A greedy randomized adaptive search procedure applied to the clustering problem as an initialization process using K-Means as a local search procedure

University of Granada, Granata, Andalusia, Spain
Journal of Intelligent and Fuzzy Systems (Impact Factor: 1.81). 01/2002; 12:235-242.
Source: DBLP


We present a new approach for Cluster Analysis based on a Greedy Randomized Adaptive Search Procedure (GRASP), with the objective of overcoming the convergence to a local solution. It uses a probabilistic greedy Kaufman initialization to get initial solutions and K-Means as a local search algorithm. The approach is a new initialization one for K-Means. Hence, we compare it with some typical initialization methods: Random, Forgy, Macqueen and Kaufman. Our empirical results suggest that the hybrid GRASP – K-Means with probabilistic greedy Kaufman initialization performs better than the other methods with improved results. The new approach obtains high quality solutions for eight benchmark problems.

Download full-text


Available from: Oscar Cordon
  • Source
    • "It is similar to calculating the centroid of the whole dataset and then obtaining k perturbations of this point (Thiesson, Meek et al. 1999). More random selection based algorithms have been proposed (Kaufman and Rousseeuw 1990; Cano, Cordón et al. 2002; MacQueen 1967) each with specific strengths and weaknesses. The order by which the initial seeds are presented may influence the final outcome, so re-ordering techniques have been used in (Fisher, Xu et al. 1992) and (Roure and Talavera 1998). "
    [Show abstract] [Hide abstract]
    ABSTRACT: One of the most widely used clustering techniques used in GISc problems is the k-means algorithm. One of the most important issues in the correct use of k-means is the initialization procedure that ultimately determines which part of the solution space will be searched. In this paper we briefly review different initialization procedures, and propose Kohonen's Self- Organizing Maps as the most convenient method, given the proper training parameters. Furthermore, we show that in the final stages of its training procedure the Self-Organizing Map algorithms is rigorously the same as the k- means algorithm. Thus we propose the use of Self-Organizing Maps as possible substitutes for the more classical k-means clustering algorithms.
    Full-text · Conference Paper · May 2005
  • Source

    Preview · Article · Jan 2005
  • [Show abstract] [Hide abstract]
    ABSTRACT: Clustering procedures partition a set of objects into clusters such that objects in the same cluster are more similar to each other than objects in different clusters according to some predefined criteria. Clustering is a popular data analysis and data mining technique. Since clustering problem have NP-complete nature, the larger the size of the problem, the harder to find the optimal solution and furthermore, the longer to reach a reasonable results. One of the most used techniques for clustering is based on K-means such that the data is partitioned into K clusters. Although k-means algorithm is easy to implement and works fast in most situations, it suffers from two major drawbacks. One is sensitivity to initialization and the other is convergence to local optima. It is seen from the studies K harmonic means clustering solves the problem of initialization but since its greedy search nature, the second problem; convergence to local optima, still remains.In this paper we develop a new algorithm for solving this problem based on a simulated annealing technique – simulated annealing K-harmonic means clustering (SAKHMC). The experiment results on the Iris and the other well known data, illustrate the robustness of the SAKHMC clustering algorithm.
    No preview · Article · Jan 2007 · Applied Mathematics and Computation
Show more