in the case of the popular multi layer perceptron structure and can be generated. Also the partial descriptions of nodes can use various forms such as linear, modified quadratic, cubic, high-order polynomial and so on. In this paper, the optimal design procedure of the proposed FSONN is shown in each step and performance index related to approximation and generalization capabilities of model is evaluated and also discussed.

• 전기학회논문지
• /
• 제63권4호
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.372-372
• /
• 2000

In this paper, we propose Neuro Fuzzy Polynomial Networks(NFPN) based on Polynomial Neural Network(PNN) and Neuro-Fuzzy(NF) for model identification of complex and nonlinear systems. The proposed NFPN is generated from the mutually combined structure of both NF and PNN. The one and the other are considered as the premise part and consequence part of NFPN structure respectively. As the premise part of NFPN, NF uses both the simplified fuzzy inference as fuzzy inference method and error back-propagation algorithm as learning rule. The parameters such as parameters of membership functions, learning rates and momentum coefficients are adjusted using genetic algorithms. As the consequence part of NFPN, PNN is based on Group Method of Data Handling(GMDH) method and its structure is similar to Neural Networks. But the structure of PNN is not fixed like in conventional Neural Networks and self-organizing networks that can be generated. NFPN is available effectively for multi-input variables and high-order polynomial according to the combination of NF with PNN. Accordingly it is possible to consider the nonlinearity characteristics of process and to get better output performance with superb predictive ability. In order to evaluate the performance of proposed models, we use the nonlinear function. The results show that the proposed FPNN can produce the model with higher accuracy and more robustness than any other method presented previously.

• 제어로봇시스템학회논문지
• /
• 제11권2호
• /
• pp.127-136
• /
• 2005

In this paper, a new architecture and comprehensive design methodology of genetically optimized Rule-based Fuzzy Polynomial Neural Networks(gRFPNN) are introduced and a series of numeric experiments are carried out. The architecture of the resulting gRFPNN results from asynergistic usage of the hybrid system generated by combining rule-based Fuzzy Neural Networks(FNN) with polynomial neural networks (PNN). FNN contributes to the formation of the premise part of the overall rule-based structure of the gRFPNN. The consequence part of the gRFPNN is designed using PNNs. At the premise part of the gRFPNN, FNN exploits fuzzy set based approach designed by using space partitioning in terms of individual variables and comes in two fuzzy inference forms: simplified and linear. As the consequence part of the gRFPNN, the development of the genetically optimized PNN dwells on two general optimization mechanism: the structural optimization is realized via GAs whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the gRFPNN, the models are experimented with the use of several representative numerical examples. A comparative analysis shows that the proposed gRFPNN are models with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• 대한조선학회논문집
• /
• 제40권1호
• /
• pp.69-73
• /
• 2003

Neuro-Fuzzy System is to combine merits of fuzzy inference system and neural networks. The neuro-fuzzy system applies a information about given input-output data to fuzzy theories and deals these fuzzy values with neural networks, e.g. first, redefines normalized input-output data as membership functions and then executes thses fuzzy information with backpropagation neural networks. This paper describes an innovative application of the Taguchi method for the determination of these parameters to meet the training speed and accuracy requirements. Results drawn from this research show that the Taguchi method provides an effective means to enhance the performance of the neuro-fuzzy system in terms of the speed for learning and the accuracy for recall.