Temporal Interval Logic in Data Mining

Abstract

The last decade has seen the emergence of data mining as a significant field of research. Whilst the exploitation of time series data has been widely examined in this context, the accommodation of temporal interval semantics has not been widely investigated. Temporal intervals and the interaction of interval-based events are fundamental in many domains including commerce, medicine, computer security and various types of normalcy analysis. We have developed an algorithm for integrating temporal interval semantics into association rules, a form of rule that has become widely used in data mining. We have also developed a visualisation technique to view the discovered rules. The model of temporal reasoning that has been adopted accommodates both point-based and interval-based models of time simultaneously. In addition, the use of a generalized taxonomy of temporal relationships supports the generalization of temporal relationships and their specification at different levels of abstraction. This approach also facilitates the possibility of reasoning with incomplete or missing information.