СЕКЦИОННЫЕ ДОКЛАДЫ

XFEL diffraction patterns representation method for classification, indexing and search

S. A. Bobkov^a, A. B. Teslyuk^a, O. Yu. Gorobtsov^ab, O. M. Yefanov^c, R. P. Kurta^b, V. A. Ilyin^ad, M. V. Golosova^a, I. A. Vartan'yants<sup>eb

a</sup> National Research Center “Kurchatov Institute”, 1 Kurchatov Sq., Moscow 123182, Russia
^b Deutsches Elektronen-Synchrotron DESY, 85 Notkestraße, D-22607 Hamburg, Germany
^c Center for Free-Electron Laser Science, 85 Notkestraße, D-22607 Hamburg, German
^d Lomonosov Moscow State University,GSP-1, 1-52 Leninskie Gory, Moscow, 119991, Russia
^e National Research Nuclear University MEPhI, 31 Kashirskoe highway, 115409, Moscow, Russia

Abstract: The paper presents the results of application of machine learning methods: principle component analysis and support vector machine for classification of diffraction images produced in experiments at free-electron lasers. High efficiency of this approach presented by application to simulated data of adenovirus capsid and blue-tongue virus core. This dataset were simulated with taking into account the real conditions of the experiment on lasers free electrons such as noise and features of used detectors.

Keywords: principle component analysis, support vector machine, coherent diffraction imaging.

UDC: 004.02, 004.94

Received: 21.01.2015

DOI: 10.20537/2076-7633-2015-7-3-631-639