• Proceedings of the KIEE Conference
• /
• 2003.07a
• /
• pp.552-554
• /
• 2003

The second harmonic component is commonly used for blocking differential relay in power transformers. However, it is difficult to distinguish between inrush and internal winding fault with differential current protective relaying. This paper proposed a new method using Nuro-Fuzzy System based on HCM(Hard C-Means). The proposed system is more objective and systematic than existing model. The data used in input are 3-phase primary voltage and fundamental harmonic of differential current. Various states of transformer are simulated using BCTRAN and HYSDAT of EMTP. As a result of the application of algorithm in various cases, the exact discrimination between internal winding fault and inrush is performed.

• Proceedings of the KIEE Conference
• /
• 2007.10a
• /
• pp.405-406
• /
• 2007

본 논문에서는 FCM 기반 퍼지 뉴럴네트워크 구조를 제안하고 진화 알고리즘을 이용한 FCM 기반 퍼지 뉴럴네트워크의 구조와 파라미터의 최적화 방법을 제시한다. 클러스터링 알고리즘은 퍼지 뉴럴 네트워크에서 멤버쉽함수의 중심점과 반경 등을 결정하는 학습에 일반적으로 사용된다. 제안된 FCM 기반 뉴럴 네트워크에서 멤버쉽함수는 가우시안, 삼각형 타입등의 정해진 형태를 사용하지 않고 데이터들 사이의 거리에 관계된 계산을 수행하는 FCM에 의해 결정된다. 후반부는 상수형, 선형, 2차식 등의 다양한 다항식 구조로 표현될 수 있으며 다항식의 계수는 LSE를 이용하여 결정한다. FCM 기반 퍼지 뉴럴 네트워크는 퍼지규칙의 수, 입력변수의 선택, 후반부 다항식의 차수, FCM의 퍼지화 계수의 결정은 성능에 많은 차이가 있으며 이러한 구조와 파라미터의 최적화가 요구된다. 본 논문에서는 유전자 알고리즘을 이용하여 FCM 기반 퍼지뉴럴네트워크의 구조에 관련된 입력변수의 수, 퍼지규칙의 수 그리고 후반부 다항식의 차수와 파라미터에 관련된 퍼지화 계수를 최적화 한다. 제안된 방법은 비선형 시스템의 모델링에 적용하여 성능을 분석하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.757-759
• /
• 2003

암의 치료법은 같은 종류의 암이라 해도 그 하부 클래스에 따라 매우 다르기 때문에 암의 클래스를 예측하는 것은 그 정확한 치료를 위하여 매우 중요하다. 유전자 발현 데이터를 이용한 암의 분류에 있어 기존의 연구들은 각 데이터를 하나의 클러스터에 소속시키는 하드 분할(hard partition)에 의한 분할 방식을 사용하는 하드 클러스터링을 사용하였다. 하지만 일반적으로 유전자 발현 암 데이터와 같은 실세계의 데이터는 쉽게 나뉘어지기 힘들거나 클러스터 간의 경계가 분명하지 않기 때문에 하드 클러스터링 기법은 주어진 데이터의 성질을 손실시킬 수 있는데 반해, 퍼지 클러스터링 기법은 각 데이터가 소속 정도에 따라 여러 개의 클러스터에 속할 수 있도록 분할하기 때문에 이러한 손실을 최소화할 수 있다. 따라서 본 논문에서는 퍼지 클러스터링의 대표적인 방법인 fuzzy c-means 클러스터링을 적용하여 암의 클래스를 예측하고, 다양한 하드 클러스터링 방법과 비교함으로써 퍼지 클러스터링의 성능을 검증하였다.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2388-2398
• /
• 2017

