{"id":1989,"date":"2016-05-05T15:08:44","date_gmt":"2016-05-05T13:08:44","guid":{"rendered":"http:\/\/excel.fit.vutbr.cz\/2020\/?page_id=1989"},"modified":"2020-06-01T18:18:13","modified_gmt":"2020-06-01T16:18:13","slug":"vysledky","status":"publish","type":"page","link":"https:\/\/excel.fit.vutbr.cz\/2020\/vysledky\/","title":{"rendered":"V\u00fdsledky"},"content":{"rendered":"\r\n\t<link rel=\"stylesheet\" media=\"all\" type=\"text\/css\" href=\"\/submissions\/css\/results.css?v2020527\">\r\n\r\n\t<div class=\"well\">\r\n\t\t<ul>\r\n\t\t\t<li><a href=\"#oceneni-odbornym-panelem\">Ocen\u011bn\u00ed <strong>odborn\u00fdm panelem<\/strong><\/a><\/li>\r\n            <li><a href=\"#oceneni-partnery\">Ocen\u011bn\u00ed <strong>partnery z pr\u016fmyslu<\/strong><\/a><\/li>\r\n            <li><a href=\"#oceneni-odbornou-verejnosti-cena-jiriho-kunovskeho\">Ocen\u011bn\u00ed <strong>odbornou ve\u0159ejnost\u00ed<\/strong> - cena Ji\u0159\u00edho Kunovsk\u00e9ho<\/a><\/li>\r\n\t\t<\/ul>\r\n\t<\/div>\r\n\t  \r\n\t<h2 id=\"oceneni-odbornym-panelem\">Ocen\u011bn\u00ed <strong>odborn\u00fdm panelem<\/strong><\/h2>\r\n\t<div class=\"row results\">\r\n\t\t<div class=\"thumbnail topic01 topic05 topic08\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za n\u00e1vrh roz\u0161\u00ed\u0159en\u00ed pro zp\u011btn\u00fd p\u0159eklada\u010d RetDec\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">2<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal2\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/002\/2_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Sp\u00e4tn\u00fd preklad \u0161pecializovan\u00fdch a pokro\u010dil\u00fdch instruk\u010dn\u00fdch s\u00e1d n\u00e1strojom RetDec<\/h4>\r\n\t\t\t\t<h5>Juraj Holub<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/002\/2.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/002\/2_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal2\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">2<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Sp\u00e4tn\u00fd preklad \u0161pecializovan\u00fdch a pokro\u010dil\u00fdch instruk\u010dn\u00fdch s\u00e1d n\u00e1strojom RetDec<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Juraj Holub<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>RetDec, reverse engineering, decompiler, x86, FPU, Avast<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Bezpe\u010dnost<\/span> <span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 architektura a vestav\u011bn\u00e9 syst\u00e9my<\/span> <span class=\"label label-default\">P\u0159eklada\u010de a gramatiky<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>V dne\u0161nej dobe je proces anal\u00fdzy nebezpe\u010dn\u00e9ho softv\u00e9ru d\u00f4le\u017eitou s\u00fa\u010das\u0165ou informa\u010dn\u00fdch technol\u00f3gi\u00ed. Jedna z k\u013e\u00fa\u010dov\u00fdch techn\u00edk je sp\u00e4tn\u00fd preklad \u0161kodliv\u00fdch bin\u00e1rnych programov. Sp\u00e4tn\u00fd preklad je komplexn\u00fd proces, ktor\u00fdm sa zaober\u00e1 nieko\u013eko projektov. Projekt RetDec sa zameriava na flexibiln\u00fd n\u00e1vrh a rie\u0161enie sp\u00e4tn\u00e9ho preklada\u010da s mo\u017enos\u0165ou znovupou\u017eite\u013enosti. Ide o open-source projekt veden\u00fd firmou Avast. Tento \u010dl\u00e1nok sa zaober\u00e1 n\u00e1vrhom nov\u00e9ho roz\u0161\u00edrenia pre sp\u00e4tn\u00fd preklada\u010d RetDec v oblasti podpory \u0161pecializovanej in\u0161truk\u010dnej sady pre jednotku FPU, ktor\u00e1 je s\u00fa\u010das\u0165ou procesorovej architekt\u00fary x86.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/002\/2_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/002\/2.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/002\/2_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za n\u00e1vrh a implementaci nov\u00e9ho pluginu pro framework Frama-C zam\u011b\u0159en\u00e9ho na hled\u00e1n\u00ed deadlocku\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">12<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal12\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/012\/12_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Static Deadlock Detection in Frama-C<\/h4>\r\n\t\t\t\t<h5>Tom\u00e1\u0161 Dac\u00edk<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/012\/12.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/012\/12_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal12\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">12<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Static Deadlock Detection in Frama-C<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Tom\u00e1\u0161 Dac\u00edk<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Static Analysis, Deadlock Detection, Frama-C<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Frama-C is a platform for static analysis of source codes written in the C language. It provides a wide range of analysers usually based on EVA - Frama-C's value analysis plugin. Despite some attempts to support analysis of multi-threaded code have been done in Frama-C, the whole platform is currently limited to analysis of sequential code only. In this paper, we present Deadlock, a new plugin of Frama-C focused on deadlock detection. Together with the core algorithm of deadlock detection, we present a technique our analyser uses to handle multi-threaded code partially as a sequential one, which allows us to improve the precision of our analysis by using existing plugins of Frama-C. In our experimental evaluation, we show that our tool is able to handle real-word C code with a high precision.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/012\/12_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/012\/12.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/012\/12_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za roz\u0161\u00ed\u0159en\u00ed frameworku ANaConDA o podporu testov\u00e1n\u00ed v\u00edceprocesov\u00fdch aplikac\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">20<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal20\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h4>\r\n\t\t\t\t<h5>Monika Mu\u017eikovsk\u00e1<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal20\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">20<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Monika Mu\u017eikovsk\u00e1<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>ANaConDA, Dynamick\u00e1 anal\u00fdza, Paraleln\u00ed chyby, V\u00edceprocesov\u00e9 programy<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Dynamick\u00e1 anal\u00fdza se s \u00fasp\u011bchem vyu\u017e\u00edv\u00e1 pro detekci chyb ve v\u00edcevl\u00e1knov\u00fdch programech. Algoritmy, kter\u00e9 byly za t\u00edmto \u00fa\u010delem navr\u017eeny, jsou ale \u010dasto vyu\u017eiteln\u00e9 i pro v\u00edceprocesov\u00e9 programy. \u017d\u00e1dn\u00fd ze zn\u00e1m\u00fdch n\u00e1stroj\u016f pro dynamickou anal\u00fdzu ale monitorov\u00e1n\u00ed proces\u016f nepodporuje. C\u00edlem t\u00e9to pr\u00e1ce bylo roz\u0161\u00ed\u0159it n\u00e1stroj ANaConDA o anal\u00fdzu a monitorov\u00e1n\u00ed v\u00edceprocesov\u00fdch program\u016f. V\u00fdsledkem je implementace roz\u0161\u00ed\u0159en\u00ed, kter\u00e9 za v\u00fdvoj\u00e1\u0159e analyz\u00e1tor\u016f \u0159e\u0161\u00ed probl\u00e9my spojen\u00e9 s odd\u011blen\u00fdmi adresov\u00fdmi prostory a synchronizac\u00ed pomoc\u00ed semafor\u016f. Roz\u0161\u00ed\u0159en\u00ed bylo vyu\u017eito pro \u00fapravu analyz\u00e1toru AtomRace pro detekci \u010dasov\u011b z\u00e1visl\u00fdch chyb nad daty ve v\u00edceprocesov\u00fdch programech a pou\u017eito na experimenty se studentsk\u00fdmi projekty z p\u0159edm\u011btu Opera\u010dn\u00ed syst\u00e9my. V\u00fdsledky experiment\u016f uk\u00e1zaly, \u017ee se n\u00e1stroj ANaConDA m\u016f\u017ee st\u00e1t v\u00edtan\u00fdm pomocn\u00edkem p\u0159i implementaci nejen v\u00edceprocesov\u00fdch projekt\u016f.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za n\u00e1vrh algoritmu pro test inkluze regul\u00e1rn\u00edch v\u00fdraz\u016f efektivn\u011b reprezentovan\u00fdch automaty s \u010d\u00edta\u010di\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">33<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal33\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/033\/33_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Inclusion of Regular Expressions with Counting<\/h4>\r\n\t\t\t\t<h5>David Mik\u0161an\u00edk<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/033\/33.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/033\/33_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal33\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">33<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Inclusion of Regular Expressions with Counting<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>David Mik\u0161an\u00edk<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>regular expressions, language inclusion, finite automata, counting automata<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>We present an algorithm solving the inclusion problem for regular expressions  with the counting operator limited to character classes, the so-called extended regular expressions (eREs), which are common in practice. Such regular expressions do not extend expressiveness beyond regularity, but allow one to succinctly express repeated patterns. Our algorithm is based on the transformation eREs into monadic counting automata (MCAs), i.e., finite automata with counting loops on character class where each counter is bounded. Similarly to the classical algorithm, we transform eREs into automata, but now we use MCAs instead of nondeterministic finite automata (NFAs). Following by building the product of MCAs and searching for a final state in the product. MCAs are compact representation of eREs because the number of states in MCAs does not depend on the bounds used in the counting operator, in contrast to NFAs where the number of states grows linearly. These bounds can be large in practice, thus MCAs are often significantly smaller than NFAs. We provide several examples for which the classical algorithm working with NFAs does not terminate in a reasonable amount of time, but our algorithm does. We also hope that our algorithm outperforms the classical algorithm in general, especially if the bounds of the counting operators are large.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/033\/33_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/033\/33.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/033\/33_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic02\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za praktick\u00e9 roz\u0161\u00ed\u0159en\u00ed komplexn\u00edho syst\u00e9mu pro v\u00fdzkum enzym\u016f\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">7<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal7\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/007\/7_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>EnzymeMiner: Web Server for Automated Mining of Soluble Enzymes<\/h4>\r\n\t\t\t\t<h5>Simeon Borko<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/007\/7.