Clustering Data of Different Information Levels
Tobias Galliat · 1999
For using Data Mining, especially cluster analysis, one needs measures to determine the similarity or distance between data objects. In many ap-plication 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 in-formation 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 Kohonen’s Self-Organizing Map algorithm, a well-known and powerful tool for cluster analysis.