In this study, we propose a robust face recognition system to pose variations based on automatic pose estimation. Radial basis function neural network is applied as one of the functional components of the overall face recognition system. The proposed system consists of preprocessing and recognition modules to provide a solution to pose variation and high-dimensional pattern recognition problems. In the preprocessing part, principal component analysis (PCA) and 2-dimensional 2-directional PCA ($(2D)^2$ PCA) are applied. These functional modules are useful in reducing dimensionality of the feature space. The proposed RBFNNs architecture consists of three functional modules such as condition, conclusion and inference phase realized in terms of fuzzy "if-then" rules. In the condition phase of fuzzy rules, the input space is partitioned with the use of fuzzy clustering realized by the Fuzzy C-Means (FCM) algorithm. In conclusion phase of rules, the connections (weights) are realized through four types of polynomials such as constant, linear, quadratic and modified quadratic. The coefficients of the RBFNNs model are obtained by fuzzy inference method constituting the inference phase of fuzzy rules. The essential design parameters (such as the number of nodes, and fuzzification coefficient) of the networks are optimized with the aid of Particle Swarm Optimization (PSO). Experimental results completed on standard face database -Honda/UCSD, Cambridge Head pose, and IC&CI databases demonstrate the effectiveness and efficiency of face recognition system compared with other studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.62 no.4
• /
• pp.544-553
• /
• 2013

In this paper, we propose the pattern classifier of Radial Basis Function Neural Networks(RBFNNs) for diagnosis of 3-phase partial discharge. Conventional methods map the partial discharge/noise data on 3-PARD map, and decide whether the partial discharge occurs or not from 3-phase or neutral point. However, it is decided based on his own subjective knowledge of skilled experter. In order to solve these problems, the mapping of data as well as the classification of phases are considered by using the general 3-PARD map and PA method, and the identification of phases occurring partial discharge/noise discharge is done. In the sequel, the type of partial discharge occurring on arbitrary random phase is classified and identified by fuzzy clustering-based polynomial Radial Basis Function Neural Networks(RBFNN) classifier. And by identifying the learning rate, momentum coefficient, and fuzzification coefficient of FCM fuzzy clustering with the aid of PSO algorithm, the RBFNN classifier is optimized. The virtual simulated data and the experimental data acquired from practical field are used for performance estimation of 3-phase partial discharge pattern classifier.

• Structural Engineering and Mechanics
• /
• v.44 no.2
• /
• pp.179-196
• /
• 2012

An eigenspace projection clustering method is proposed for structural damage detection by combining projection algorithm and fuzzy clustering technique. The integrated procedure includes data selection, data normalization, projection, damage feature extraction, and clustering algorithm to structural damage assessment. The frequency response functions (FRFs) of the healthy and the damaged structure are used as initial data, median values of the projections are considered as damage features, and the fuzzy c-means (FCM) algorithm are used to categorize these features. The performance of the proposed method has been validated using a three-story frame structure built and tested by Los Alamos National Laboratory, USA. Two projection algorithms, namely principal component analysis (PCA) and kernel principal component analysis (KPCA), are compared for better extraction of damage features, further six kinds of distances adopted in FCM process are studied and discussed. The illustrated results reveal that the distance selection depends on the distribution of features. For the optimal choice of projections, it is recommended that the Cosine distance is used for the PCA while the Seuclidean distance and the Cityblock distance suitably used for the KPCA. The PCA method is recommended when a large amount of data need to be processed due to its higher correct decisions and less computational costs.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.516-527
• /
• 2013

This paper presents a new overall system for state-of-available-power (SoAP) prediction for a lithium-ion battery pack. The essential part of this method is based on an adaptive network architecture which utilizes both fuzzy model (FIS) and artificial neural network (ANN) into the framework of adaptive neuro-fuzzy inference system (ANFIS). While battery aging proceeds, the system is capable of delivering accurate power prediction not only for room temperature, but also at lower temperatures at which power prediction is most challenging. Due to design property of ANN, the network parameters are adapted on-line to the current battery states (state-of-charge (SoC), state-of-health (SoH), temperature). SoC is required as an input parameter to SoAP module and high accuracy is crucial for a reliable on-line adaptation. Therefore, a reasonable way to determine the battery state variables is proposed applying a combination of several partly different algorithms. Among other SoC boundary estimation methods, robust extended Kalman filter (REKF) for recalibration of amp hour counters was implemented. ANFIS then achieves the SoAP estimation by means of time forward voltage prognosis (TFVP) before a power pulse occurs. The trade-off between computational cost of batch-learning and accuracy during on-line adaptation was optimized resulting in a real-time system with TFVP absolute error less than 1%. The verification was performed on a software-in-the-loop test bench setup using a 53 Ah lithium-ion cell.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.970-976
• /
• 2007

