Similarity Search in Time Series Databases

Abstract

In many application domains, data can be represented as a series of values (time series). Examples include stocks, seismic signals, audio, and many more. Similarity search in time series databases is an important research direction. Several methods have been proposed in order to provide algorithms for efficient query processing in the case of static time series of fixed length. Research in this field has focused on the development of effective transformation techniques, the application of dimensionality reduction methods, and the design of efficient indexing schemes. These tools enable the process of similarity queries in time series databases. In the case where time series are continuously updated with new values (streaming time series), the similarity problem becomes even more difficult to solve, since we must take into consideration the new values of the series. The dynamic nature of streaming time series makes the methods proposed for the static case inappropriate. To attack the problem, significant research has been performed towards the development of effective and efficient methods for streaming time series processing. In this paper, we introduce the most important issues concerning similarity search in static and streaming time series databases, presenting fundamental concepts and techniques that have been proposed by the research community.