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/007\/7_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal7\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">7<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">EnzymeMiner: Web Server for Automated Mining of Soluble Enzymes<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Simeon Borko<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>enzyme mining, novel biocatalysts, web server<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Bioinformatika<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Millions of protein sequences are being discovered at an incredible pace, representing an inexhaustible source of biocatalysts. Despite genomic databases growing exponentially, classical biochemical characterization techniques are time-demanding, cost-ineffective and low-throughput. Therefore, computational methods are being developed to explore the unmapped sequence space efficiently. Selection of putative enzymes for biochemical characterization based on rational and robust analysis of all available sequences remains an unsolved problem. To address this challenge, I have developed EnzymeMiner \u2013 a web server for automated screening and annotation of enzymes that enables selection of hits for wet-lab experiments. EnzymeMiner prioritizes sequences that are more likely to preserve the catalytic activity and are expressible in a soluble form in heterologous host organism Escherichia coli. EnzymeMiner reduces the time devoted to data gathering, multi-step analysis, sequence prioritization and selection from days to hours. EnzymeMiner is a universal tool applicable to any enzyme family that provides an interactive and easy-to-use web interface freely available at https:\/\/loschmidt.chemi.muni.cz\/enzymeminer\/.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/007\/7_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/007\/7.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/007\/7_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za v\u00fdvoj technik pro zefektivn\u011bn\u00ed tvorby lokaliza\u010dn\u00edch syst\u00e9m\u016f\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">23<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal23\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/023\/23_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Infrastructure for Testing and Deployment of the Real-Time Localization Platform<\/h4>\r\n\t\t\t\t<h5>Michal Ormo\u0161<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/023\/23.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/023\/23_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal23\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">23<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Infrastructure for Testing and Deployment of the Real-Time Localization Platform<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Michal Ormo\u0161<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>RTLS Systems, UWB, CI\/CD, Indoor Localization<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Fast development and deployment of the software are the new phenomena of the era. It is not different in the field of real-time localization systems (RTLS). In our global world where the global positioning system (GPS) is the everyday utility, there is a necessity of localizing under the roof where the GPS cannot access. Here come the local position systems based on Ultra Wide Band (UWB), which bring the ultimate precision. This work solves the problem of fast delivery of the software responsible for the RTLS System. It produces a case study on how to develop, test, and deploy this system in the fast CI\/CD environment with the help of DevOps principles. This requires introducing the new techniques and methods for how to validate and test the precision of these systems.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/023\/23_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/023\/23.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/023\/23_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic05 topic11\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za zaj\u00edmavou my\u0161lenku spojuj\u00edc\u00ed chytr\u00fd telefon s extern\u00edm HW s mo\u017en\u00fdm re\u00e1ln\u00fdm p\u0159\u00ednosem pro specifick\u00e9 skupiny u\u017eivatel\u016f\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">6<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal6\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/006\/6_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Hardwarov\u00fd indik\u00e1tor ozn\u00e1men\u00ed pro telefony se syst\u00e9mem Android<\/h4>\r\n\t\t\t\t<h5>Roman B\u00e1rtl<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/006\/6.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/006\/6_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/PTxRNvYpG-g\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal6\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">6<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Hardwarov\u00fd indik\u00e1tor ozn\u00e1men\u00ed pro telefony se syst\u00e9mem Android<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Roman B\u00e1rtl<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Arduino, Android, Bluetooth Low Energy, Vestav\u011bn\u00fd syst\u00e9m, Notifikace<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 architektura a vestav\u011bn\u00e9 syst\u00e9my<\/span> <span class=\"label label-default\">U\u017eivatelsk\u00e1 rozhran\u00ed<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>C\u00edlem t\u00e9to pr\u00e1ce je navrhnout a vytvo\u0159it notifika\u010dn\u00ed za\u0159\u00edzen\u00ed, kter\u00e9 bude zobrazovat nejr\u016fzn\u011bj\u0161\u00ed upozorn\u011bn\u00ed z chytr\u00fdch telefon\u016f. Jedn\u00e1 se o upozorn\u011bn\u00ed na p\u0159\u00edchoz\u00ed hovory, stav baterie a notifikace nainstalovan\u00fdch aplikac\u00ed. J\u00e1drem za\u0159\u00edzen\u00ed je jednodeskov\u00fd po\u010d\u00edta\u010d Arduino. Sou\u010d\u00e1st\u00ed pr\u00e1ce je i implementace aplikace pro opera\u010dn\u00ed syst\u00e9m Android, kter\u00e1 slou\u017e\u00ed jak pro komunikaci s t\u00edmto za\u0159\u00edzen\u00edm, tak i k samotn\u00e9mu zachyt\u00e1v\u00e1n\u00ed zm\u00edn\u011bn\u00fdch ud\u00e1lost\u00ed. Pro komunikaci je pou\u017eita technologie Bluetooth Low Energy. Je kladen d\u016fraz na jednoduchost a srozumitelnost cel\u00e9ho syst\u00e9mu v\u010detn\u011b zaji\u0161t\u011bn\u00ed co nejv\u011bt\u0161\u00ed mo\u017en\u00e9 kompatibility nap\u0159\u00ed\u010d verzemi syst\u00e9mu Android.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/006\/6_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/006\/6.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/006\/6_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/PTxRNvYpG-g\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za v\u00fdvoj syst\u00e9mu pro automatick\u00e9 rozpozn\u00e1v\u00e1n\u00ed lidsk\u00fdch tv\u00e1\u0159\u00ed z obrazov\u00fdch dat\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">35<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal35\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/035\/35_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Automated human recognition from image data<\/h4>\r\n\t\t\t\t<h5>Luk\u00e1\u0161 Dobi\u0161<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/035\/35.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/035\/35_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/hTfqqwv62gE\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal35\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">35<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Automated human recognition from image data<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Luk\u00e1\u0161 Dobi\u0161<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Human classification, Computer vision, Deep learning<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>This paper describes an approach for automated human recognition by using convolutional neural networks (CNN) to perform facial analysis of persons face in image data. The predicted biometric indicators are following: age, gender, facial landmarks and facial expression. CNN architectures with pretrained weights for each task are described. Age estimation CNN has new weights trained and freezed, then has added new LSTM layers into its architecture. New LSTM layers are trained and tested on newly created video data set. Solution for human recognition inference with single image and time series variants, in form of script with interconnected CNNs is explained and its inference speed performance supports further proposed expansion plans for live video inference.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/035\/35_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/035\/35.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/035\/35_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/hTfqqwv62gE\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic09\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za snahu o vlastn\u00ed p\u0159\u00edstup k automatizaci n\u00e1vrhu struktury konvolu\u010dn\u00edch neuronov\u00fdch s\u00edt\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">26<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal26\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/026\/26_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Evolu\u010dn\u00ed n\u00e1vrh konvolu\u010dn\u00edch neuronov\u00fdch s\u00edt\u00ed<\/h4>\r\n\t\t\t\t<h5>Michal Pi\u0148os<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/026\/26.