• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.1
• /
• pp.177-185
• /
• 2009

Cluster analysis or clustering is a kind of unsupervised learning method in which a set of data points is divided into a given number of homogeneous groups. Fuzzy clustering method, one of the most popular clustering method, allows a point to belong to all the clusters with different degrees, so produces more intuitive and natural clusters than hard clustering method does. Even more some of fuzzy clustering variants have noise-immunity. In this paper, we improved the Possibilistic Fuzzy C-Means (PFCM), which generates a membership matrix as well as a typicality matrix, using Gath-Geva (GG) method. The proposed method has a focus on the boundaries of clusters, which is different from most of the other methods having a focus on the centers of clusters. The generated membership values are suitable for the classification-type applications. As the typicality values generated from the algorithm have a similar distribution with the values of density function of Gaussian distribution, it is useful for Gaussian-type density estimation. Even more GG method can handle the clusters having different numbers of data points, which the other well-known method by Gustafson and Kessel can not. All of these points are obvious in the experimental results.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.4
• /
• pp.733-739
• /
• 2012

In this paper, a smoke detection algorithm robust to brightness and color variations depending on time and weather is proposed. The proposed smoke detection algorithm specifies the candidate region using difference images of input and background images, determines smoke by comparing feature coefficients of Gaussian mixture model of difference images. Thresholds for specifying candidate region is divided by four levels according to average brightness and chrominance of input images. Clusters of Gaussian mixture models of difference images are aligned according to average brightness. Smoke is determined by comparing distance of Gaussian mixture model parameters. The proposed algorithm is implemented by media dedicated DSP. As results of experiments, it is shown that the proposed algorithm is effective to detect smoke with camera installed outdoor.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.512-519
• /
• 2003

In this paper, we propose a neuro-fuzzy modeling to improve the performance using the hierarchical clustering and Gaussian Mixture Model(GMM). The hierarchical clustering algorithm has a property of producing unique parameters for the given data because it does not use the object function to perform the clustering. After optimizing the obtained parameters using the GMM, we apply them as initial parameters for Adaptive Network-based Fuzzy Inference System. Here, the number of fuzzy rules becomes to the cluster numbers. From this, we can improve the performance index and reduce the number of rules simultaneously. The proposed method is verified by applying to a neuro-fuzzy modeling for Box-Jenkins s gas furnace data and Sugeno's nonlinear system, which yields better results than previous oiles.

• The KIPS Transactions:PartA
• /
• v.13A no.3 s.100
• /
• pp.241-252
• /
• 2006

In cluster file systems, the availability of files has been supported by replicating entire files or generating parities on parity servers. However, those methods require very large temporal and spatial cost, and cannot handle massive failures situation on the file system. So we propose HA-PVFS, a cluster file system supporting high data availability adaptive to temporal locality. HA-PVFS restricts replication or parity generation to some important files, for that it employs an efficient algorithm to estimate file access patterns from limited information. Moreover, in order to minimize the performance degradation of the file system, it uses delayed update method and relay replication.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.437-442
• /
• 2005

For the purpose of speaker normalization in speaker independent speech recognition systems, experiments are conducted on a method based on Gaussian mixture model(GMM). The method, which is an improvement of the previous study based on vector quantizer, consists of modeling the probability distribution of canonical feature vectors by a GMM with an appropriate number of clusters, and of estimating the warp factor of a test speaker by making use of the obtained probabilistic model. The purpose of this study is twofold: improving the existing ML based methods, and comparing the performance of what is called 'soft decision' method with that of the previous study based on vector quantizer. The effectiveness of the proposed method is investigated by recognition experiments on the TIMIT corpus. The experimental results showed that a little improvement could be obtained tv adjusting the number of clusters in GMM appropriately.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.9-9
• /
• 2018

추계학적 강우생성모형 중 포아송 클러스터(Poisson Cluster) 모형은 단일지점에 대하여 시간강우량의 관측연한 문제점을 해결하기 위한 강우모형으로 강우 단계별 계층적 구조를 이해하는데 유용한 모형이다. 특히 강우 특성을 계절, 지역 등과 같이 비교하는 기준에 따라 5~6개의 비교적 적은 매개변수들로 모의 강우시계열을 생성할 수 있다는 점에서 장기간 강우분석에 필요한 관측연한 문제를 보완할 수 있다. 그러나 매개변수 최적해가 수렴되지 않는 사례가 많고, 매개변수들이 강우의 물리적 특성을 반영하는 것에 비해 내포된 불확실성에 관한 연구는 미흡하다. 본 연구에서는 포아송 클러스터 강우생성모형 중 Neyman-Scott Rectangular Pulse(NSRP) 모형을 Bayesian 모형과 연계한 Bayesian NSRP 모형을 개발하여 매개변수간 물리적 상관성을 고려한 최적화 기법을 개발하였다. Bayesian 모형은 물리적 범위가 다른 매개변수간의 결합확률분포를 산정하여 사후분포(posterior)를 추정하므로 매개변수 최적화와 불확실성 정량화 문제를 동시에 해결할 수 있다. 최종적으로 Bayesian NSRP 모형에 기후변화 시나리오의 통계적 특성을 고려한 시간단위 강우시계열 생성 모의 기법의 활용 가능성을 평가하고자 한다.

