• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.481-486
• /
• 2021

Machine learning algorithms adopt criterion function as a key component to measure the quality of their model derived from data. Cluster analysis also uses this function to rate the clustering result. All the criterion functions have in general certain types of favoritism in producing high quality clusters. These clusters are then described by attributes and their values. Category utility and partition utility play an important role in cluster analysis. These are fully analyzed in this research particularly in terms of how they are related to the favoritism in the final results. In this research, several data sets are selected and analyzed to show how different results are induced from these criterion functions.

• Communications for Statistical Applications and Methods
• /
• v.24 no.5
• /
• pp.457-480
• /
• 2017

We develop a random partition procedure based on a Dirichlet process prior with Laplace distribution. Gibbs sampling of a Laplace mixture of linear mixed regressions with a Dirichlet process is implemented as a random partition model when the number of clusters is unknown. Our approach provides simultaneous partitioning and parameter estimation with the computation of classification probabilities, unlike its counterparts. A full Gibbs-sampling algorithm is developed for an efficient Markov chain Monte Carlo posterior computation. The proposed method is illustrated with simulated data and one real data of the energy efficiency of Tsanas and Xifara (Energy and Buildings, 49, 560-567, 2012).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.455-460
• /
• 2003

A new cluster validity index is proposed that determines the optimal partition and optimal number of clusters for fuzzy partitions obtained from the fuzzy c-means algorithm. The proposed validity index exploits an overlap measure and a separation measure between clusters. The overlap measure is obtained by computing an inter-cluster overlap. The separation measure is obtained by computing a distance between fuzzy clusters. A good fuzzy partition is expected to have a low degree of overlap and a larger separation distance. Testing of the proposed index and nine previously formulated indexes on well-known data sets showed the superior effectiveness and reliability of the proposed index in comparison to other indexes.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.5 no.2
• /
• pp.44-57
• /
• 1995

In this paper GFI (Generalized Fuzzy Isodata) and FI (Fuzzy Isodata) algorithms are studied and applied to the tire tread pattern classification problem. GFI algorithm which repeatedly grouping the partitioned cluster depending on the fuzzy partition matrix is general form of GI algorithm. In the constructing the binary tree using GFI algorithm cluster validity, namely, whether partitioned cluster is feasible or not is checked and construction of the binary tree is obtained by FDH clustering algorithm. These algorithms show the good performance in selecting the prototypes of each patterns and classifying patterns. Directions of edge in the preprocessed image of tire tread pattern are selected as features of pattern. These features are thought to have useful information which well represents the characteristics of patterns.

• Korean Journal of Weed Science
• /
• v.17 no.3
• /
• pp.303-309
• /
• 1997

Variation of morphological and physiological traits of 50 Bidens tripartita accessions were studied and the accessions were grouped through cluster analysis based on four major characters; plant type, leaf partition, achene length, days to flowering. Bidens tripartite accessions have shown significant variations in plant type, stem length, days to flowering, leaf shape, leaf partition, chlorophyll content, leaf color, stem color, achene color, achene length and achene shape. Most of Bidens tripartite accessions appeared to have strong dormancy and also photodormancy with some exceptions. Plants could be classified into 5 types from straight(I) to triangle(V), and intermediate diamond type(III) was prevalent. The plant type score has negative correlation with the stem length. None, three, and five part leaved plants were observed and most of them were three or five parted. Leaf partition had negative correlation with achene length and chlorophyll content. Average days to flowering was 108 days in the range of 94~141 days. It had positive correlation with achene length and leaf shape and negative correlation with achene color. Average achene length was 10.0mm and it had positive correlation with achene shape, stem length, days to flowering and leaf shape. It also had negative correlation with leaf color, stem color, achene color, leaf partition. Bidens tripartite accessions could be divided into identifiable six groups from the cluster analysis at the distance 0.06 using Ward's minimum-variance method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.4 no.3
• /
• pp.337-340
• /
• 2004

The clustering problem can be formulated as the problem to find the number of clusters and a partition matrix from a given data set using the iterative or non-iterative algorithms. The author proposes a nearest neighbor and validity-based clustering algorithm where each data point in the data set is linked with the nearest neighbor data point to form initial clusters and then a cluster in the initial clusters is linked with the nearest neighbor cluster to form a new cluster. The linking between clusters is continued until no more linking is possible. An optimal set of clusters is identified by using the conventional cluster validity index. Experimental results on well-known data sets are provided to show the effectiveness of the proposed clustering algorithm.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.3
• /
• pp.16-23
• /
• 1998

In this paper, we present a fast and efficient Iterative Improvement Partitioning(IIP) technique for VLSI circuits and hybrid bucket structures on its implementation. The IIP algorithms are very widely used in VLSI circuit partition due to their time efficiency. As the performance of these algorithms depends on choices of moving cell, various methods have been proposed. Specially, Cluster-Removal algorithm by S. Dutt significantly improved partition quality. We indicate the weakness of previous algorithms wjere they used a uniform method for choice of cells during for choice of cells during the improvement. To solve the problem, we propose a new IIP technique that selects the method for choice of cells according to the improvement status and present hybrid bucket structures for easy implementation. The time complexity of proposed algorithm is the same with FM method and the experimental results on ACM/SIGDA benchmark circuits show improvment up to 33-44%, 45%-50% and 10-12% in cutsize over FM, LA-3 and CLIP respectively. Also with less CUP tiem, it outperforms Paraboli and MELO represented constructive-partition methods by about 12% and 24%, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 1991.10a
• /
• pp.601-605
• /
• 1991

In this paper an approximate solution method for the large-scale Traveling Salesman Problem(TSP) is presented. The method start with the subdivision of the problem domain into a number of clusters by considering their geometries. The clusters have limited number of nodes so as to get local solutions. They are linked to give the least path which covers the whole domain and become TSPs with start- and end-node. The approximate local solutions in each cluster are obtained by using geometrical property of the cluster, and combined to give an overall-approximate solution for the large-scale TSP.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.1
• /
• pp.22-33
• /
• 1999

In this paper, we propose a new multi-way circuit partitioning system that partition large circuits to progrmmable circuit board which consist of FPGAs and interconnect components. Here the routing topology among the chips are predetermined and the number of available interconnections are fixed. Since the given constraints are difficult to be satisfied by the previous partition method, we suggest a new multi-way partition method by target restriction that considers all the constraints for the given board. To speed up, we construct a multi-level cluster tree for hierarchical partitioning. Experimental results for several benchmarks show that the our partition method partition them by satisfying all the given constraints and it used up to 10 % fewer interconnections among the chips than the previous K-way partition method.

• Journal of the Korean Society for Precision Engineering
• /
• v.9 no.3
• /
• pp.122-131
• /
• 1992

In this paper an approximate solution method for the large-scale Traveling Salesman Problem (TSP) is presented. The method starts with the subdivision of the problem domain into a number of cluster by considering their geometric characteristic. Each cluster has a limited number of nodes so as to get a local solution. They are linked go give the least pathe which covers the whole domain and become TSPs solution with start-and end-node. The approximate local solution in each cluster are obtained based on geometrical properties of the cluster, and combined to give an overall approximate solution for the larte-scale TSP.