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/026\/26_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal26\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">26<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Evolu\u010dn\u00ed n\u00e1vrh konvolu\u010dn\u00edch neuronov\u00fdch s\u00edt\u00ed<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Michal Pi\u0148os<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Neuroevoluce, Neuronov\u00e9 s\u00edt\u011b, Evolu\u010dn\u00ed v\u00fdpo\u010detn\u00ed techniky<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>C\u0131\u0301lem t\u00e9to pr\u00e1ce je n\u00e1vrh a implementace programu pro automatizovan\u00fd n\u00e1vrh konvolu\u010dn\u0131\u0301ch neuronov\u00fdch s\u0131\u0301t\u0131\u0301 (CNN) s vyu\u017eit\u0131\u0301m evolu\u010dn\u0131\u0301ch v\u00fdpo\u010detn\u0131\u0301ch technik. Z praktick\u00e9ho hlediska tento p\u0159\u0131\u0301stup redukuje pot\u0159ebu lidsk\u00e9ho faktoru p\u0159i tvorb\u011b CNN, a tak eliminuje zdlouhav\u00fd a nam\u00e1hav\u00fd proces n\u00e1vrhu. Tato pr\u00e1ce vyu\u017e\u0131\u0301v\u00e1 speci\u00e1ln\u0131\u0301 formu genetick\u00e9ho programov\u00e1n\u0131\u0301 naz\u00fdvanou kart\u00e9zsk\u00e9 genetick\u00e9 programov\u00e1n\u0131\u0301, kter\u00e9 pro zak\u00f3dov\u00e1n\u0131\u0301 \u0159e\u0161en\u00e9ho probl\u00e9mu vyu\u017e\u0131\u0301v\u00e1 grafovou reprezentaci. Tato technika umo\u017e\u0148uje u\u017eivateli parametrizovat proces hled\u00e1n\u0131\u0301 CNN, a tak se zam\u011b\u0159it na architektury zaj\u0131\u0301mav\u00e9 z pohledu pou\u017eit\u00fdch v\u00fdpo\u010detn\u0131\u0301ch jednotek, p\u0159esnosti \u010di po\u010dtu parametr\u016f. Navrhovan\u00fd p\u0159\u0131\u0301stup byl otestov\u00e1n na standardizovan\u00e9 datov\u00e9 sad\u011b CIFAR-10, kter\u00e1 je \u010dasto vyu\u017e\u0131\u0301v\u00e1na v\u00fdzkumn\u0131\u0301ky pro srovn\u00e1n\u0131\u0301 v\u00fdkonnosti jejich CNN. Prvotn\u0131\u0301 experimenty uk\u00e1zaly, \u017ee vytvo\u0159en\u00e1 implementace (vyu\u017e\u0131\u0301vaj\u0131\u0301c\u0131\u0301 GPU akceleraci) je schopna vytvo\u0159it \u010di vylep\u0161it p\u0159esnost CNN. V\u00fdsledkem experiment\u016f, kdy bylo pro tr\u00e9nov\u00e1n\u0131\u0301 k dispozici pouze n\u011bkolik epoch, byla \u0159e\u0161en\u0131\u0301 s p\u0159esnost\u0131\u0301 64.5 % a po\u010dtem parametr\u016f 146K p\u0159i vyu\u017eit\u0131\u0301 z\u00e1kladn\u0131\u0301ch vrstev a \u0159e\u0161en\u0131\u0301 s p\u0159esnost\u0131\u0301 74.5 % s po\u010dtem parametr\u016f 475K p\u0159i vyu\u017eit\u0131\u0301 rezidu\u00e1ln\u0131\u0301ch vrstev. Z\u00e1m\u011brem t\u011bchto experiment\u016f bylo dok\u00e1zat funk\u010dnost implementovan\u00e9ho programu a proof-of-concept navr\u017een\u00e9 metody.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/026\/26_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/026\/26.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/026\/26_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za dota\u017eenou aplikaci s okam\u017eit\u00fdm praktick\u00fdm vyu\u017eit\u00edm\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">9<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal9\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h4>\r\n\t\t\t\t<h5>Dominik Vagala<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal9\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">9<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Dominik Vagala<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Paint my room, Change wall color, N\u00e1h\u013ead farby na stene, Roz\u0161\u00edren\u00e1 realita, AR, ArCore, Mobiln\u00e1 aplik\u00e1cia, Android<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Cie\u013eom tejto pr\u00e1ce je n\u00e1vrh a implement\u00e1cia mobilnej aplik\u00e1cie pre Android, ktor\u00e1 by umo\u017e\u0148ovala meni\u0165 farby na stene pomocou roz\u0161\u00edrenej reality. U\u017e\u00edvate\u013e si tak m\u00f4\u017ee vysk\u00fa\u0161a\u0165 r\u00f4zne farby priamo v miestnosti kde sa nach\u00e1dza, a n\u00e1sledne sa rozhodn\u00fa\u0165, ktor\u00e1 farba sa mu tam najviac hod\u00ed na vyma\u013eovanie stien. Na rozpoznanie hran\u00edc steny je pou\u017eit\u00fd Sobelov detektor hr\u00e1n, kde sa ohrani\u010den\u00fd \u00fasek steny vyp\u013a\u0148a farbou pomocou upraven\u00e9ho Queue-Linear Flood Fill algoritmu. 2D s\u00faradnice, kde u\u017e\u00edvate\u013e klikol na stenu, sa pribli\u017ene prepo\u010d\u00edtaj\u00fa na 3D s\u00faradnice v priestore. Tie sa n\u00e1sledne sleduj\u00fa pomocou kni\u017enice ArCore, v\u010faka \u010domu stena zostane zafarben\u00e1 aj ke\u010f sa u\u017e\u00edvate\u013e pohybuje po miestnosti.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic09 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za pe\u010dlivou v\u011bdeckou pr\u00e1ci v oblasti strojov\u00e9ho u\u010den\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">14<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal14\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/014\/14_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Speech Enhancement with Cycle-Consistent Neural Networks<\/h4>\r\n\t\t\t\t<h5>Pavol Karl\u00edk<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/014\/14.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/014\/14_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal14\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">14<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Speech Enhancement with Cycle-Consistent Neural Networks<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Pavol Karl\u00edk<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Speech Enhancement, Deep Learning, Cycle-Consistency<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Speech enhancement aims to improve speech intelligibility and overall perceptual quality of speech by using various algorithms. Neural networks (NNs) have become a standard approach for solving such problems. NNs are usually trained by comparing the network output to the target sample. In our work, we incorporate cycle consistency constraint during the training period to improve the network robustness --- we add another NN to the process. The second NN performs an opposite task --- its goal is to introduce noise to clean speech recording. The networks are trained in a cycle, each taking the output of the other network as an input. Cycle-consistency, among other things, causes the network to see a much larger variety of noisy data, which improves the network's robustness. We perform experiments on both paired and unpaired data, which is enabled by adding adversarial training to the training. The DNN models are evaluated by using an automatic speech recognition system. The speech enhancement models trained and evaluated in this work are based on a recent publication. The results have shown that adding cycle-consistency improves the models' performance significantly.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/014\/14_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/014\/14.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/014\/14_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za vytvo\u0159en\u00ed konkurenceschopn\u00e9ho rozpozn\u00e1va\u010de \u0159e\u010di\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">15<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal15\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/015\/15_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Best possible speech recognizer on your own data<\/h4>\r\n\t\t\t\t<h5>Tom\u00e1\u0161 S\u00fdkora<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/015\/15.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/015\/15_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal15\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">15<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Best possible speech recognizer on your own data<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Tom\u00e1\u0161 S\u00fdkora<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>automatic speech recognition, domain adaptation, conversational speech<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Many state-of-the-art results in different machine learning areas are presented on day-to-day basis. By adjusting these systems to perform perfectly on a specific subset of the general data, huge improvements may be achieved in their resulting accuracy. Usage of domain adaptation in automatic speech recognition can bring us to production level models capable of transcribing difficult and noisy customer conversations way more accurately than the general models trained on all kinds of language and speech data. In this work I present 12.7% word error rate improvement in our speech recognition task over the general domain speech recognizer from Google. The improvement was achieved by both very precise annotation and preparation of domain data and by combining state-of-the-art architectures and algorithms. The described system was successfully integrated into a production environment of the Parrot transcription company founded by, among other team members, current and former faculty students, which drastically increased performance of the human transcribers.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/015\/15_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/015\/15.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/015\/15_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic09 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za implementaci n\u011bkolika architektur, jejich pe\u010dliv\u00e9 srovn\u00e1n\u00ed a v\u00fdsledek pou\u017eiteln\u00fd v dal\u0161\u00ed pr\u00e1ci skupiny Graph@FIT\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">18<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal18\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/018\/18_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Counting Vehicles in Image and Video<\/h4>\r\n\t\t\t\t<h5>Dominik Gabzdyl<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/018\/18.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/018\/18_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal18\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">18<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Counting Vehicles in Image and Video<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Dominik Gabzdyl<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>vehicle counting, counting by regression, convolutional neural networks<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Traffic analysis is still a challenging task. During such task there are many pitfalls to be aware of. Such as small image resolution, high number of overlapping objects, angle of camera, blurred objects due to their motion or weather conditions. This paper addresses the issue of counting vehicles instances in images and videos. Remarkable results and state-of-the-art methods are defined by convolutional neural networks. There are many approaches to address the issue of counting objects in images. One of which is counting by regression, which is the aim of this paper. I propose an architecture which is inspired by some state-of-the-art models. The proposed model improves accuracy on various datasets. For instance on the very small PUCPR+ dataset the Root Mean Square Error between expected and predicted vehicle counts was reduced from 34.46 to 8.84 vehicles (measured on the test set).<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/018\/18_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/018\/18.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/018\/18_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic06 topic09 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za \u00fasp\u011b\u0161nou pr\u00e1ci na pomez\u00ed biomedic\u00ednsk\u00e9ho in\u017een\u00fdrstv\u00ed a strojov\u00e9ho u\u010den\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">22<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal22\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/022\/22_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Benchmarking medical segmentation models with limited training sets<\/h4>\r\n\t\t\t\t<h5>Kate\u0159ina Tr\u00e1vn\u00ed\u010dkov\u00e1, Old\u0159ich Kodym<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/022\/22.