• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.5
• /
• pp.744-752
• /
• 2012

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as an one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problems. In data preprocessing part, Principal Component Analysis(PCA) which is generally used in face recognition, which is useful to express some classes using reduction, since it is effective to maintain the rate of recognition and to reduce the amount of data at the same time. However, because of there of the whole face image, it can not guarantee the detection rate about the change of viewpoint and whole image. Thus, to compensate for the defects, Linear Discriminant Analysis(LDA) is used to enhance the separation of different classes. In this paper, we combine the PCA&LDA algorithm and design the optimized pRBFNNs for recognition module. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as two kinds of polynomials such as constant, and linear. The coefficients of connection weight identified with back-propagation using gradient descent method. The output of the pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to face image(ex Yale, AT&T) datasets and then demonstrated from the viewpoint of the output performance and recognition rate.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.11a
• /
• pp.366-369
• /
• 2006

본 논문에서는 계층적 공정 경쟁 유전자 알고리즘을 통한 비선형시스템의 정보입자 기반 퍼지집합 퍼지집합 모델의 최적화 방법을 제안한다. 퍼지집합 모델은 주로 전문가의 경험에 기반을 두어 얻어지기 때문에 동정과 최적화 과정이 필요하며 GAs를 이용하여 퍼지모델을 최적화한 연구가 많이 있다. GAs는 전역 해를 찾을 수 있는 최적화 알고리즘으로 잘 알려져 있지만 조기 수렴 문제를 포함하고 있다. 병렬유전자 알고리즘(PGA)은 조기수렴를 더디게 하고 전역 해를 찾기 위한 진화알고리즘이다. 적응형 계층적 공정 경쟁기반 유전자 알고리즘(AHFCGA)을 이용하여 퍼지모델의 입력변수, 멤버쉽함수의 수, 멤버쉽함수의 정점 등의 전반부 구조와 파라미터를 동정하였고, LSE를 사용하여 후반부 파라미터를 동정하였으며 실험적 예제를 통하여 제안된 방법의 성능을 평가한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2158-2165
• /
• 2007

In this paper, a Modified Fuzzy C-Means algorithm with Gaussian Weights(MFCM_GW) is presented for nonlinear blind channel equalization. The proposed algorithm searches the optimal channel output states of a nonlinear channel from the received symbols, based on the Bayesian likelihood fitness function and Gaussian weighted partition matrix instead of a conventional Euclidean distance measure. Next, the desired channel states of a nonlinear channel are constructed with the elements of estimated channel output states, and placed at the center of a Radial Basis Function(RBF) equalizer to reconstruct transmitted symbols. In the simulations, binary signals are generated at random with Gaussian noise. The performance of the proposed method is compared with those of a simplex genetic algorithm(GA), a hybrid genetic algorithm(GA merged with simulated annealing(SA): GASA), and a previously developed version of MFCM. It is shown that a relatively high accuracy and fast search speed has been achieved.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.4
• /
• pp.575-594
• /
• 2010

In this study, we propose a space search algorithm (SSA) and then introduce a hybrid optimization of fuzzy inference systems based on SSA and information granulation (IG). In comparison with "conventional" evolutionary algorithms (such as PSO), SSA leads no.t only to better search performance to find global optimization but is also more computationally effective when dealing with the optimization of the fuzzy models. In the hybrid optimization of fuzzy inference system, SSA is exploited to carry out the parametric optimization of the fuzzy model as well as to realize its structural optimization. IG realized with the aid of C-Means clustering helps determine the initial values of the apex parameters of the membership function of fuzzy model. The overall hybrid identification of fuzzy inference systems comes in the form of two optimization mechanisms: structure identification (such as the number of input variables to be used, a specific subset of input variables, the number of membership functions, and polyno.mial type) and parameter identification (viz. the apexes of membership function). The structure identification is developed by SSA and C-Means while the parameter estimation is realized via SSA and a standard least square method. The evaluation of the performance of the proposed model was carried out by using four representative numerical examples such as No.n-linear function, gas furnace, NO.x emission process data, and Mackey-Glass time series. A comparative study of SSA and PSO demonstrates that SSA leads to improved performance both in terms of the quality of the model and the computing time required. The proposed model is also contrasted with the quality of some "conventional" fuzzy models already encountered in the literature.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.13 no.11
• /
• pp.5379-5388
• /
• 2012

In fuzzy modeling for nonlinear process, the fuzzy rules are typically formed by selection of the input variables, the number of space division and membership functions. The Generation of fuzzy rules for nonlinear processes have the problem that the number of fuzzy rules exponentially increases. To solve this problem, complex nonlinear process can be modeled by generating the fuzzy rules by means of fuzzy division of input space. Therefore, in this paper, rules of non-fuzzy inference systems are generated by partitioning the input space in the scatter form using HCM clustering algorithm. The premise parameters of the rules are determined by membership matrix by means of HCM clustering algorithm. The consequence part of the rules is represented in the form of polynomial functions and the consequence parameters of each rule are identified by the standard least-squares method. And lastly, we evaluate the performance and the nonlinear characteristics using the data widely used in nonlinear process. Through this experiment, we showed that high-dimensional nonlinear systems can be modeled by a very small number of rules.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.1-7
• /
• 2009

