Issue No. 11 - November (2006 vol. 28)
Jaewook Lee , Department of Industrial and Management Engineering, Pohang University of Science and Technology, Pohang, Kyungbuk, Korea
Daewon Lee , Department of Industrial and Management Engineering, Pohang University of Science and Technology, Pohang, Kyungbuk, Korea
A topological and dynamical characterization of the cluster structures described by the support vector clustering is developed. It is shown that each cluster can be decomposed into its constituent basin level cells and can be naturally extended to an enlarged clustered domain, which serves as a basis for inductive clustering. A simplified weighted graph preserving the topological structure of the clusters is also constructed and is employed to develop a robust and inductive clustering algorithm. Simulation results are given to illustrate the robustness and effectiveness of the proposed method
Robustness, Kernel, Clustering algorithms, Static VAr compensators, Support vector machines, Labeling, Machine learning, Shape, Computational modeling, Clustering methods
Jaewook Lee and Daewon Lee, "Dynamic Characterization of Cluster Structures for Robust and Inductive Support Vector Clustering," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 28, no. 11, pp. 1869-1874, 2009.