Fast time intervals mining using the transitivity of temporal relations

Abstract

We introduce an algorithm, called KarmaLego, for the discovery of frequent symbolic time interval-related patterns (TIRPs). The mined symbolic time intervals can be part of the input, or can be generated by a temporal-abstraction process from raw time-stamped data. The algorithm includes a data structure for TIRP-candidate generation and a novel method for efficient candidate-TIRP generation, by exploiting the transitivity property of Allen's temporal relations. Additionally, since the non-ambiguous definition of TIRPs does not specify the duration of the time intervals, we propose to pre-cluster the time intervals based on their duration to decrease the variance of the supporting instances. Our experimental comparison of the KarmaLego algorithm's runtime performance with several existing state of the art time intervals pattern mining methods demonstrated a significant speed-up, especially with large datasets and low levels of minimal vertical support. Furthermore, pre-clustering by time interval duration led to an increase in the homogeneity of the duration of the discovered TIRP's supporting instances' time intervals components, accompanied, however, by a corresponding decrease in the number of discovered TIRPs.