Predictive Mining of Time Series Data in Astronomy

Eric Perlman; Akshay Java

Astronomical Data Analysis Software and Systems XII ASP Conference Series

Predictive Mining of Time Series Data in Astronomy

January 1, 2003

We discuss the development of a Java toolbox for astronomical time series data. Rather than using methods conventional in astronomy (e.g., power spectrum and cross-correlation analysis) we employ rule discovery techniques commonly used in analyzing stock-market data. By clustering patterns found within the data, rule discovery allows one to build pre- dictive models, allowing one to forecast when a given event might occur or whether the occurrence of one event will trigger a second. We have tested the toolbox and accompanying display tool on datasets (represent- ing several classes of objects) from the RXTE All Sky Monitor. We use these datasets to illustrate the methods and functionality of the toolbox. We also discuss issues that can come up in data analysis as well as the possible future development of the package.

123499 bytes

BibTeX OWL Tweet Scholar

Type: Article

Volume: 295

Downloads: 2596 downloads

Google Scholar Citations: 12 citations