• 전기학회논문지
• /
• 제57권11호
• /
• pp.2108-2116
• /
• 2008

The paper concerns Fuzzy C-Means clustering based Radial Basis Function neural networks (FCM-RBFNN) and the optimization of the network is carried out by means of Particle Swarm Optimization(PSO). FCM-RBFNN is the extended architecture of Radial Basis Function Neural Network(RBFNN). In the proposed network, the membership functions of the premise part of fuzzy rules do not assume any explicit functional forms such as Gaussian, ellipsoidal, triangular, etc., so its resulting fitness values directly rely on the computation of the relevant distance between data points by means of FCM. Also, as the consequent part of fuzzy rules extracted by the FCM - RBFNN model, the order of four types of polynomials can be considered such as constant, linear, quadratic and modified quadratic. Weighted Least Square Estimator(WLSE) are used to estimates the coefficients of polynomial. Since the performance of FCM-RBFNN is affected by some parameters of FCM-RBFNN such as a specific subset of input variables, fuzzification coefficient of FCM, the number of rules and the order of polynomials of consequent part of fuzzy rule, we need the structural as well as parametric optimization of the network. In this study, the PSO is exploited to carry out the structural as well as parametric optimization of FCM-RBFNN. Moreover The proposed model is demonstrated with the use of numerical example and gas furnace data set.

• 한국전기전자재료학회논문지
• /
• 제18권1호
• /
• pp.1-5
• /
• 2005

A new model of plasma etch process was constructed by using a radial basis function network (RBFN). This technique was applied to an etching of silicon carbide films in a NF$_3$ inductively coupled plasma. Experimental data to train RBFN were systematically collected by means of a 2$^4$ full factorial experiment. Appropriateness of prediction models was tested with test data consisted of 16 experiments not pertaining to the training data. Prediction performance was optimized with variations in three training factors, the number of pattern units, width of radial basis function, and initial weight distribution between the pattern and output layers. The etch responses to model were an etch rate and a surface roughness measured by atomic force microscopy. Optimized models had the root mean-squared errors of 26.1 nm/min and 0.103 nm for the etch rate and surface roughness, respectively. Compared to statistical regression models, RBFN models demonstrated an improvement of more than 20 % and 50 % for the etch rate and surface roughness, respectively. It is therefore expected that RBFN can be effectively used to construct prediction models of plasma processes.

• 한국콘텐츠학회논문지
• /
• 제5권6호
• /
• pp.41-48
• /
• 2005

이 논문은 얼굴인식을 수행하기 위해서 이미 잘 알려진 주성분 분석법과 선형판별 분석법에 레이디얼 기저 함수 신경망을 결합한 인식 알고리즘을 제시하였다. 입력된 원래의 얼굴영상은 주성분분석법을 통하여 차원을 줄인 고유 얼굴 가중치를 산출한다. 이 가중치 벡터를 선형판별 분석법의 입력데이터로 사용하여 선형판별분석의 변환행렬을 계산할 때 클래스 내의 분산행렬에서 특이점이 발생하지 않도록 하면서 특징벡터를 산출하여 인식을 수행하였다. 두 번째 시도에서는 선형판별분석법에 의해 생성된 특징벡터를 레이디얼 기저 함수 신경망에 입력하여 학습하고 얼굴인식을 수행하였다. ORL DB의 얼굴영상에 대해 실험한 결과 93.5%의 인식률을 얻을 수 있었다.

• 한국멀티미디어학회논문지
• /
• 제3권3호
• /
• pp.253-262
• /
• 2000

본 논문에서는 적응적으로 추출된 입력 데이터의 특징을 은닉층 뉴런 개수와 중심값 설정에 이용하는 새로운 radial basis 함수 신경망을 제안하였다. 제안된 신경망에서는 입력데이터의 특징을 효과적으로 추출하기 위해 적응 학습알고리즘의 주요성분분석 기법을 이용하였다. 이렇게 하면 주요성분분석 기법이 가지는 대용량의 입력데이터를 통계적으로 독립인 특징들의 집합으로 변환시키는 장점과 RBF신경망이 가지는 우수한 속성을 그대로 살릴 수 있다. 제안된 기법의 radial basis 함수 신경망을 200명의 암환자를 2부류(초기와 악성)로 분류하는 문제에 적용하여 시뮬레이션한 결과, k-평균 군집화 알고리즘을 이용한 radial basis 함수 신경망에 의한 결과와 비교할 때 학습시간과 시험 데이터의 분류에서 더욱 우수한 성능이 있음을 확인할 수 있었다. 그리고 신경망의 초기 연 결가중치에 대한 의존도와 평활요소의 설정여유도 측면에서도 우수한 특성이 있음을 확인할 수 있었다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.420-420
• /
• 2000

In this paper, we propose an adaptive controller using RBFN(radial basis function network) for robot manipulators The structure of the proposed controller consists of a RBFN and VSC-1 ike control. RBFN is used in order to approximate かon system, and VSC-like control to guarantee robustness On the basis of the Lyapunov stability theorem, we guarantee the stability for the total system. And the learning law of RBFN is established by the Lyapunov method, Finally, we apply the proposed controller to tracking control for a 2 link SCARA type robot manipulator.

