Temporal databases provide built-in supports for efficient recording and querying of time-evolving data. Since many applications, such as trend analysis, version management, and medical record management, handle temporal aspects of underlying data, DBMS should provide temporal support directly in these cases.
In this work, we address data clustering issues in temporal database environment. Data clustering is one of the most effective techniques that can improve performance of a database system. However, data clustering techniques of conventional databases do not perform well in temporal databases because there exist crucial differences between their query patterns.
In this thesis, we propose a data clustering measure, called Temporal Affinity, that can be used for the clustering of temporal data. Temporal affinity, which is based on the analysis of query patterns in temporal database, reflects the similarities of temporal data in viewpoints of temporal query processing. We perform experiments in order to evaluate our proposed measure. The experimental results show that a data clustering method with temporal affinity works better than other methods.