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/022\/22_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal22\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">22<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Benchmarking medical segmentation models with limited training sets<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Kate\u0159ina Tr\u00e1vn\u00ed\u010dkov\u00e1, Old\u0159ich Kodym<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Segmentation, Deep learning, Medical data, Image restauration, Limited training set<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Deep learning based medical data segmentation methods can provide excellent results already. However, these results are obtained mostly thanks to the large training data sets. Obtaining the sufficient amount of correct annotations might be problematic in the medical field. This paper describes the problem of training medical segmentation models with limited annotations and proposes solutions to address the issue.  We compare the baseline segmentation model group with two other model groups. These groups use different means to battle the lack of data problem. First group is pretrained in unsupervised manner and the second one uses human interaction in form of guidance clicks. We train 14 models for each group on subsets with varying number of patients. Segmentation model trained on small number of patients has better results when pretrained in unsupervised manner on the whole trainig set with 70 patients. Better results are obtained with the interactive method, where training on only two patients reaches Dice score 0.929 whereas the preitrained model reaches 0.830 and the baseline model only 0.749.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/022\/22_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/022\/22.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/022\/22_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za tvorbu reprezentativn\u00edho datasetu v\u010detn\u011b test\u016f state of the art p\u0159\u00edstup\u016f\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">31<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal31\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/031\/31_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Counting Vehicles in Static Images<\/h4>\r\n\t\t\t\t<h5>Ond\u0159ej Zem\u00e1nek<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/031\/31.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/031\/31_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal31\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">31<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Counting Vehicles in Static Images<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Ond\u0159ej Zem\u00e1nek<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>visual counting, vehicle counting in static images, car park dataset<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>This paper addresses the problem of counting vehicles in static images with no geometric information of the scene. Four convolutional neural network architectures were studied, implemented and trained as a main part of this work. Also, a dataset that consists of 19 310 images in total from 12 views that captures 7 different scenes were taken as part of this work. The trained networks map the appearance of the input sample to its corresponding vehicles density map, which can be easily translated to the vehicle count with keeping the localization of the vehicles in the input image. The main contribution of this work is in a comparison and application of the state-of-the-art solutions to the problem of object counting. Most of them were mainly designed to count pedestrians in crowded scenes or for medicine images, so the major goal was to adapt these solutions for vehicle counting task. The implemented models were trained on TRANCOS dataset which is a popular benchmark for counting vehicles on annotated low quality highway pictures. Their performance is compared and the results are discussed.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/031\/31_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/031\/31.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/031\/31_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic07\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za praktick\u00fd p\u0159\u00ednos a dobr\u00e9 porovn\u00e1n\u00ed \u0159e\u0161en\u00ed probl\u00e9m\u016f DDoS \u00fatok\u016f\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">34<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal34\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/034\/34_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Adaptive SYN Flood Mitigation Based on Attack Vector Detection and Mitigation Process Monitoring<\/h4>\r\n\t\t\t\t<h5>Patrik Goldschmidt<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/034\/34.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/034\/34_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal34\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">34<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Adaptive SYN Flood Mitigation Based on Attack Vector Detection and Mitigation Process Monitoring<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Patrik Goldschmidt<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>TCP SYN Flood, DDoS Mitigation, Adaptive DoS Protection<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e9 s\u00edt\u011b<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>TCP SYN Flood is one of the most widespread DoS attack types performed on computer networks nowadays. The attack comes in many possible forms and several different mitigation methods to deflect it also exist. This paper discusses mentioned security incidents, various mitigation approaches, and presents a mechanism able to choose the most suitable method to mitigate the attack. The suggestion is made according to network traffic and the properties of mitigation methods. After the suggested method is deployed, the algorithm also monitors its behavior and may suggest a different strategy when the one currently in use proves to be ineffective. Our experiments have shown that the mechanism is able to successfully detect several attack variants and suggest a suitable method to deflect them while trying to minimize the impact on the end-user as much as possible. On the other hand, the suggestion accuracy is heavily dependent on available mitigation methods and their properties, which need to be set manually before the system can be used.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/034\/34_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/034\/34.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/034\/34_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic12\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za dobr\u00fd n\u00e1vrh dotazovac\u00edho jazyka EQL a syst\u00e9mu vyhled\u00e1va\u010de\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">19<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal19\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/019\/19_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Enticing \u2013 Semantic Search Engine<\/h4>\r\n\t\t\t\t<h5>David Koz\u00e1k<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/019\/19.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/019\/19_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal19\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">19<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Enticing \u2013 Semantic Search Engine<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>David Koz\u00e1k<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>search engine, semantic enhancement, MG4J, compiler, indexation, searching, annotation, big data<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Webov\u00e9 technologie<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>The topic of this paper is semantic searching over big textual data. It describes the design and implementation of a search engine Enticing that queries semantically enhanced documents efficiently and has a user friendly interface for working with the results. First, state of the art solutions along with their strengths and shortcomings are analyzed. Then a design for new search engine is presented along with a specialized query language EQL. The system consists of components for indexing and searching the documents, management server, compiler for the query language and two clients, web based and command line. The engine has been successfully designed, developed and deployed and is available via Internet. As a result of that, the possibility to use semantic searching is available to a wide audience.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/019\/19_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/019\/19.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/019\/19_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic01 topic07 topic12 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za dobr\u00e9 \u0159e\u0161en\u00ed \u0161k\u00e1lovateln\u00e9ho syst\u00e9mu pro sb\u011br a spr\u00e1vu adres kryptom\u011bn s vyu\u017eit\u00edm aktu\u00e1ln\u00edch technologi\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">1<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal1\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/001\/1_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Platform for Cryptocurrency Address Collection<\/h4>\r\n\t\t\t\t<h5>Vladislav Bambuch<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/001\/1.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/001\/1_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/F0Hrr62X_qU\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal1\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">1<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Platform for Cryptocurrency Address Collection<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Vladislav Bambuch<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>web scraping, cryptocurrencies, crypto crime detection, microservices, apache kafka, data streaming<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Bezpe\u010dnost<\/span> <span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e9 s\u00edt\u011b<\/span> <span class=\"label label-default\">Webov\u00e9 technologie<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>The goal of this work is to build a platform for collecting and displaying metadata about cryptocurrency addresses from public and also dark web. To achieve this goal, the author uses web parsing technologies written in PHP. Challenges accompanying a  website parsing are solved by scaling capabilities of Apache Kafka streaming platform. The modularity of the platform is accomplished by microservice architecture and Docker containerization.  The work creates a unique way how to search for potential crypto criminal activities, that appeared outside of the blockchain world, by building a web page application on top of this platform (that serves for managing the platform and exploring the extracted data). The platform architecture allows adding loosely coupled modules smoothly where the Apache Kafka mediates communication of the modules.   