STIDes Revisited - Tackling Global Time Shifts and Scaling

Abstract

In times where large amounts of time-dependent data is generated, the importance of time interval data sets in general and similarity analyses on these in particular continues to increase. In this context, various approaches regarding the comparability of two time interval data sets have been developed in recent years. The STIDes approach as a bottom up approach offers on the one hand the possibility to focus on individual properties of the intervals, on the other hand it allows time delays or scaling to be taken into consideration. In this paper, we take a closer look at the management of time delays and different scales and show that a similarity analysis using STIDes can be completed in polynomial time. Furthermore, we improve the handling of cardinality differences in the data sets to be compared.