• 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.

• 대한전자공학회논문지SP
• /
• 제42권6호
• /
• pp.73-82
• /
• 2005

본 논문은 weighted FCM(Fuzzy C-Means) 알고리즘을 적용한 컬러 영상 multi-level thresholding을 제안한다. FCM 알고리즘은 기존의 thresholding 방법들과 달리 최적의 임계치를 결정할 수 있으며 multi-level thresholding으로의 확장이 가능하다. 그러나 공간정보를 포함하고 있지 않기 때문에 잡음 등에 민감하다는 단점을 가진다. 본 논문은 이러한 단점을 해결하기 위해서 이웃 화소들로부터 얻은 entropy 기반의 가중치(weight)를 FCM 알고리즘에 적용함으로써 잡음의 제거가 가능하다. 그리고 각 색상별 성분의 군집 화소들을 기반으로 생성한 코드 영상에 대해서 군집 내부의 거리값을 이용하여 최적의 군집수를 결정한다. 실험에서 제안한 방법이 기존의 방법들보다 잡음에 대해서 강건하며 우수한 분할 성능을 보였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권12호
• /
• pp.83-93
• /
• 2012

본 논문에서는 기존의 퍼지 클러스터링 기반 이미지 분할의 성능과 계산 효율을 개선하기 위해 퍼지 클러스터링의 목적 함수를 수정하는 이미지 분할 프레임워크를 제안한다. 제안하는 이미지 분할 프레임워크는 주변 픽셀들에 가중치를 부여함으로써 현재 센터 픽셀 연산을 위해 주변 픽셀들의 중요성을 고려하는 지역 가중치 적용 퍼지 클러스터링 기법을 포함한다. 이러한 가중치들은 각 멤버쉽들의 중요성을 표시하기 위해 현재 픽셀과 대응되는 각 주변 픽셀들 사이의 거리차에 의해 결정되어 지며, 이러한 프로세서는 향상된 클러스터링 성능을 보장한다. 제안하는 방법의 성능을 평가하기 위해 분할 계수, 분할 엔트로피, Xie-Bdni 함수, Fukuyzma-Sugeno 함수와 같은 네 가지 클러스터 유효성 함수를 이용하여 분석하였다. 모의실험 결과, 제안한 방법은 기존의 다른 퍼지 클러스터링 기법들보다 클러스터 유효성 함수들뿐만 아니라 분할과 조밀도 측면에서 우수한 성능을 보였다.

• 전기학회논문지
• /
• 제60권1호
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• 전기학회논문지
• /
• 제59권5호
• /
• pp.981-989
• /
• 2010

In this study, we introduce a new architecture of fuzzy inference system. In the fuzzy inference system, we use Fuzzy C-Means clustering algorithm to form the premise part of the rules. The membership functions standing in the premise part of fuzzy rules do not assume any explicit functional forms, but for any input the resulting activation levels of such radial basis functions directly depend upon the distance between data points by means of the Fuzzy C-Means clustering. As the consequent part of fuzzy rules of the fuzzy inference system (being the local model representing input output relation in the corresponding sub-space), four types of polynomial are considered, namely constant, linear, quadratic and modified quadratic. This offers a significant level of design flexibility as each rule could come with a different type of the local model in its consequence. Either the Least Square Estimator (LSE) or the weighted Least Square Estimator (WLSE)-based learning is exploited to estimate the coefficients of the consequent polynomial of fuzzy rules. In fuzzy modeling, complexity and interpretability (or simplicity) as well as accuracy of the obtained model are essential design criteria. The performance of the fuzzy inference system is directly affected by some parameters such as e.g., the fuzzification coefficient used in the FCM, the number of rules(clusters) and the order of polynomial in the consequent part of the rules. Accordingly we can obtain preferred model structure through an adjustment of such parameters of the fuzzy inference system. Moreover the comparative experimental study between WLSE and LSE is analyzed according to the change of the number of clusters(rules) as well as polynomial type. The superiority of the proposed model is illustrated and also demonstrated with the use of Automobile Miles per Gallon(MPG), Boston housing called Machine Learning dataset, and Mackey-glass time series dataset.

• Journal of information and communication convergence engineering
• /
• 제7권3호
• /
• pp.383-391
• /
• 2009

In this paper, blind equalization using a modified Fuzzy C-Means algorithm with Gaussian Weights (MFCM_GW) is attempted to the heavy noise-corrupted channels. The proposed algorithm can deal with both of linear and nonlinear channels, because it searches for the optimal channel output states of a channel instead of estimating the channel parameters in a direct manner. In contrast to the common Euclidean distance in Fuzzy C-Means (FCM), the use of the Bayesian likelihood fitness function and the Gaussian weighted partition matrix is exploited in its search procedure. The selected channel states by MFCM_GW are always close to the optimal set of a channel even the additive white Gaussian noise (AWGN) is heavily corrupted in it. Simulation studies demonstrate that the performance of the proposed method is relatively superior to existing genetic algorithm (GA) and conventional FCM based methods in terms of accuracy and speed.