The result of this article is meant to be used for cybercrime detection and prevention. Its users can be law enforcement authorities or other agencies interested in reputations of cryptocurrency addresses.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/001\/1_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/001\/1.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/001\/1_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/F0Hrr62X_qU\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic03\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za precizn\u00ed popis mo\u017enost\u00ed pou\u017eit\u00ed technologi\u00ed Nix pro pr\u016fb\u011b\u017enou integraci a nasazen\u00ed p\u0159i v\u00fdvoji software\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">3<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal3\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/003\/3_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Vyu\u017eit\u00ed Nix\/NixOps pro pr\u016fb\u011b\u017enou integraci a nasazen\u00ed software p\u0159i v\u00fdvoji<\/h4>\r\n\t\t\t\t<h5>Tom\u00e1\u0161 Vlk<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/003\/3.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/003\/3_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal3\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">3<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Vyu\u017eit\u00ed Nix\/NixOps pro pr\u016fb\u011b\u017enou integraci a nasazen\u00ed software p\u0159i v\u00fdvoji<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Tom\u00e1\u0161 Vlk<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Continuous Integration, Continuous Deployment, Configuration Management, Infrastructure as Code, Nix, NixOS, NixOps<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Informa\u010dn\u00ed syst\u00e9my<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Tato pr\u00e1ce se zab\u00fdv\u00e1 uplatn\u011bn\u00edm funkcion\u00e1ln\u00edho bal\u00ed\u010dkovac\u00edho syst\u00e9mu Nix a jeho ekosyst\u00e9mu (NixOS, NixOps) pro CI\/CD p\u0159i agiln\u00edm v\u00fdvoji. P\u0159i pou\u017eit\u00ed t\u011bchto technologi\u00ed jsou probl\u00e9my zp\u016fsoben\u00e9 odli\u0161n\u00fdm prost\u0159ed\u00edm prakticky eliminov\u00e1ny bez nutnosti kontejnerizace. Pr\u00e1ce obsahuje popis mo\u017enost\u00ed a nedostatk\u016f Nix\/NixOps a navrhuje obecn\u00fd postup pou\u017eit\u00ed t\u011bchto technologi\u00ed pro jednotliv\u00e9 f\u00e1ze agiln\u00edho v\u00fdvoje a CI\/CD. D\u00edky Nix\/NixOps je implementace CI\/CD velmi jednoduch\u00e1 a cel\u00fd proces je nav\u00edc reprodukovateln\u00fd. V\u00fdstupem pr\u00e1ce je sada p\u0159\u00edklad\u016f demonstruj\u00edc\u00ed pou\u017eit\u00ed Nix\/NixOps v r\u016fzn\u00fdch projektech, a kter\u00e1 je dostupn\u00e1 jako open-source. D\u00edky t\u00e9to sad\u011b mohou v\u00fdvoj\u00e1\u0159i pou\u017e\u00edt Nix rychle a jednodu\u0161e v jak\u00e9mkoliv projektu, bez nutnosti studia velk\u00e9ho mno\u017estv\u00ed materi\u00e1l\u016f.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/003\/3_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/003\/3.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/003\/3_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic01 topic07\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"za zaj\u00edmav\u00e9 experiment\u00e1ln\u00ed v\u00fdsledky a potenci\u00e1ln\u00ed p\u0159\u00ednos v oblasti sledov\u00e1n\u00ed s\u00ed\u0165ov\u00fdch za\u0159\u00edzen\u00ed\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">8<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal8\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/008\/8_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Behavior-Based Network Device Tracking<\/h4>\r\n\t\t\t\t<h5>Michael Pol\u00e1k<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/008\/8.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/008\/8_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal8\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">8<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Behavior-Based Network Device Tracking<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Michael Pol\u00e1k<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Network Device Identification, k-Nearest Neighbors, Frequency Analysis<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Bezpe\u010dnost<\/span> <span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e9 s\u00edt\u011b<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>With the constantly growing number of devices on private and corporate networks, it is becoming increasingly more important for network administrators to track devices based on their behavior with limited feature availability due to the increasing security risks. This paper analyzes methods used to create device profiles that are subsequently used to identify devices using frequency analysis and the k-Nearest Neighbors algorithm with cosine similarity as the distance metric. Lastly, the results of this method are presented with possible improvements to the existing algorithm.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/008\/8_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/008\/8.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/008\/8_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div><div class=\"clearfix\"><\/div>\r\n\t<\/div>\r\n\t\r\n\t\r\n\t\r\n\t\r\n\r\n\t<h2 id=\"oceneni-partnery\">Ocen\u011bn\u00ed <strong>partnery z pr\u016fmyslu<\/strong><\/h2>\r\n\t<div class=\"row results\">\r\n\t\t<div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje bl\u00edzkost t\u00e9matu k aktu\u00e1ln\u011b \u0159e\u0161en\u00fdm v\u00fdzv\u00e1m na stran\u011b komer\u010dn\u00ed sf\u00e9ry a tak\u00e9 dosa\u017een\u00e9 v\u00fdsledky pr\u00e1ce, kter\u00e9 jsou inspirativn\u00ed.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">31<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal31\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/031\/31_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Counting Vehicles in Static Images<\/h4>\r\n\t\t\t\t<h5>Ond\u0159ej Zem\u00e1nek<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/031\/31.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/031\/31_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/generalni-partner\/camea.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal31\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">31<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Counting Vehicles in Static Images<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Ond\u0159ej Zem\u00e1nek<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>visual counting, vehicle counting in static images, car park dataset<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>This paper addresses the problem of counting vehicles in static images with no geometric information of the scene. Four convolutional neural network architectures were studied, implemented and trained as a main part of this work. Also, a dataset that consists of 19 310 images in total from 12 views that captures 7 different scenes were taken as part of this work. The trained networks map the appearance of the input sample to its corresponding vehicles density map, which can be easily translated to the vehicle count with keeping the localization of the vehicles in the input image. The main contribution of this work is in a comparison and application of the state-of-the-art solutions to the problem of object counting. Most of them were mainly designed to count pedestrians in crowded scenes or for medicine images, so the major goal was to adapt these solutions for vehicle counting task. The implemented models were trained on TRANCOS dataset which is a popular benchmark for counting vehicles on annotated low quality highway pictures. Their performance is compared and the results are discussed.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/031\/31_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/031\/31.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/031\/31_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje kvalitn\u00ed pr\u00e1ci a p\u0159\u00ednos v oblasti anal\u00fdzy v\u00edceprocesov\u00fdch syst\u00e9m\u016f.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">20<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal20\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h4>\r\n\t\t\t\t<h5>Monika Mu\u017eikovsk\u00e1<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/generalni-partner\/honeywell.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal20\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">20<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Monika Mu\u017eikovsk\u00e1<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>ANaConDA, Dynamick\u00e1 anal\u00fdza, Paraleln\u00ed chyby, V\u00edceprocesov\u00e9 programy<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Dynamick\u00e1 anal\u00fdza se s \u00fasp\u011bchem vyu\u017e\u00edv\u00e1 pro detekci chyb ve v\u00edcevl\u00e1knov\u00fdch programech. Algoritmy, kter\u00e9 byly za t\u00edmto \u00fa\u010delem navr\u017eeny, jsou ale \u010dasto vyu\u017eiteln\u00e9 i pro v\u00edceprocesov\u00e9 programy. \u017d\u00e1dn\u00fd ze zn\u00e1m\u00fdch n\u00e1stroj\u016f pro dynamickou anal\u00fdzu ale monitorov\u00e1n\u00ed proces\u016f nepodporuje. C\u00edlem t\u00e9to pr\u00e1ce bylo roz\u0161\u00ed\u0159it n\u00e1stroj ANaConDA o anal\u00fdzu a monitorov\u00e1n\u00ed v\u00edceprocesov\u00fdch program\u016f. V\u00fdsledkem je implementace roz\u0161\u00ed\u0159en\u00ed, kter\u00e9 za v\u00fdvoj\u00e1\u0159e analyz\u00e1tor\u016f \u0159e\u0161\u00ed probl\u00e9my spojen\u00e9 s odd\u011blen\u00fdmi adresov\u00fdmi prostory a synchronizac\u00ed pomoc\u00ed semafor\u016f. Roz\u0161\u00ed\u0159en\u00ed bylo vyu\u017eito pro \u00fapravu analyz\u00e1toru AtomRace pro detekci \u010dasov\u011b z\u00e1visl\u00fdch chyb nad daty ve v\u00edceprocesov\u00fdch programech a pou\u017eito na experimenty se studentsk\u00fdmi projekty z p\u0159edm\u011btu Opera\u010dn\u00ed syst\u00e9my. V\u00fdsledky experiment\u016f uk\u00e1zaly, \u017ee se n\u00e1stroj ANaConDA m\u016f\u017ee st\u00e1t v\u00edtan\u00fdm pomocn\u00edkem p\u0159i implementaci nejen v\u00edceprocesov\u00fdch projekt\u016f.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje kvalitn\u00ed pr\u00e1ci a p\u0159\u00ednos v oblasti statick\u00e9 anal\u00fdzy a detekce deadlock\u016f.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">12<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal12\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/012\/12_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Static Deadlock Detection in Frama-C<\/h4>\r\n\t\t\t\t<h5>Tom\u00e1\u0161 Dac\u00edk<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/012\/12.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/012\/12_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/generalni-partner\/honeywell.