• 산업경영시스템학회지
• /
• 제36권4호
• /
• pp.59-63
• /
• 2013

In biomass gasification, efficiency of energy quantification is a difficult part without finishing the process. In this article, a radial basis function neural network (RBFN) is proposed to predict biomass efficiency before gasification. RBFN will be compared with a principal component regression (PCR) and a multilayer perceptron neural network (MLPN). Due to the high dimensionality of data, principal component transform is first used in PCR and afterwards, ordinary regression is applied to selected principal components for modeling. Multilayer perceptron neural network (MLPN) is also used without any preprocessing. For this research, 3 wood samples and 3 other feedstock are used and they are near infrared (NIR) spectrum data with high-dimensionality. Ash and char are used as response variables. The comparison results of two responses will be shown.

• 한국유체기계학회 논문집
• /
• 제12권3호
• /
• pp.7-12
• /
• 2009

In this paper, shape optimization based on three-dimensional flow analysis has been performed for impeller design of centrifugal compressor. To evaluate the objective function of an isentropic efficiency, Reynolds-averaged Navier-Stokes equations are solved with SST (Shear Stress Transport) turbulence model. The governing equations are discretized by finite volume approximations. The optimization techniques based on the radial basis neural network method are used for the optimization. Latin hypercube sampling as design of experiments is used to generate thirty design points within design space. Sequential quadratic programming is used to search the optimal point based on the radial basis neural network model. Four geometrical variables concerning impeller shape are selected as design variables. The results show that the isentropic efficiency is enhanced effectively from the shape optimization by the radial basis neural network method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2011년도 제42회 하계학술대회
• /
• pp.1964-1965
• /
• 2011

본 연구에서는 패턴분류를 위해 기존의 방사형 기저 함수 신경회로망(Radial Basis Funtion Neural Network)과 다항식 신경회로망(Polynomial Neural Network)을 결합한 다중 출력 방사형 기저 함수다항식 신경회로망 (Multi Output Radial Basis Funtion Polynomial Neural Network)의 분류기를 제안한다. 제안된 모델은 PNN을 기본 구조로 하여 1층에 기존의 다항식 노드 대신 다중 출력 형태의 RBFNN을 적용 한다. RBFNN의 은닉층에는 기존의 활성함수가 아닌 fuzzy 클러스터링을 사용하여 입력 데이터의 특성을 고려한 적합도를 사용하였다. PNN은 입력변수의 수와 다항식 차수가 모델의 성능을 결정함으로 최적화가 필요하며 본 논문에서는 Differential Evolution(DE)을 사용하여 모델의 구조 및 파라미터를 최적화시켜 모델의 성능을 향상시켰다. 패턴분류기로써의 제안된 모델을 평가하기 위해 pima 데이터를 이용하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 춘계학술대회 논문집 전기기기 및 에너지변환시스템부문
• /
• pp.162-164
• /
• 2007

This paper presents a "window-zoom-out" optimization strategy with relatively fewer sampling data. In this method, an optimal Latin hypercube sampling experiment based on multi-objective Pareto optimization is developed to obtain the sampling data. The response surface method with multiquadric radial basis function combined with (1+$\lambda$) evolution strategy is used to find the global optimal point. The proposed method is verified with numerical experiments.

• Journal of Communications and Networks
• /
• 제12권6호
• /
• pp.600-604
• /
• 2010

A method of width adaptation in the radial basis function network (RBFN) using stochastic gradient (SG) algorithm is introduced. Using Taylor's expansion of error signal and differentiating the error with respect to the step-size, the optimal time-varying step-size of the width in RBFN is derived. The proposed approach to adjusting widths in RBFN achieves superior learning speed and the steady-state mean square error (MSE) performance in nonlinear channel environment. The proposed method has shown enhanced steady-state MSE performance by more than 3 dB in both nonlinear channel environments. The results confirm that controlling over step-size of the width in RBFN by the proposed algorithm can be an effective approach to enhancement of convergence speed and the steady-state value of MSE.