AUTHOR(S): Xiaoyan Wang, Caixia Zhang, Yanping Bai

TITLE 
KEYWORDS subspace clustering, spectral clustering, kmeans, SOM 
ABSTRACT Sparse Subspace Clustering constructs a sparse similarity graph by using the coefficient of sparse representation to subspace clustering. Based on sparse representation techniques, the algorithm gets the sparse coefficient by using l1minimization and gets clustersâ€™ data by spectral clustering algorithm. The spectral clustering algorithm depends on kmeans algorithm for data clustering, while kmeans algorithm is sensitive to the choice of initial starting conditions and it needs iterations. In order to avoid the drawbacks of kmeans algorithm, we propose two modified Sparse Subspace Clustering algorithm, then the results are not be affected by the centers or the iterations. In one of the method, we get the clusters by comparing the positions of nonzero elements in the sparse adjacent matrix of similarity graph and the eigenvector. And in the second method, we use SOM algorithm instead of kmeans algorithm. The experiment results show our proposed algorithm outperforms the initial Sparse Subspace Clustering. 
Cite this paper Xiaoyan Wang, Caixia Zhang, Yanping Bai. (2016) Two Modified Sparse Subspace Clustering. International Journal of Mathematical and Computational Methods, 1, 400404 