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal12\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">12<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Static Deadlock Detection in Frama-C<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Tom\u00e1\u0161 Dac\u00edk<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Static Analysis, Deadlock Detection, Frama-C<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Frama-C is a platform for static analysis of source codes written in the C language. It provides a wide range of analysers usually based on EVA - Frama-C's value analysis plugin. Despite some attempts to support analysis of multi-threaded code have been done in Frama-C, the whole platform is currently limited to analysis of sequential code only. In this paper, we present Deadlock, a new plugin of Frama-C focused on deadlock detection. Together with the core algorithm of deadlock detection, we present a technique our analyser uses to handle multi-threaded code partially as a sequential one, which allows us to improve the precision of our analysis by using existing plugins of Frama-C. In our experimental evaluation, we show that our tool is able to handle real-word C code with a high precision.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/012\/12_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/012\/12.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/012\/12_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje aktu\u00e1ln\u00ed mo\u017enost pou\u017eit\u00ed v\u00fdsledku v praxi: aplikace  je funk\u010dn\u00ed a u\u017eivatelsky p\u0159\u00edjemn\u00e1 a jednoduch\u00e1.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">9<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal9\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h4>\r\n\t\t\t\t<h5>Dominik Vagala<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/hlavni-partner\/artin.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal9\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">9<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Dominik Vagala<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Paint my room, Change wall color, N\u00e1h\u013ead farby na stene, Roz\u0161\u00edren\u00e1 realita, AR, ArCore, Mobiln\u00e1 aplik\u00e1cia, Android<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Cie\u013eom tejto pr\u00e1ce je n\u00e1vrh a implement\u00e1cia mobilnej aplik\u00e1cie pre Android, ktor\u00e1 by umo\u017e\u0148ovala meni\u0165 farby na stene pomocou roz\u0161\u00edrenej reality. U\u017e\u00edvate\u013e si tak m\u00f4\u017ee vysk\u00fa\u0161a\u0165 r\u00f4zne farby priamo v miestnosti kde sa nach\u00e1dza, a n\u00e1sledne sa rozhodn\u00fa\u0165, ktor\u00e1 farba sa mu tam najviac hod\u00ed na vyma\u013eovanie stien. Na rozpoznanie hran\u00edc steny je pou\u017eit\u00fd Sobelov detektor hr\u00e1n, kde sa ohrani\u010den\u00fd \u00fasek steny vyp\u013a\u0148a farbou pomocou upraven\u00e9ho Queue-Linear Flood Fill algoritmu. 2D s\u00faradnice, kde u\u017e\u00edvate\u013e klikol na stenu, sa pribli\u017ene prepo\u010d\u00edtaj\u00fa na 3D s\u00faradnice v priestore. Tie sa n\u00e1sledne sleduj\u00fa pomocou kni\u017enice ArCore, v\u010faka \u010domu stena zostane zafarben\u00e1 aj ke\u010f sa u\u017e\u00edvate\u013e pohybuje po miestnosti.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje \u0159e\u0161en\u00ed doposud nepokryt\u00e9ho probl\u00e9mu pr\u00e1ce pomoc\u00ed roz\u0161\u00ed\u0159en\u00ed existuj\u00edc\u00edch p\u0159\u00edstup\u016f a dal\u0161\u00ed mo\u017enosti vyu\u017eit\u00ed v praxi.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">20<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal20\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h4>\r\n\t\t\t\t<h5>Monika Mu\u017eikovsk\u00e1<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/hlavni-partner\/redhat.png?2\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal20\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">20<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Monika Mu\u017eikovsk\u00e1<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>ANaConDA, Dynamick\u00e1 anal\u00fdza, Paraleln\u00ed chyby, V\u00edceprocesov\u00e9 programy<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Dynamick\u00e1 anal\u00fdza se s \u00fasp\u011bchem vyu\u017e\u00edv\u00e1 pro detekci chyb ve v\u00edcevl\u00e1knov\u00fdch programech. Algoritmy, kter\u00e9 byly za t\u00edmto \u00fa\u010delem navr\u017eeny, jsou ale \u010dasto vyu\u017eiteln\u00e9 i pro v\u00edceprocesov\u00e9 programy. \u017d\u00e1dn\u00fd ze zn\u00e1m\u00fdch n\u00e1stroj\u016f pro dynamickou anal\u00fdzu ale monitorov\u00e1n\u00ed proces\u016f nepodporuje. C\u00edlem t\u00e9to pr\u00e1ce bylo roz\u0161\u00ed\u0159it n\u00e1stroj ANaConDA o anal\u00fdzu a monitorov\u00e1n\u00ed v\u00edceprocesov\u00fdch program\u016f. V\u00fdsledkem je implementace roz\u0161\u00ed\u0159en\u00ed, kter\u00e9 za v\u00fdvoj\u00e1\u0159e analyz\u00e1tor\u016f \u0159e\u0161\u00ed probl\u00e9my spojen\u00e9 s odd\u011blen\u00fdmi adresov\u00fdmi prostory a synchronizac\u00ed pomoc\u00ed semafor\u016f. Roz\u0161\u00ed\u0159en\u00ed bylo vyu\u017eito pro \u00fapravu analyz\u00e1toru AtomRace pro detekci \u010dasov\u011b z\u00e1visl\u00fdch chyb nad daty ve v\u00edceprocesov\u00fdch programech a pou\u017eito na experimenty se studentsk\u00fdmi projekty z p\u0159edm\u011btu Opera\u010dn\u00ed syst\u00e9my. V\u00fdsledky experiment\u016f uk\u00e1zaly, \u017ee se n\u00e1stroj ANaConDA m\u016f\u017ee st\u00e1t v\u00edtan\u00fdm pomocn\u00edkem p\u0159i implementaci nejen v\u00edceprocesov\u00fdch projekt\u016f.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic09 topic11\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje nalezen\u00ed \u0159e\u0161en\u00ed tohoto netrivi\u00e1ln\u00edho probl\u00e9mu a z\u00e1rove\u0148 jeho implementace a prezentace srozumitelnou formou.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">30<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal30\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h4>\r\n\t\t\t\t<h5>Adam Ferencz<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/hlavni-partner\/sewio.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal30\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">30<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Adam Ferencz<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed, Po\u010d\u00edta\u010dov\u00e9 vid\u011bn\u00ed, Konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, Keras, Leaflet, OpenStreetMap<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">U\u017eivatelsk\u00e1 rozhran\u00ed<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>C\u00edlem t\u00e9to pr\u00e1ce je umo\u017enit z\u00edskat v\u011brohodn\u00fd odhad po\u010dtu lid\u00ed v davu na demonstraci \u010di jin\u00e9 hromadn\u00e9 akci z n\u011bkolika fotografi\u00ed po\u0159\u00edzen\u00fdch dronem, \u010di jin\u00fdch fotografi\u00ed. V\u00fdsledkem jsou obarven\u00e9 \u010d\u00e1sti mapy podle hustoty lid\u00ed v dan\u00e9m m\u00edst\u011b. Jednotliv\u00e9 fotografie jsou d\u00e1ny do souvislosti s jejich um\u00edst\u011bn\u00edm do topologick\u00e9 mapy. Pro po\u010d\u00edt\u00e1n\u00ed lid\u00ed z fotky je pou\u017eita metoda konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, kter\u00e1 dok\u00e1\u017ee k fotografii vytvo\u0159it p\u0159\u00edslu\u0161nou mapu hustoty lid\u00ed. Integrace v\u00edce fotek dohromady se pak prov\u00e1d\u00ed transformac\u00ed do mapov\u00e9ho podkladu, \u010d\u00edm\u017e se vezme v potaz i rozm\u00edst\u011bn\u00ed davu v prostoru.   Aplikace je rozd\u011blena na server a webov\u00fd klient. Serverov\u00e1 \u010d\u00e1st se star\u00e1 o anal\u00fdzu davu a vytvo\u0159en\u00ed map hustoty k jednotliv\u00fdm obr\u00e1zk\u016fm. Toho dos\u00e1hne pomoc\u00ed natr\u00e9novan\u00e9ho modelu neuronov\u00e9 s\u00edt\u011b Multi-Column Convolutional Neural Network. Klient se pak krom\u011b vstupn\u00edch obr\u00e1zk\u016f star\u00e1 o jejich zobrazen\u00ed do mapy, p\u0159\u00edpadn\u011b modifikaci dat. V\u00fdsledkem je interaktivn\u00ed mapa, ve kter\u00e9 jsou um\u00edst\u011bn\u00e9 mapy hustoty davu.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje celkovou dota\u017eenost projektu a zam\u011b\u0159en\u00ed na praktick\u00e9 pot\u0159eby u\u017eivatele.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">9<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal9\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h4>\r\n\t\t\t\t<h5>Dominik Vagala<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/hlavni-partner\/thermo.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal9\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">9<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Dominik Vagala<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Paint my room, Change wall color, N\u00e1h\u013ead farby na stene, Roz\u0161\u00edren\u00e1 realita, AR, ArCore, Mobiln\u00e1 aplik\u00e1cia, Android<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>Cie\u013eom tejto pr\u00e1ce je n\u00e1vrh a implement\u00e1cia mobilnej aplik\u00e1cie pre Android, ktor\u00e1 by umo\u017e\u0148ovala meni\u0165 farby na stene pomocou roz\u0161\u00edrenej reality. U\u017e\u00edvate\u013e si tak m\u00f4\u017ee vysk\u00fa\u0161a\u0165 r\u00f4zne farby priamo v miestnosti kde sa nach\u00e1dza, a n\u00e1sledne sa rozhodn\u00fa\u0165, ktor\u00e1 farba sa mu tam najviac hod\u00ed na vyma\u013eovanie stien. Na rozpoznanie hran\u00edc steny je pou\u017eit\u00fd Sobelov detektor hr\u00e1n, kde sa ohrani\u010den\u00fd \u00fasek steny vyp\u013a\u0148a farbou pomocou upraven\u00e9ho Queue-Linear Flood Fill algoritmu. 2D s\u00faradnice, kde u\u017e\u00edvate\u013e klikol na stenu, sa pribli\u017ene prepo\u010d\u00edtaj\u00fa na 3D s\u00faradnice v priestore. Tie sa n\u00e1sledne sleduj\u00fa pomocou kni\u017enice ArCore, v\u010faka \u010domu stena zostane zafarben\u00e1 aj ke\u010f sa u\u017e\u00edvate\u013e pohybuje po miestnosti.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"thumbnail topic09 topic11\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"Partner oce\u0148uje \u0159e\u0161en\u00ed, kter\u00e9 zahrnuje nejen samotnou funk\u010dn\u00ed aplikaci vyu\u017e\u00edvaj\u00edc\u00ed konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b vhodn\u00e9 pro danou problematiku, ale tak\u00e9 u\u017eivatelsky jednoduch\u00e9 webov\u00e9 rozhran\u00ed, zjednodu\u0161uj\u00edc\u00ed pr\u00e1ci se samotnou aplikac\u00ed. Oce\u0148ujeme, \u017ee se student v r\u00e1mci pr\u00e1ce zab\u00fdval i u\u017eivatelskou p\u0159\u00edv\u011btivost\u00ed a nikoli pouze funk\u010dnost\u00ed sv\u00e9ho \u0159e\u0161en\u00ed.