• Journal of Korea Multimedia Society
• /
• v.10 no.10
• /
• pp.1284-1294
• /
• 2007

In this paper, a blind nonlinear channel equalization is implemented by using a Modified Fuzzy C-Means (MFCM) algorithm. The proposed MFCM searches the optimal channel output states of a nonlinear channel from the received symbols, based on the Bayesian likelihood fitness function 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 that of a hybrid genetic algorithm (GA merged with simulated annealing (SA): GASA), and the relatively high accuracy and fast searching speed are achieved.

• The Journal of the Korea Contents Association
• /
• v.7 no.6
• /
• pp.22-30
• /
• 2007

Most real word systems such as world economy, stock market, and medical applications, contain a series of dynamic and complex phenomena. One of common methods to understand these systems is to build a model and analyze the behavior of the system. In this paper, we investigated methods for best clustering over time series data. As a first step for clustering, BIC (Bayesian Information Criterion) approximation is used to determine the number of clusters. A search technique to improve clustering efficiency is also suggested by analyzing the relationship between data size and BIC values. For clustering, two methods, model-based and similarity based methods, are analyzed and compared. A number of experiments have been performed to check its validity using real data(stock price). BIC approximation measure has been confirmed that it suggests best number of clusters through experiments provided that the number of data is relatively large. It is also confirmed that the model-based clustering produces more reliable clustering than similarity based ones.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.46-46
• /
• 2017

지역가뭄빈도분석의 분위산정에 대한 신뢰성은 수문학적으로 균일한 지역으로 구분하기 위해 사용된 장기간의 과거 자료와 분석절차에 의해 결정된다. 그러나 극심한 가뭄은 매우 드물게 발생하며 신뢰 할 수 있는 지역빈도분석을 위한 지속기간이 충분치 않는 경우가 많이 발생한다. 이 외에도 우리나라의 복잡한 지형적 및 기후적 특징은 동질한 지역으로 구분하기 위한 통계적인 처리방법이 필요하였다. 본 연구에서 적용한 지역빈도분석은 여러 지역의 다양한 변수인 수문기상 특성을 분석하여 동질한 지역을 확인하고, 주요 가뭄변수(지속 시간 및 심각도)를 통합 적용하여 각각의 동질한 지역 분위를 추정함으로써 동질한 지역을 구분하는 해결책을 제시하였다. 본 연구에서는 가우시안 혼합 모형(Gaussian Mixture Model)을 기반으로 기반 군집분석 방법을 적용하여 최적의 동질한 지역을 구분하고 그 결과를 우도비검정 및 다른 유효성 검사 지수를 이용해서 확인하였다. 가우시안 혼합 모델에서 산정했던 매개변수를 방향저감 공간으로 표현하기 위해서 가우시안 혼합 모델방향 저감(GMMDR)방법을 적용하였다. 이 변수는 가뭄빈도분석을 위해 다양한 분포와 코풀라(copula) 적합도를 이용하여 추정 비교하였다. 그 결과 우리나라를 4개의 동질한 지역으로 나누게 되었다. 가우시안과 Frank copula를 이용한 Pearson type III(PE3) 분포는 우리나라의 가뭄 기간과 심각도의 공동 분포를 추정하는데 적합한 것으로 나타났다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.8
• /
• pp.1659-1664
• /
• 2011

Fuzzy C-Means (FCM) is one of the most widely used clustering algorithms and has been used in many applications successfully. However, FCM has some shortcomings and initial prototype selection is one of them. As FCM is only guaranteed to converge on a local optimum, different initial prototype results in different clustering. Therefore, much care should be given to the selection of initial prototype. In this paper, a new initialization method for FCM using kernel density estimation (KDE) is proposed to resolve the initialization problem. KDE can be used to estimate non-parametric data distribution and is useful in estimating local density. After KDE, in the proposed method, one initial point is placed at the most dense region and the density of that region is reduced. By iterating the process, initial prototype can be obtained. The initial prototype such obtained showed better result than the randomly selected one commonly used in FCM, which was demonstrated by experimental results.