Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

T: Fachverband Teilchenphysik

T 38: Gammaastronomie II

T 38.3: Vortrag

Montag, 29. Februar 2016, 17:15–17:30, VMP9 SR 27

FACT - Streamed data analysis and online application of machine learning models — •Kai Arno Brügge and Jens Buss for the FACT collaboration — Technische Universität Dortmund, Astroteilchenphysik

Imaging Atmospheric Cherenkov Telescopes (IACTs) like FACT produce a continuous flow of data during measurements. Analyzing the data in near real time is essential for monitoring sources. One major task of a monitoring system is to detect changes in the gamma-ray flux of a source, and to alert other experiments if some predefined limit is reached. In order to calculate the flux of an observed source, it is necessary to run an entire data analysis process including calibration, image cleaning, parameterization, signal-background separation and flux estimation. Software built on top of a data streaming framework has been implemented for FACT and generalized to work with the data acquisition framework of the Cherenkov Telescope Array (CTA). We will present how the streams-framework is used to apply supervised machine learning models to an online data stream from the telescope.