\">\r\n\t\t\t<div class=\"caption caption-image\">\r\n\t\t\t\t<span class=\"badge\">30<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal30\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/a>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"caption\">\r\n\t\t\t\t<h4>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h4>\r\n\t\t\t\t<h5>Adam Ferencz<\/h5>\r\n\t\t\t\t<p class=\"download-menu\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n\t\t\t<\/div>\r\n\t\t\t<div class=\"sponsor-logo\"><img src=\"\/wp-content\/partners\/2020\/hlavni-partner\/ysoft.png\"><\/div>\r\n\t\t<\/div>\r\n\t\t<div class=\"modal fade bs-example-modal-lg\" id=\"modal30\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n\t\t\t<div class=\"modal-dialog modal-lg\">\r\n\t\t\t\t<div class=\"modal-content\">\r\n\t\t\t\t\t<div class=\"modal-header\">\r\n\t\t\t\t\t\t<span class=\"badge\">30<\/span>\r\n\t\t\t\t\t\t<p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n\t\t\t\t\t\t<h3 class=\"modal-title\">Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h3>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-body\">\r\n\t\t\t\t\t\t<div class=\"row\">\r\n\t\t\t\t\t\t\t<div class=\"col-md-8\">\r\n\t\t\t\t\t\t\t\t<p><strong>Adam Ferencz<\/strong><\/p>\r\n\t\t\t\t\t\t\t\t<p><em>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed, Po\u010d\u00edta\u010dov\u00e9 vid\u011bn\u00ed, Konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, Keras, Leaflet, OpenStreetMap<\/em><\/p>\r\n\t\t\t\t\t\t\t\t<p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">U\u017eivatelsk\u00e1 rozhran\u00ed<\/span> <\/p>\r\n\t\t\t\t\t\t\t\t<p>C\u00edlem t\u00e9to pr\u00e1ce je umo\u017enit z\u00edskat v\u011brohodn\u00fd odhad po\u010dtu lid\u00ed v davu na demonstraci \u010di jin\u00e9 hromadn\u00e9 akci z n\u011bkolika fotografi\u00ed po\u0159\u00edzen\u00fdch dronem, \u010di jin\u00fdch fotografi\u00ed. V\u00fdsledkem jsou obarven\u00e9 \u010d\u00e1sti mapy podle hustoty lid\u00ed v dan\u00e9m m\u00edst\u011b. Jednotliv\u00e9 fotografie jsou d\u00e1ny do souvislosti s jejich um\u00edst\u011bn\u00edm do topologick\u00e9 mapy. Pro po\u010d\u00edt\u00e1n\u00ed lid\u00ed z fotky je pou\u017eita metoda konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, kter\u00e1 dok\u00e1\u017ee k fotografii vytvo\u0159it p\u0159\u00edslu\u0161nou mapu hustoty lid\u00ed. Integrace v\u00edce fotek dohromady se pak prov\u00e1d\u00ed transformac\u00ed do mapov\u00e9ho podkladu, \u010d\u00edm\u017e se vezme v potaz i rozm\u00edst\u011bn\u00ed davu v prostoru.   Aplikace je rozd\u011blena na server a webov\u00fd klient. Serverov\u00e1 \u010d\u00e1st se star\u00e1 o anal\u00fdzu davu a vytvo\u0159en\u00ed map hustoty k jednotliv\u00fdm obr\u00e1zk\u016fm. Toho dos\u00e1hne pomoc\u00ed natr\u00e9novan\u00e9ho modelu neuronov\u00e9 s\u00edt\u011b Multi-Column Convolutional Neural Network. Klient se pak krom\u011b vstupn\u00edch obr\u00e1zk\u016f star\u00e1 o jejich zobrazen\u00ed do mapy, p\u0159\u00edpadn\u011b modifikaci dat. V\u00fdsledkem je interaktivn\u00ed mapa, ve kter\u00e9 jsou um\u00edst\u011bn\u00e9 mapy hustoty davu.<\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t<div class=\"col-md-4\">\r\n\t\t\t\t\t\t\t\t<p><img class=\"img-responsive\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/p>\r\n\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t\t<div class=\"modal-footer\">\r\n\t\t\t\t\t\t<div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n\t\t\t\t\t\t<div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n\t\t\t\t\t<\/div>\r\n\t\t\t\t<\/div>\r\n\t\t\t<\/div>\r\n\t\t<\/div><div class=\"clearfix\"><\/div>\r\n\t<\/div>\r\n\t\r\n\t\r\n\r\n\t<h2 id=\"oceneni-odbornou-verejnosti-cena-jiriho-kunovskeho\">Ocen\u011bn\u00ed <strong>odbornou ve\u0159ejnost\u00ed<\/strong> - cena Ji\u0159\u00edho Kunovsk\u00e9ho<\/h2>\r\n        <div class=\"row results\">\r\n\t\t\t<div class=\"thumbnail topic09 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">29<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal29\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/029\/29_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>Improving robustness of neural networks against adversarial examples<\/h4>\r\n                    <h5>Martin Ga\u0148o<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/029\/29.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/029\/29_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal29\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">29<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">Improving robustness of neural networks against adversarial examples<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Martin Ga\u0148o<\/strong><\/p>\r\n                                    <p><em>Neural networks, Optimization, Machine learning<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n                                    <p>The main goal of this work is to design and implement the framework that yields robust neural network model against whatever adversarial attack, while result models accuracy is not signi\ufb01cantly lower comparing to naturally trained model. Our approach is to minimize maximization the loss function of the target model. Related work and our experiments lead us to the usage of Projected gradient descent method as a reference attack, therefore, we train against data generated by PGD. As a result, using the framework we can reach accuracy more than 90% against sophisticated adversarial attacks on MNIST dataset. The greatest contribution of this work is an implementation of adversarial attacks and defences against them because there misses any public implementation.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/029\/29_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/029\/29.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/029\/29_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div>\r\n            <div class=\"thumbnail topic06 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">9<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal9\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h4>\r\n                    <h5>Dominik Vagala<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal9\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">9<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">N\u00e1h\u013ead farby na stene pomocou roz\u0161\u00edrenej reality v mobile<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Dominik Vagala<\/strong><\/p>\r\n                                    <p><em>Paint my room, Change wall color, N\u00e1h\u013ead farby na stene, Roz\u0161\u00edren\u00e1 realita, AR, ArCore, Mobiln\u00e1 aplik\u00e1cia, Android<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e1 grafika<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n                                    <p>Cie\u013eom tejto pr\u00e1ce je n\u00e1vrh a implement\u00e1cia mobilnej aplik\u00e1cie pre Android, ktor\u00e1 by umo\u017e\u0148ovala meni\u0165 farby na stene pomocou roz\u0161\u00edrenej reality. U\u017e\u00edvate\u013e si tak m\u00f4\u017ee vysk\u00fa\u0161a\u0165 r\u00f4zne farby priamo v miestnosti kde sa nach\u00e1dza, a n\u00e1sledne sa rozhodn\u00fa\u0165, ktor\u00e1 farba sa mu tam najviac hod\u00ed na vyma\u013eovanie stien. Na rozpoznanie hran\u00edc steny je pou\u017eit\u00fd Sobelov detektor hr\u00e1n, kde sa ohrani\u010den\u00fd \u00fasek steny vyp\u013a\u0148a farbou pomocou upraven\u00e9ho Queue-Linear Flood Fill algoritmu. 2D s\u00faradnice, kde u\u017e\u00edvate\u013e klikol na stenu, sa pribli\u017ene prepo\u010d\u00edtaj\u00fa na 3D s\u00faradnice v priestore. Tie sa n\u00e1sledne sleduj\u00fa pomocou kni\u017enice ArCore, v\u010faka \u010domu stena zostane zafarben\u00e1 aj ke\u010f sa u\u017e\u00edvate\u013e pohybuje po miestnosti.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/009\/9_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/009\/9.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/009\/9_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/cf39K8Keqhc\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div>\r\n            <div class=\"thumbnail topic01\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">11<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal11\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/011\/11_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>Pokro\u010dil\u00e1 evaluace priv\u00e1tnosti na soci\u00e1ln\u00edch s\u00edt\u00edch<\/h4>\r\n                    <h5>Filip Janu\u0161<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/011\/11.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/011\/11_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal11\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">11<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">Pokro\u010dil\u00e1 evaluace priv\u00e1tnosti na soci\u00e1ln\u00edch s\u00edt\u00edch<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Filip Janu\u0161<\/strong><\/p>\r\n                                    <p><em>Soci\u00e1ln\u00ed s\u00ed\u0165, Soukrom\u00ed, Bezpe\u010dnost, Sk\u00f3re soukrom\u00ed, Nastaven\u00ed soukrom\u00ed<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Bezpe\u010dnost<\/span> <\/p>\r\n                                    <p>V dne\u0161n\u00ed dob\u011b st\u00e1le p\u0159etrv\u00e1v\u00e1 trend p\u0159esunu mezilidsk\u00e9 komunikace do online prost\u0159ed\u00ed. A to d\u00edky soci\u00e1ln\u00edm s\u00edt\u00edm a slu\u017eb\u00e1m jimi poskytovan\u00fdmi. S t\u00edmto faktem souvis\u00ed i rostouc\u00ed po\u010det u\u017eivatel\u016f soci\u00e1ln\u00edch s\u00edt\u00ed. Mnoho u\u017eivatel\u016f ov\u0161em nevn\u00edm\u00e1 rizika spojen\u00e1 s p\u0159\u00edtomnost\u00ed v internetov\u00e9m prost\u0159ed\u00ed. Tato pr\u00e1ce se zam\u011b\u0159uje na anal\u00fdzu bezpe\u010dnostn\u00edch nastaven\u00ed u\u017eivatelsk\u00fdch \u00fa\u010dt\u016f soci\u00e1ln\u00edch s\u00edt\u00ed a n\u00e1sledn\u00e9 vyhodnocen\u00ed tohoto nastaven\u00ed. C\u00edlem pr\u00e1ce je vytvo\u0159it n\u00e1stroj poskytuj\u00edc\u00ed mo\u017enost vyhodnotit bezpe\u010dnostn\u00ed nastaven\u00ed u\u017eivatelsk\u00e9ho \u00fa\u010dtu na soci\u00e1ln\u00ed s\u00edti p\u0159\u00edpadn\u011b doporu\u010dit vhodn\u011bj\u0161\u00ed nastaven\u00ed s ohledem na soukrom\u00ed u\u017eivatele. Aby bylo mo\u017en\u00e9 dos\u00e1hnout t\u011bchto c\u00edl\u016f, je pot\u0159ebn\u00e9 pou\u017e\u00edt vhodn\u00fd model prov\u00e1d\u011bj\u00edc\u00ed vy\u010d\u00edslen\u00ed sk\u00f3re priv\u00e1tnosti. V\u00fdstupem pr\u00e1ce bude n\u00e1vrh a implementace n\u00e1stroje prov\u00e1d\u011bj\u00edc\u00ed anal\u00fdzu, vyhodnocen\u00ed a doporu\u010den\u00ed, jak vylep\u0161it sv\u00e9 nastaven\u00ed soukrom\u00ed na soci\u00e1ln\u00ed s\u00edti. Co\u017e by m\u011blo pomoci u\u017eivateli omezit mno\u017estv\u00ed unikl\u00fdch citliv\u00fdch informac\u00ed.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/011\/11_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/011\/11.