Analysis of Time Series Using Compact Model-Based Descriptions

Abstract. Recently, we have proposed a novel method for the compression of time series based on mathematical models that explore dependencies between different time series. This representation models each time series by a combination of a set of specific reference time series. The cost of this representation depend only on the number of reference time series rather than on the length of the time series. In this demonstration, we present a Java toolkit which is able to perform several data mining tasks based on this novel time series representation. In particular, this framework allows the user to explore the properties of our novel approach in comparison to other state-of-the-art compression methods. The results are visually presented in a very concise way so that the user can easily identify important settings of the model-based time series representation. 1 Background Clustering time series data is a very important data mining task for a wide variety of applications. In many scenar...

• Type: Conference
• Year: 2008
• Where: DASFAA
• Authors: Hans-Peter Kriegel, Peer Kröger, Alexey Pryakhin, Matthias Renz
• Keywords: DASFAA 2008, Database, Reference Time Series, Time Series, Time Series Representation