Ci ≠ Ø, i = 1,…,m
∪i=1m Ci = X
Ci ∩ Cj = Ø, i ≠ j, i, j = 1,…,m
In addition, the data points contained in a cluster Ci are “more similar” to each other and “less similar” to the points of the other clusters. The terms “similar” and “dissimilar” depend very much on the types of clusters the user expects to recover from X. A clustering defined as above is known as hard clustering, to distinguish it from the fuzzy clustering case.
The essence of clustering is to “reveal” the organization of patterns into “sensible” groups. It has been used as a critical analysis tool in a vast range of disciplines, such as medicine, social sciences, engineering, computer science, machine learning, bioinformatics, data mining and information retrieval. The...
- 3.Chung FRK. Spectral graph theory. American Mathematical Society; 1997.Google Scholar
- 5.Golub GH, Van Loan CF. Matrix somputations. Baltimore: John Hopkins; 1989.Google Scholar
- 7.Hendrickson B, Leland R. Multidimensional spectral load balancing. In: Proceedings of the 4th SIAM Conference on Parallel Processing; 1993. p. 953–61.Google Scholar
- 8.Kannan R, Vempala S, Vetta A. On clusterings- good, bad and spectral. In: Proceedings of the 41st Annual Symposium on Foundations of Computer Science; 2000. p. 367–77.Google Scholar
- 10.Ng AY, Jordan M, Weiis Y. On spectral clustering analysis and an algorithm. In: Proceedings of the 14th Conference on Advances in Neural Information Processing Systems; 2001.Google Scholar
- 12.Scott G, Longuet-Higgins H. Feature grouping by relocalization of eigenvectors of the proximity matrix. In: Proceedings of the British Machine Vision Conference; 1990. p. 103–8.Google Scholar
- 14.Theodoridis S, Koutroumbas K. Pattern recognition. 4th edn. Academic Press; 2008.Google Scholar
- 15.Verma D, Meilă M. A comparison of spectral clustering algorithms. Technical Report, UW-CSE-03-05-01. Seattle: CSE Department/University of Washington; 2003.Google Scholar