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/011\/11_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div>\r\n            <div class=\"thumbnail topic10\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">20<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal20\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h4>\r\n                    <h5>Monika Mu\u017eikovsk\u00e1<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal20\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">20<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">Detekce paraleln\u00edch chyb ve v\u00edceprocesov\u00fdch programech<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Monika Mu\u017eikovsk\u00e1<\/strong><\/p>\r\n                                    <p><em>ANaConDA, Dynamick\u00e1 anal\u00fdza, Paraleln\u00ed chyby, V\u00edceprocesov\u00e9 programy<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Testov\u00e1n\u00ed, anal\u00fdza a verifikace<\/span> <\/p>\r\n                                    <p>Dynamick\u00e1 anal\u00fdza se s \u00fasp\u011bchem vyu\u017e\u00edv\u00e1 pro detekci chyb ve v\u00edcevl\u00e1knov\u00fdch programech. Algoritmy, kter\u00e9 byly za t\u00edmto \u00fa\u010delem navr\u017eeny, jsou ale \u010dasto vyu\u017eiteln\u00e9 i pro v\u00edceprocesov\u00e9 programy. \u017d\u00e1dn\u00fd ze zn\u00e1m\u00fdch n\u00e1stroj\u016f pro dynamickou anal\u00fdzu ale monitorov\u00e1n\u00ed proces\u016f nepodporuje. C\u00edlem t\u00e9to pr\u00e1ce bylo roz\u0161\u00ed\u0159it n\u00e1stroj ANaConDA o anal\u00fdzu a monitorov\u00e1n\u00ed v\u00edceprocesov\u00fdch program\u016f. V\u00fdsledkem je implementace roz\u0161\u00ed\u0159en\u00ed, kter\u00e9 za v\u00fdvoj\u00e1\u0159e analyz\u00e1tor\u016f \u0159e\u0161\u00ed probl\u00e9my spojen\u00e9 s odd\u011blen\u00fdmi adresov\u00fdmi prostory a synchronizac\u00ed pomoc\u00ed semafor\u016f. Roz\u0161\u00ed\u0159en\u00ed bylo vyu\u017eito pro \u00fapravu analyz\u00e1toru AtomRace pro detekci \u010dasov\u011b z\u00e1visl\u00fdch chyb nad daty ve v\u00edceprocesov\u00fdch programech a pou\u017eito na experimenty se studentsk\u00fdmi projekty z p\u0159edm\u011btu Opera\u010dn\u00ed syst\u00e9my. V\u00fdsledky experiment\u016f uk\u00e1zaly, \u017ee se n\u00e1stroj ANaConDA m\u016f\u017ee st\u00e1t v\u00edtan\u00fdm pomocn\u00edkem p\u0159i implementaci nejen v\u00edceprocesov\u00fdch projekt\u016f.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/020\/20_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/020\/20.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/020\/20_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div>\r\n            <div class=\"thumbnail topic01 topic07 topic12 topic13\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">1<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal1\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/001\/1_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>Platform for Cryptocurrency Address Collection<\/h4>\r\n                    <h5>Vladislav Bambuch<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/001\/1.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/001\/1_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/F0Hrr62X_qU\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal1\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">1<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">Platform for Cryptocurrency Address Collection<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Vladislav Bambuch<\/strong><\/p>\r\n                                    <p><em>web scraping, cryptocurrencies, crypto crime detection, microservices, apache kafka, data streaming<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Bezpe\u010dnost<\/span> <span class=\"label label-default\">Po\u010d\u00edta\u010dov\u00e9 s\u00edt\u011b<\/span> <span class=\"label label-default\">Webov\u00e9 technologie<\/span> <span class=\"label label-default\">Zpracov\u00e1n\u00ed dat (obraz, zvuk, text apod.)<\/span> <\/p>\r\n                                    <p>The goal of this work is to build a platform for collecting and displaying metadata about cryptocurrency addresses from public and also dark web. To achieve this goal, the author uses web parsing technologies written in PHP. Challenges accompanying a  website parsing are solved by scaling capabilities of Apache Kafka streaming platform. The modularity of the platform is accomplished by microservice architecture and Docker containerization.  The work creates a unique way how to search for potential crypto criminal activities, that appeared outside of the blockchain world, by building a web page application on top of this platform (that serves for managing the platform and exploring the extracted data). The platform architecture allows adding loosely coupled modules smoothly where the Apache Kafka mediates communication of the modules.   The result of this article is meant to be used for cybercrime detection and prevention. Its users can be law enforcement authorities or other agencies interested in reputations of cryptocurrency addresses.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/001\/1_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/001\/1.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/001\/1_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/F0Hrr62X_qU\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div>\r\n            <div class=\"thumbnail topic09 topic11\" data-toggle=\"tooltip\" data-placement=\"top\" title=\"\">\r\n                <div class=\"caption caption-image\">\r\n                    <span class=\"badge\">30<\/span><a href=\"#\" data-toggle=\"modal\" data-target=\"#modal30\"><img class=\"thumbnail-icon\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/a>\r\n                <\/div>\r\n                <div class=\"caption\">\r\n                    <h4>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h4>\r\n                    <h5>Adam Ferencz<\/h5>\r\n                    <p class=\"download-menu\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"32\" height=\"32\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"32\" height=\"32\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"32\" height=\"32\" alt=\"Video\"><\/a><\/p>\r\n                <\/div>\r\n                \r\n            <\/div>\r\n            <div class=\"modal fade bs-example-modal-lg\" id=\"modal30\" tabindex=\"-1\" role=\"dialog\" aria-hidden=\"true\">\r\n                <div class=\"modal-dialog modal-lg\">\r\n                    <div class=\"modal-content\">\r\n                        <div class=\"modal-header\">\r\n                            <span class=\"badge\">30<\/span>\r\n                            <p><button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">\u00d7<\/span><\/button><\/p>\r\n                            <h3 class=\"modal-title\">Po\u010d\u00edt\u00e1n\u00ed lid\u00ed v davu pomoc\u00ed neuronov\u00fdch s\u00edt\u00ed s integrac\u00ed do mapy<\/h3>\r\n                        <\/div>\r\n                        <div class=\"modal-body\">\r\n                            <div class=\"row\">\r\n                                <div class=\"col-md-8\">\r\n                                    <p><strong>Adam Ferencz<\/strong><\/p>\r\n                                    <p><em>Po\u010d\u00edt\u00e1n\u00ed lid\u00ed, Po\u010d\u00edta\u010dov\u00e9 vid\u011bn\u00ed, Konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, Keras, Leaflet, OpenStreetMap<\/em><\/p>\r\n                                    <p><span class=\"label label-default\">Robotika a um\u011bl\u00e1 inteligence<\/span> <span class=\"label label-default\">U\u017eivatelsk\u00e1 rozhran\u00ed<\/span> <\/p>\r\n                                    <p>C\u00edlem t\u00e9to pr\u00e1ce je umo\u017enit z\u00edskat v\u011brohodn\u00fd odhad po\u010dtu lid\u00ed v davu na demonstraci \u010di jin\u00e9 hromadn\u00e9 akci z n\u011bkolika fotografi\u00ed po\u0159\u00edzen\u00fdch dronem, \u010di jin\u00fdch fotografi\u00ed. V\u00fdsledkem jsou obarven\u00e9 \u010d\u00e1sti mapy podle hustoty lid\u00ed v dan\u00e9m m\u00edst\u011b. Jednotliv\u00e9 fotografie jsou d\u00e1ny do souvislosti s jejich um\u00edst\u011bn\u00edm do topologick\u00e9 mapy. Pro po\u010d\u00edt\u00e1n\u00ed lid\u00ed z fotky je pou\u017eita metoda konvolu\u010dn\u00ed neuronov\u00e9 s\u00edt\u011b, kter\u00e1 dok\u00e1\u017ee k fotografii vytvo\u0159it p\u0159\u00edslu\u0161nou mapu hustoty lid\u00ed. Integrace v\u00edce fotek dohromady se pak prov\u00e1d\u00ed transformac\u00ed do mapov\u00e9ho podkladu, \u010d\u00edm\u017e se vezme v potaz i rozm\u00edst\u011bn\u00ed davu v prostoru.   Aplikace je rozd\u011blena na server a webov\u00fd klient. Serverov\u00e1 \u010d\u00e1st se star\u00e1 o anal\u00fdzu davu a vytvo\u0159en\u00ed map hustoty k jednotliv\u00fdm obr\u00e1zk\u016fm. Toho dos\u00e1hne pomoc\u00ed natr\u00e9novan\u00e9ho modelu neuronov\u00e9 s\u00edt\u011b Multi-Column Convolutional Neural Network. Klient se pak krom\u011b vstupn\u00edch obr\u00e1zk\u016f star\u00e1 o jejich zobrazen\u00ed do mapy, p\u0159\u00edpadn\u011b modifikaci dat. V\u00fdsledkem je interaktivn\u00ed mapa, ve kter\u00e9 jsou um\u00edst\u011bn\u00e9 mapy hustoty davu.<\/p>\r\n                                <\/div>\r\n                                <div class=\"col-md-4\">\r\n                                    <p><img class=\"img-responsive\" src=\"\/submissions\/2020\/030\/30_nahled.png\" alt=\"\"><\/p>\r\n                                <\/div>\r\n                            <\/div>\r\n                        <\/div>\r\n                        <div class=\"modal-footer\">\r\n                            <div class=\"pull-left\"><div class=\"btn-group\" role=\"group\"><a href=\"\/submissions\/2020\/030\/30.pdf\"><img src=\"\/submissions\/images\/paper-icon.png\" width=\"48\" height=\"48\" alt=\"\u010cl\u00e1nek\"><\/a><a href=\"\/submissions\/2020\/030\/30_poster.pdf\"><img src=\"\/submissions\/images\/poster-icon.png\" width=\"48\" height=\"48\" alt=\"Plak\u00e1t\"><\/a><a href=\"https:\/\/youtu.be\/EC44IQeqK00\"><img src=\"\/submissions\/images\/video-icon.png\" width=\"48\" height=\"48\" alt=\"Video\"><\/a><\/div><\/div>\r\n                            <div class=\"pull-right\"><button type=\"button\" class=\"btn btn-primary\" data-dismiss=\"modal\">Zav\u0159\u00edt<\/button><\/div>\r\n                        <\/div>\r\n                    <\/div>\r\n                <\/div>\r\n            <\/div><div class=\"clearfix\"><\/div>\r\n\t<\/div>\r\n<script>\t\t\t\t\t\t\t\r\njQuery(function() {\r\n  jQuery('[data-toggle=\"tooltip\"]').tooltip()\r\n})\t\r\n<\/script>\r\n\r\n\r\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":2,"featured_media":2982,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"ngg_post_thumbnail":0,"footnotes":""},"class_list":["post-1989","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/pages\/1989","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/comments?post=1989"}],"version-history":[{"count":32,"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/pages\/1989\/revisions"}],"predecessor-version":[{"id":3195,"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/pages\/1989\/revisions\/3195"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/media\/2982"}],"wp:attachment":[{"href":"https:\/\/excel.fit.vutbr.cz\/2020\/wp-json\/wp\/v2\/media?parent=1989"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}