Conference Paper

Alexander Kolesnikov, Elena Trichina, Determining the Number of Clusters with Rate-Distortion Curve Modeling.

Conference: ICIAR
Download full-text


Available from: Alexander Kolesnikov, Sep 28, 2015
1 Follower
53 Reads
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A method for identifying clusters of points in a multidimensional Euclidean space is described and its application to taxonomy considered. It reconciles, in a sense, two different approaches to the investigation of the spatial relationships between the points, viz., the agglomerative and the divisive methods. A graph, the shortest dendrite of Florek etal. (1951a), is constructed on a nearest neighbour basis and then divided into clusters by applying the criterion of minimum within cluster sum of squares. This procedure ensures an effective reduction of the number of possible splits. The method may be applied to a dichotomous division, but is perfectly suitable also for a global division into any number of clusters. An informal indicator of the "best number" of clusters is suggested. It is a"variance ratio criterion" giving some insight into the structure of the points. The method is illustrated by three examples, one of which is original. The results obtained by the dendrite method are compared with those obtained by using the agglomerative method or Ward (1963) and the divisive method of Edwards and Cavalli-Sforza (1965).
    01/1974; 3(1-1):1-27. DOI:10.1080/03610927408827101
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The problem of choosing the correct number of clusters is as old as cluster analysis itself. A number of authors have suggested various indexes to facilitate this crucial decision. One of the most extensive comparative studies of indexes was conducted by Milligan and Cooper (1985). The present piece of work pursues the same goal under different conditions. In contrast to Milligan and Cooper's work, the emphasis here is on high-dimensional empirical binary data. Binary artificial data sets are constructed to reflect features typically encountered in real-world data situations in the field of marketing research. The simulation includes 162 binary data sets that are clustered by two different algorithms and lead to recommendations on the number of clusters for each index under consideration. Index results are evaluated and their performance is compared and analyzed.
    Psychometrika 02/2002; 67(1):137-159. DOI:10.1007/BF02294713 · 1.09 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In k\hbox{-}{\rm{means}} clustering, we are given a set of n data points in d\hbox{-}{\rm{dimensional}} space {\bf{R}}^d and an integer k and the problem is to determine a set of k points in {\bf{R}}^d, called centers, so as to minimize the mean squared distance from each data point to its nearest center. A popular heuristic for k\hbox{-}{\rm{means}} clustering is Lloyd's algorithm. In this paper, we present a simple and efficient implementation of Lloyd's k\hbox{-}{\rm{means}} clustering algorithm, which we call the filtering algorithm. This algorithm is easy to implement, requiring a kd-tree as the only major data structure. We establish the practical efficiency of the filtering algorithm in two ways. First, we present a data-sensitive analysis of the algorithm's running time, which shows that the algorithm runs faster as the separation between clusters increases. Second, we present a number of empirical studies both on synthetically generated data and on real data sets from applications in color quantization, data compression, and image segmentation.
    IEEE Transactions on Pattern Analysis and Machine Intelligence 06/2002; 24(7):881-892. DOI:10.1109/TPAMI.2002.1017616 · 5.78 Impact Factor
Show more