An approach for the classification of music genres using a Fuzzy c-Means(FcM) with divergence-based kernel is proposed and presented in this paper. The proposed model utilizes the mean and covariance information of feature vectors extracted from music data and modelled by Gaussian Probability Density Function (GPDF). Furthermore, since the classifier utilizes a kernel method that can convert a complicated nonlinear classification boundary to a simpler linear one, he classifier can improve its classification accuracy over conventional algorithms. Experiments and results on collected music data sets demonstrate hat the proposed classification scheme outperforms conventional algorithms including FcM and SOM 17.73%-21.84% on average in terms of classification accuracy.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.139-142
• /
• 1997

본 논문에서는 기존 FCM(Fuzzy C-Means) 타입 클러스터링 알고리즘의 선은 향상을 위한 설계 방법을 제시한다. 우선 클러스터의 응집성(compactness)과 분리성(separation)을 동시에 고려한 성능 지수를 정의하고, 이를 진화 프로그램을 통하여 최적화 한다. 또한 실험을 통하여 기존 연구들과의 비교 및 제안된 방법론의 유효성을 보인다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.87-91
• /
• 2011

강수는 지역에 따라 발생양상이 매우 다른 자연현상 중 하나이다. 이러한 강수를 효과적으로 분석하여 확률강수량을 산정하기위해서 수문학에서는 다양한 방법이 시도되어 왔다. 우리나라에서는 지점빈도해석을 통한 확률강수량을 주로 사용해왔으나 최근 들어 Hosking and Wallis(1997)가 제안한 지역빈도해석을 활용을 적극 도모 하고 있는 중이다. 이러한 지역빈도해석 기법은 지점빈도해석 기법에 비하여 한정된 강수자료를 활용하는 측면 등 여러 가지 장점을 가진 확률 강수량 산정방법이다. 그러나 이 기법을 적용하여 확률강수량을 산정하기 위해서는 강수의 지역구분을 먼저 수행하여야 한다. 강수지역의 구분을 위해서는 여러 가지 기법이 존재하나 최근에는 Cluster 기법 중 K-means 방법이나 Fuzzy c-means 방법 등을 주로 적용하여 지역구분을 수행하고 있다. 그러나 K-means 방법이나 Fuzzy c-means 방법 등은 산정 방법내에서 최적 군집수를 결정할 수 있는 알고리즘이 없기 때문에 임의적으로 최적 군집수를 결정하여야 한다. 본 연구에서는 이러한 단점을 극복하기 위하여 Cluster 평가지수 중 하나인 Dunn 지수를 이용하여 최적 군집수를 제시하고자 한다. 본 연구에서 강수지역을 구분하기 위하여 적용한 인자는 월 평균 강수량, 연 평균 강수량, 월 최대 강수량, 경도, 위도, 고도 등이며, 이를 K-means, PAM 및 친근도 전파 기법을 통하여 강수지역을 구분하였다. 적정 군집수를 임의적으로 증가시켜 가면서 Dunn 지수를 산정하였다. 산정된 결과를 통하여 최적 군집수를 결정하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.8
• /
• pp.3689-3696
• /
• 2011

In decision support system, knowledge workers require aggregation operations of the large data and are more interested in the trend analysis rather than in the punctual analysis. Therefore, it is necessary to provide fast approximate answers rather than exact answers, and to research approximate query answering techniques. In this paper, we propose a new approximation query answering method which is based on Fuzzy C-means clustering (FCM) method and Adaptive Neuro-Fuzzy Inference System (ANFIS). The proposed method using FCM-ANFIS can compute aggregate queries without accessing massive multidimensional data cube by producing the KR model of multidimensional data cube. In our experiments, we show that our method using the KR model outperforms the NMF method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.6
• /
• pp.1070-1079
• /
• 2016

In this paper, the design of recursive radial basis function neural networks based on incremental fuzzy c-means is introduced for processing the big data. Radial basis function neural networks consist of condition, conclusion and inference phase. Gaussian function is generally used as the activation function of the condition phase, but in this study, incremental fuzzy clustering is considered for the activation function of radial basis function neural networks, which could effectively do big data processing. In the conclusion phase, the connection weights of networks are given as the linear function. And then the connection weights are calculated by recursive least square estimation. In the inference phase, a final output is obtained by fuzzy inference method. Machine Learning datasets are employed to demonstrate the superiority of the proposed classifier, and their results are described from the viewpoint of the algorithm complexity and performance index.