• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.7
• /
• pp.536-543
• /
• 2004

In this paper, we proposed a new method of modeling a neuro-fuzzy system using a hybrid clustering algorithm. The initial parameters and the number of clusters of the proposed system are optimally chosen simultaneously with respect to the process of regression, which is a unique characteristics of the proposed system. The proposed algorithm presented in this work improves the overall performance of the proposed a neuro-fuzzy system by choosing a proper number of clusters adaptively according the characteristics of given data. The process of clustering is performed by deciding on the number of classes, which yields the property of convergence of the system. In experiments, the superiority of the proposed neuro-fuzzy system is demonstrated, especially the process of optimizing parameters and clustering of learning speed.

• Asia pacific journal of information systems
• /
• v.16 no.1
• /
• pp.127-144
• /
• 2006

The K-means algorithm is widely used at the initial stage of data analysis in data mining process, partly because of its low time complexity and the simplicity of practical implementation. Cluster validity indices are used along with the algorithm in order to determine the number of clusters as well as the clustering results of datasets. In this paper, we present a performance comparison of sixteen indices, which are selected from forty indices in literature, while considering their applicability to nonhierarchical clustering algorithms. Data sets used in the experiment are generated based on multivariate normal distribution. In particular, four error types including standardization, outlier generation, error perturbation, and noise dimension addition are considered in the comparison. Through the experiment the effects of varying number of points, attributes, and clusters on the performance are analyzed. The result of the simulation experiment shows that Calinski and Harabasz index performs the best through the all datasets and that Davis and Bouldin index becomes a strong competitor as the number of points increases in dataset.

• The Korean Journal of Applied Statistics
• /
• v.22 no.4
• /
• pp.723-733
• /
• 2009

The crucial problems of K-means clustering are deciding the number of clusters and initial centroids of clusters. Hence, the steps of K-means clustering are generally consisted of two-stage clustering procedure. The first stage is to run hierarchical clusters to obtain the number of clusters and cluster centroids and second stage is to run nonhierarchical K-means clustering using the results of first stage. Here we provide automated K-means clustering procedure to be useful to obtain initial centroids of clusters which can also be useful for large data sets, and provide software program implemented using R.

• 한국전산유체공학회:학술대회논문집
• /
• 2003.10a
• /
• pp.9-11
• /
• 2003

A homogeneous flow field including more than 2000 spherical particles was directly simulated. Particles are settling by gravity with the Reynolds number ranging from 50 to 300, based on diameter and slip velocity. Particular attention was focused on the distribution of particles. The Reynolds-number dependence, influences of particle rotation and loading ratio, and the dynamics of particle clusters are discussed. In the higher Reynolds number case, the wake attraction causes particle clusters and the average drag coefficient decreases significantly. Non-rotating particles maintain cluster structure and rotating ones moves randomly in the horizontal direction. It is because of the difference in the direction of the lift force.

• Journal of Korea Multimedia Society
• /
• v.8 no.12
• /
• pp.1623-1630
• /
• 2005

Adaptive modulation and coding (AMC), which has a number of variation levels in accordance with the fading channel variation, is a promising technique for communication systems. In this paper, we present an AMC method using the cluster in OFDM system for bandwidth efficiency and performance improvement. The AMC schemes applied into each cluster or some clusters are determined by the minimum or the average SNR value among all the sub carriers within the corresponding cluster. It is important to find the optimal information on cluster because AMC performance can be varied according to the number and position of cluster. It is shown by computer simulation that the AMC method outperforms the fixed modulation in terms of bandwidth efficiency and its performance can be determined by the position and number of clusters.

• Nuclear Engineering and Technology
• /
• v.56 no.6
• /
• pp.2071-2078
• /
• 2024

The precipitation of solutes is a major cause of irradiation hardening and embrittlement limiting the service life of reactor pressure vessel (RPV) steels. Impurities play a significant role in the formation of precipitation in RPV materials. In this study, the effects of carbon on cluster formation and irradiation hardening were investigated in an RPV alloy Fe-1.35Mn-0.75Ni using C and Fe ions irradiation at 290 ℃. Nanoindentation results showed that C ion irradiation led to less hardening below 1.0 dpa, with hardening continuing to increase gradually at higher doses, while it was saturated under Fe ion irradiation. Atom probe tomography revealed a broad size distribution of Ni-Mn clusters under Fe ion irradiation, contrasting a narrower size distribution of small Ni-Mn clusters under C ion irradiation. Further analysis indicated the influence of carbon on the cluster formation, with solute-precipitated defects dominating under C ion irradiation but interstitial clusters dominating under Fe ion irradiation. Simulations suggested that carbon significantly affected solute nucleation, with defect clusters displaying smaller size and higher density as carbon concentration increased. The higher hardening at doses above 1.0 dpa was attributed to a substantial increase in the number density of defect clusters when carbon was present in the matrix.