In this study, Polynomial Network Pattern Classifier(PNC) based on Fuzzy Inference Mechanism is designed and its parameters such as learning rate, momentum coefficient and fuzzification coefficient are optimized by means of Particle Swarm Optimization. The proposed PNC employes a partition function created by Fuzzy C-means(FCM) clustering as an activation function in hidden layer and polynomials weights between hidden layer and output layer. Using polynomials weights can help to improve the characteristic of the linear classification of basic neural networks classifier. In the viewpoint of linguistic analysis, the proposed classifier is expressed as a collection of "If-then" fuzzy rules. Namely, architecture of networks is constructed by three functional modules that are condition part, conclusion part and inference part. The condition part relates to the partition function of input space using FCM clustering. In the conclusion part, a polynomial function caries out the presentation of a partitioned local space. Lastly, the output of networks is gotten by fuzzy inference in the inference part. The proposed PNC generates a nonlinear discernment function in the output space and has the better performance of pattern classification as a classifier, because of the characteristic of polynomial based fuzzy inference of PNC.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.1
• /
• pp.149-160
• /
• 1997

This paper is concerned with the problem of speaker-adaptive speech synthes is method using a mapped codebook designed by fuzzy mapping on FLVQ (Fuzzy Learning Vector Quantization). The FLVQ is used to design both input and reference speaker's codebook. This algorithm is incorporated fuzzy membership function into the LVQ(learning vector quantization) networks. Unlike the LVQ algorithm, this algorithm minimizes the network output errors which are the differences of clas s membership target and actual membership values, and results to minimize the distances between training patterns and competing neurons. Speaker Adaptation in speech synthesis is performed as follow;input speaker's codebook is mapped a reference speaker's codebook in fuzzy concepts. The Fuzzy VQ mapping replaces a codevector preserving its fuzzy membership function. The codevector correspondence histogram is obtained by accumulating the vector correspondence along the DTW optimal path. We use the Fuzzy VQ mapping to design a mapped codebook. The mapped codebook is defined as a linear combination of reference speaker's vectors using each fuzzy histogram as a weighting function with membership values. In adaptive-speech synthesis stage, input speech is fuzzy vector-quantized by the mapped codcbook, and then FCM arithmetic is used to synthesize speech adapted to input speaker. The speaker adaption experiments are carried out using speech of males in their thirties as input speaker's speech, and a female in her twenties as reference speaker's speech. Speeches used in experiments are sentences /anyoung hasim nika/ and /good morning/. As a results of experiments, we obtained a synthesized speech adapted to input speaker.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.99-106
• /
• 2015

In this study, we propose Radial basis function Neural Network(RBFNN) using Recursive Weighted Least Square Estimation(RWLSE) to effectively deal with big data class meteorological radar data. In the condition part of the RBFNN, Fuzzy C-Means(FCM) clustering is used to obtain fitness values taking into account characteristics of input data, and connection weights are defined as linear polynomial function in the conclusion part. The coefficients of the polynomial function are estimated by using RWLSE in order to cope with big data. As recursive learning technique, RWLSE which is based on WLSE is carried out to efficiently process big data. This study is experimented with both widely used some Machine Learning (ML) dataset and big data obtained from meteorological radar to evaluate the performance of the proposed classifier. The meteorological radar data as big data consists of precipitation echo and non-precipitation echo, and the proposed classifier is used to efficiently classify these echoes.