Cluster Analysis by Restricted Random Walks
A new graph theoretical method is introduced to analyze a data set of objects described by a dissimilarity matrix d ij . This method is based on the generation of a series of random walks in the data set. We define a random walk in a data set by moving in each time step from one object to another one at random. In order that the random walk depends on the pattern of the data, a restriction depending on the previous moves is imposed during its generation, so that the random walk is attracted by clusters formed of similar objects. We define a hierarchical set of graphs consisting of all connections of a series of random walks at a certain time step to detect the structure of the data and to derive an similarity measure between the objects. In an example an application of the method is shown.
Unable to display preview. Download preview PDF.
- ALPERT, C.J. and KAHNG, A.B. (1993): Geometric embedding for faster (and better) multi-way netlist partitioning. In: Proceedings of the ACM/IEEE Design Automation Conference, 743–748.Google Scholar
- GODEHARDT, E. (1990): Graphs as structural models: the application of graphs and multigraphs in cluster anaysis. Advances in system analysis 4. Vieweg, Braunschweig, 2nd edition.Google Scholar
- GORDON, A.D. (1999): Classification. Chapman Hall, 2nd edition.Google Scholar
- HAGEN, L. and KAHNG, A.B. (1992): A New Approach to Effective Circuit Clustering. In: Proceedings of the IEEE Intl. Conf. on Computer-Aided Design,422–427.Google Scholar
- SCHOLL, J. and PASCHINGER, E. (2001): Classification by restricted random walks. Pattern Recognition, accepted.Google Scholar
- ZAHN, C.T. (1971): Graph-theoretical methods for detecting and describing gestalt clusters. IEEE Trans.Comp, C-20(1), 68–86.Google Scholar