• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2891-2893
• /
• 2005

In this paper, we introduce a new category of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multi-layer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization. The conventional SOFPNN algorithm leads to a tendency to produce overly complex networks as well as a repetitive computation load by the trial and error method and/or the a repetitive parameter adjustment by designer. In order to generate a structurally and parametrically optimized network, such parameters need to be optimal. In this study, in solving the problems with the conventional SOFPNN, we introduce a new design approach of evolutionary optimized SOFPNN. Optimal parameters design available within FPN (viz. the no. of input variables, the order of the polynomial, input variables, and the no. of membership function) lead to structurally and parametrically optimized network which is more flexible as well as simpler architecture than the conventional SOFPNN. In addition, we determine the initial apexes of membership functions by genetic algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.4
• /
• pp.883-889
• /
• 2005

Error backpropagation algorithm of multilayer perceptron may result in local-minima because of the insufficient nodes in the hidden layer, inadequate momentum set-up, and initial weights. In this paper, we proposed the ART-1 based fuzzy supervised learning algorithm which is composed of ART-1 and fuzzy single layer supervised learning algorithm. The Proposed fuzzy supervised learning algorithm using self-generation method applied not only ART-1 to creation of nodes from the input layer to the hidden layer, but also the winer-take-all method, modifying stored patterns according to specific patterns. to adjustment of weights. We have applied the proposed learning method to the problem of recognizing a resident registration number in resident cards. Our experimental result showed that the possibility of local-minima was decreased and the teaming speed and the paralysis were improved more than the conventional error backpropagation algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.4
• /
• pp.862-870
• /
• 2011

In this paper, we introduce a new topology of Radial Basis Function-based Polynomial Neural Networks (RPNN) that is based on a genetically optimized multi-layer perceptron with Radial Polynomial Neurons (RPNs). This study offers a comprehensive design methodology involving mechanisms of optimization algorithms, especially Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization (PSO) algorithms. In contrast to the typical architectures encountered in Polynomial Neural Networks (PNNs), our main objective is to develop a design strategy of RPNNs as follows : (a) The architecture of the proposed network consists of Radial Polynomial Neurons (RPNs). In here, the RPN is fully reflective of the structure encountered in numeric data which are granulated with the aid of Fuzzy C-Means (FCM) clustering method. The RPN dwells on the concepts of a collection of radial basis function and the function-based nonlinear (polynomial) processing. (b) The PSO-based design procedure being applied at each layer of RPNN leads to the selection of preferred nodes of the network (RPNs) whose local characteristics (such as the number of input variables, a collection of the specific subset of input variables, the order of the polynomial, and the number of clusters as well as a fuzzification coefficient in the FCM clustering) can be easily adjusted. The performance of the RPNN is quantified through the experimentation where we use a number of modeling benchmarks - NOx emission process data of gas turbine power plant and learning machine data(Automobile Miles Per Gallon Data) already experimented with in fuzzy or neurofuzzy modeling. A comparative analysis reveals that the proposed RPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• Journal of Korea Multimedia Society
• /
• v.2 no.4
• /
• pp.490-495
• /
• 1999

In this paper, a method of improving the learning time and convergence rate is proposed to exploit the advantages of artificial neural networks and fuzzy theory to neuron structure. This method is applied to the XOR Problem, n bit parity problem which is used as the benchmark in neural network structure, and recognition of digit image in the vehicle plate image for practical image application. As a result of the experiments, it does not always guarantee the convergence. However, the network showed improved the teaming time and has the high convergence rate. The proposed network can be extended to an arbitrary layer Though a single layer structure Is considered, the proposed method has a capability of high speed 3earning even on large images.

• Korean Journal of Cognitive Science
• /
• v.14 no.4
• /
• pp.33-42
• /
• 2003

This paper presents a new system for facial expression recognition based in dimension model of internal states. The information of facial expression are extracted to the three steps. In the first step, Gabor wavelet representation extracts the edges of face components. In the second step, sparse features of facial expressions are extracted using fuzzy C-means(FCM) clustering algorithm on neutral faces, and in the third step, are extracted using the Dynamic Model(DM) on the expression images. Finally, we show the recognition of facial expression based on the dimension model of internal states using a multi-layer perceptron. The two dimensional structure of emotion shows that it is possible to recognize not only facial expressions related to basic emotions but also expressions of various emotion.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.6 no.1
• /
• pp.64-69
• /
• 2006