• The Journal of Information Systems
• /
• v.26 no.4
• /
• pp.227-246
• /
• 2017

Purpose: As the importance of software has been emphasized recently, the size of the software market is continuously expanding. The development of the software market is being adversely affected by software piracy. In this study, we try to classify countries around the world based on the macro environmental factors, which influence software piracy. We also try to identify the differences in software piracy for each classified type. Design/methodology/approach: The data-driven approach is used in this study. From the BSA, the World Bank, and the OECD, we collect data from 1990 to 2015 for 127 environmental variables of 225 countries. Cronbach's ${\alpha}$ analysis, item-to-total correlation analysis, and exploratory factor analysis derive 15 constructs from the data. We apply two-step approach to cluster analysis. The number of clusters is determined to be 5 by hierarchical cluster analysis at the first step, and the countries are classified by the K-means clustering at the second step. We conduct ANOVA and MANOVA in order to verify the differences of the environmental factors and software piracy among derived clusters. Findings: The five clusters are identified as underdeveloped countries, developing countries, developed countries, world powers, and developing country with large market. There are statistically significant differences in the environmental factors among the clusters. In addition, there are statistically significant differences in software piracy rate, pirated value, and legal software sales among the clusters.

• The KIPS Transactions:PartA
• /
• v.19A no.3
• /
• pp.129-138
• /
• 2012

In distributed memory architectures like clusters, each node stores a portion of data. How data is distributed across nodes influences the performance of such systems. The data distribution scheme is the strategy to distribute data across nodes and realize parallel data processing. Due to various reasons such as maintenance, scale up, upgrade, etc., the performance of nodes in a cluster can often become non-identical. In such clusters, data distribution without considering performance cannot efficiently distribute data on nodes. In this paper, we propose a new data distribution scheme based on the number of cores in nodes. We use the number of cores as the performance factor. In our data distribution scheme, each node is allocated an amount of data proportional to the number of cores in it. We implement our data distribution scheme using the Chapel language. To show our data distribution is effective in reducing the execution time of parallel applications, we implement Mandelbrot Set and ${\pi}$-Calculation programs with our data distribution scheme, and compare the execution times on a cluster. Based on experimental results on clusters of 8-core and 16-core nodes, we demonstrate that data distribution based on the number of cores can contribute to a reduction in the execution times of parallel programs on clusters.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.54.3-54.3
• /
• 2019

During the formation of large-scale structures in the universe, shocks with the sonic Mach number Ms <~ 5 are naturally induced by supersonic flow motions of baryonic matter in the intracluster medium (ICM). Cosmic rays (CRs) are expected to be accelerated via diffusive shock acceleration (DSA) at these ICM shocks, although the existence of CR protons in the ICM remains to be confirmed through gamma-ray observations. Based on the results obtained from kinetic plasma simulations, we build an analytic DSA model for weak, quasi-parallel shocks in the test-particle regime. With our DSA model, the CR acceleration efficiency ranges ~ 0.001 - 0.02 in supercritical quasi-parallel shocks with sonic Mach number Ms ~ 2.25 - 5, and the acceleration would be negligible in subcritical shocks wth Ms <~ 2.25. Adopting our DSA model, we estimate gamma-ray and neutrino emissions from clusters of galaxies by performing cosmological hydrodynamic simulations. The estimated gamma-ray flux is below the Fermi-LAT upper limit. In addition, the possible neutrino emission due to the decay of charged pions in galaxy clusters would be about <~ 1% of the atmospheric neutrino intensity in the energy range of <~ 100 GeV. In this talk, we will discuss the implication of our results.

• Journal of Korean Society for Quality Management
• /
• v.39 no.1
• /
• pp.98-108
• /
• 2011

Clustering is an useful method to classify objects into subsets that have some meaning in the context of a particular problem and has been applied in variety of fields, customer relationship management, data mining, pattern recognition, and biotechnology etc. This paper addresses the unknown K clustering problems and presents a new approach based on a coevolutionary algorithm to solve it. Coevolutionary algorithms are known as very efficient tools to solve the integrated optimization problems with high degree of complexity compared to classical ones. The problem considered in this paper can be divided into two sub-problems; finding the number of clusters and classifying the data into these clusters. To apply to coevolutionary algorithm, the framework of algorithm and genetic elements suitable for the sub-problems are proposed. Also, a neighborhood-based evolutionary strategy is employed to maintain the population diversity. To analyze the proposed algorithm, the experiments are performed with various test-bed problems which are grouped into several classes. The experimental results confirm the effectiveness of the proposed algorithm.