Predictive Mining of Time Series Data in Astronomy

Authors: Eric Perlman, and Akshay Java

Journal: Astronomical Data Analysis Software and Systems XII ASP Conference Series

Date: January 01, 2003

Abstract: 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.

Type: Article

Pages: 431-434

Volume: 295

Google Scholar: 7hv4QbjAITEJ

Number of Google Scholar citations: 12 [show citations]

Number of downloads: 1303

Available for download as

size: 123499 bytes

Bookmark at: Digg | Del.icio.us | Connotea | CiteULike