Due to the inherent nonlinear nature of Electro-rheological (ER) fluid dampers, one of the challenging aspects for utilizing these devices to achieve high system performance is the development of accurate models and control algorithms that can take advantage of their unique characteristics. In this paper, the nonlinear damping force model is made to identify the properties of the ER damper using higher order spectrum. The higher order spectral analysis is used to investigate the nonlinear frequency coupling phenomena with the damping force signal according to the sinusoidal excitation of the damper. Also, this paper presents an inverse model of the ER damper, i.e., the model can predict the required voltage so that the ER damper can produce the desired force for the requirement of vibration control of vehicle suspension systems. The inverse model is constructed by using a multi-layer perceptron neural network. A quarter-car suspension model is considered in this paper for analysis and simulation. Simulation results show that the proposed inverse model of ER damper can obtain control voltage of ER damper for required damping force.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.1
• /
• pp.447-452
• /
• 2005

기존의 단층 퍼셉트론은 출력 노드가 선형 분리 가능한 패턴들만을 분류할 수 있고 Exclusive OR와 같은 비선형 문제에 대해서는 분류할 수 없는 단점이 있다. 그러나 퍼지 단층 퍼셉트론은 퍼지소속 함수(fuzzy membership function)를 적용하여 단층 구조로 Exclusive OR 문제와 같은 고전적인 문제를 개선하였다. 그러나 퍼지 단층 퍼셉트론은 기존의 단층 퍼셉트론과 마찬가지로 결정 경계선이 진동하는 경우가 생기며 초기 가중치의 범위와 학습률에 따라 수렴성이 매우 낮아지는 단점이 있다. 따라서 본 논문에서는 바이어스항을 도입하여 결정 경계선이 진동하는 것을 방지하여 수렴성을 개선시키고 선형 활성화 함수를 제안하고 학습률과 모멘텀 개념을 도입하여 학습 시간을 단축시키는 개선된 퍼지 단층 퍼셉트론 알고리즘을 제안한다. 제안된 방법과 퍼지 단층 퍼셉트론간의 학습 성능을 분석하기 위하여 인공 신경망에서 벤치마크로 사용되는 exclusive OR 문제와 문자 패턴 분류에 적용하여 epoch 수와 수렴성을 비교한 결과, 제안된 방법이 기존의 퍼지 단층 퍼셉트론보다 학습 시간이 적게 소요되고 수렴성이 개선된 것을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2003.07d
• /
• pp.2519-2521
• /
• 2003

In this paper, we propose Self-Organizing Fuzzy Polynomial Neural Networks(SOFPNN) architecture for optimal model identification and discuss a comprehensive design methodology supporting its development. It is shown that this network exhibits a dynamic structure as the number of its layers as well as the number of nodes in each layer of the SOFPNN are not predetermined (as this is the case in a popular topology of a multilayer perceptron). As the form of the conclusion part of the rules, especially the regression polynomial uses several types of high-order polynomials such as linear, quadratic, and modified quadratic. As the premise part of the rules, both triangular and Gaussian-like membership function are studied and the number of the premise input variables used in the rules depends on that of the inputs of its node in each layer. We introduce two kinds of SOFPNN architectures, that is, the basic and modified one with both the generic and the advanced type. The superiority and effectiveness of the proposed SOFPNN architecture is demonstrated through nonlinear function numerical example.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.2
• /
• pp.96-101
• /
• 2007

Neural networks are known as kinds of intelligent strategies since they have learning capability. There are various their applications from intelligent control fields; however, their applications have limits from the point that the stability of the intelligent control systems is not usually guaranteed. In this paper we propose an adaptive tracking control for robot manipulators using the radial basis function network (RBFN) that is e. kind of neural networks. Adaptation laws for parameters of the RBFN are developed based on the Lyapunov stability theory to guarantee the stability of the overall control scheme. Filtered tracking errors between actual outputs and desired outputs are discussed in the sense of the uniformly ultimately boundedness(UUB). Additionally, it is also shown that parameters of the RBFN are bounded. Experimental results for a SCARA-type robot manipulator show that the proposed adaptive tracking controller is adaptable to the environment changes and is more robust than the conventional PID controller and the neuro-controller based on the multilayer perceptron.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.10 no.4
• /
• pp.314-318
• /
• 2010

Predicting Alpha-helicies, Beta-sheets and Turns of a proteins secondary structure is a complex non-linear task that has been approached by several techniques such as Neural Networks, Genetic Algorithms, Decision Trees and other statistical or heuristic methods. This project introduces a new machine learning method by combining Bayesian Inference with offline trained Multilayered Perceptron (MLP) models as the likelihood for secondary structure prediction of proteins. With varying window sizes of neighboring amino acid information, the information is extracted and passed back and forth between the Neural Net and the Bayesian Inference process until the posterior probability of the secondary structure converges.