Performance evaluation of some symmetry-based cluster validity indexes
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews - Special issue on information reuse and integration
| Hi-index | 0.00 |
Clustering techniques have been widely used for solving various engineering problems such as system architecture, modular product/system design, group technology, machine layout, and so on. Most of these problems use matrix formulation to model the problem. Once the matrix formulation for the problem is obtained, cluster analysis is used to group objects represented in the matrix into homogenous clusters based on object features. In this correspondence, a new efficient algorithm for clustering large n x n binary and nonbinary (weighted) matrices is presented. For an n x n incidence matrix, the algorithm first creates n clusters. Once the initial clusters are obtained, the algorithm uses improvement steps to continuously improve the quality of the solution obtained in the previous step. Modifications to the algorithm are presented for clustering n x m matrices. A detailed discussion on the effectiveness of the clustering algorithm when it is applied to matrices of various sizes and sparsity is also presented. The application of the n x n clustering algorithm developed in this correspondence is presented with the development of modular electrical/electronic vehicle door architectures.