62H30 Classification and discrimination; cluster analysis [See also 68T10]
Refine
Year of publication
- 1999 (2) (remove)
Document Type
- ZIB-Report (2)
Language
- English (2)
Has Fulltext
- yes (2)
Is part of the Bibliography
- no (2) (remove)
Keywords
- Self-Organizing Maps (2)
- cluster analysis (2)
- Data Mining (1)
- data preprocessing (1)
- information theory (1)
- missing values (1)
- similarity measures (1)
Institute
- ZIB Allgemein (2) (remove)
For using Data Mining, especially cluster analysis, one needs measures to determine the similarity or distance between data objects. In many application fields the data objects can have different information levels. In this case the widely used euclidean distance is an inappropriate measure. The present paper describes a concept how to use data of different information levels in cluster analysis and suggests an appropriate similarity measure. An example from practice is included, that shows the usefulness of the concept and the measure in combination with {\sc Kohonens} Self-Organizing Map algorithm, a well-known and powerful tool for cluster analysis.
One of the important tasks in Data Mining is automated cluster analysis. Self-Organizing Maps (SOMs) introduced by {\sc Kohonen} are, in principle, a powerful tool for this task. Up to now, however, its cluster identification part is still open to personal bias. The present paper suggests a new approach towards automated cluster identification based on a combination of SOMs with an eigenmode analysis that has recently been developed by {\sc Deuflhard et al.} in the context of molecular conformational dynamics. Details of the algorithm are worked out. Numerical examples from Data Mining and Molecular Dynamics are included.