• 융합신호처리학회논문지
• /
• 제14권3호
• /
• pp.169-180
• /
• 2013

The modification of conditional Fuzzy C-Means (CFCM) with Gaussian weights (CFCM_GW) is accomplished for blind equalization of channels in this paper. The proposed CFCM_GW can deal with both of linear and nonlinear channels, because it searches for the optimal desired states of an unknown channel in a direct manner, which is not dependent on the type of channel structure. In the search procedure of CFCM_GW, the Bayesian likelihood fitness function, the Gaussian weighted partition matrix and the conditional constraint are exploited. Especially, in contrast to the common Euclidean distance in conventional Fuzzy C-Means(FCM), the Gaussian weighted partition matrix and the conditional constraint in the proposed CFCM_GW make it more robust to the heavy noise communication environment. The selected channel states by CFCM_GW are always close to the optimal set of a channel even when the additive white Gaussian noise (AWGN) is heavily corrupted. These given channel states are utilized as the input of the Bayesian equalizer to reconstruct transmitted symbols. The simulation studies demonstrate that the performance of the proposed method is relatively superior to those of the existing conventional FCM based approaches in terms of accuracy and speed.

• 대한전자공학회논문지SP
• /
• 제43권4호
• /
• pp.1-8
• /
• 2006

본 논문은 엔트로피 기반의 가중치와 클러스터 분포크기를 이용한 향상된 FCM(Fuzzy C-Mean)알고리즘을 제안한다. FCM 알고리즘은 영상분할에서 일반적으로 많이 사용되는 퍼지 클러스터링 방법이다. 그러나 공간정보를 포함하지 않기 때문에 잡음 등에 민감하고, 클러스터를 이루는 특정들의 분포에 따라 화소들을 정확하게 분류할 수 없다. 이러한 단점을 해결하기 위해서 FCM 알고리즘의 소속정도를 연산할 때 클러스터 분포크기와 이웃 화소의 공간정보를 이용한 엔트로피 기반의 가중치를 적용한다. 실험결과에서 제안한 방법이 기존의 방법들보다 잡음에 강건하며 분할결과를 보였다.

• 한국정보전자통신기술학회논문지
• /
• 제7권3호
• /
• pp.132-136
• /
• 2014

본 논문에서는 주어진 데이터 전처리를 통한 새로운 형태의 TSK기반 퍼지 추론 시스템을 제안한다. 제안된 모델은 주어진 데이터의 효율적인 처리를 위해 클러스터링 기법인 Fuzzy C-Means 클러스터링 방법을 이용하였다. 제안된 새로운 형태의 퍼지추론 시스템의 전반부는 FCM 을 통하여 정규화된 멤버쉽 함수와 클러스터 수를 결정하기 때문에, 멤버쉽함수의 형태 및 개수를 정의할 필요가 없어, 모델의 구조 또한 간단한 형태를 이룬다. 본 논문에서 사용된 후반부는 4가지 형태로-간략추론, 1차선형추론, 2차선형추론, 변형된 2차선형추론-가 있으며, 이는 효율적인 후반부구조를 찾는데 주도적인 역할을 한다. 또한 제안된 모델의 후반부 파라미터 계수는 Weighted Least Squares Estimation(WLSE)을 사용하여 동정하며, Least Squares Estimation(LSE)를 적용한 모델의 성능과 비교한다. 마지막으로, Boston housing 데이터를 사용하여 제안된 모델의 성능을 평가하였다.

• 전기학회논문지
• /
• 제58권12호
• /
• pp.2520-2528
• /
• 2009

In this paper, we proposed tracking detection methodology using information granulation-based fuzzy radial basis function neural networks (IG-FRBFNN). According to IEC 60112, tracking device is manufactured and utilized for experiment. We consider 12 features that can be used to decide whether tracking phenomenon happened or not. These features are considered by signal processing methods such as filtering, Fast Fourier Transform(FFT) and Wavelet. Such some effective features are used as the inputs of the IG-FRBFNN, the tracking phenomenon is confirmed by using the IG-FRBFNN. The learning of the premise and the consequent part of rules in the IG-FRBFNN is carried out by Fuzzy C-Means (FCM) clustering algorithm and weighted least squares method (WLSE), respectively. Also, Hierarchical Fair Competition-based Parallel Genetic Algorithm (HFC-PGA) is exploited to optimize the IG-FRBFNN. Effective features to be selected and the number of fuzzy rules, the order of polynomial of fuzzy rules, the fuzzification coefficient used in FCM are optimized by the HFC-PGA. Tracking inference engine is implemented by using the LabVIEW and loaded into embedded system. We show the superb performance and feasibility of the tracking detection system through some experiments.