The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.
TY - CONF AU - Biedron, S. ED - Boland, Mark ED - Tanaka, Hitoshi ED - Button, David ED - Dowd, Rohan ED - Schaa, Volker RW ED - Tan, Eugene TI - Adding Data Science and More Intelligence to Our Accelerator Toolbox J2 - Proc. of IPAC2019, Melbourne, Australia, 19-24 May 2019 CY - Melbourne, Australia T2 - International Particle Accelerator Conference T3 - 10 LA - english AB - Requirements for recent accelerators are becoming more and more stringent and sophisticated machine tuning is necessary. A large amount of data is acquired from accelerator components as an assistant of machine tuning. It is hard for operators to utilize all the accelerator data for machine tuning. Therefore, machine learning, data mining and big data handling are recently applied to accelerators. For instance, Bayesian optimization is used for maximizing a target performance, a clustering algorithm is used for anomaly detection, and hidden correlation finding is utilized for discovering new aspects of a machine. This talk reviews recent progress of machine learning applications and big data handling in accelerators. PB - JACoW Publishing CP - Geneva, Switzerland SP - 1191 EP - 1197 KW - controls KW - network KW - electron KW - laser KW - simulation DA - 2019/06 PY - 2019 SN - 978-3-95450-208-0 DO - DOI: 10.18429/JACoW-IPAC2019-TUZPLM1 UR - http://jacow.org/ipac2019/papers/tuzplm1.pdf ER -