[{"command":"settings","settings":{"pluralDelimiter":"\u0003","suppressDeprecationErrors":true,"user":{"uid":0,"permissionsHash":"d9587e6f410d2e7f476e3da6cb10a457c78ab82347f962bf83d9020620f901dd"}},"merge":true},{"command":"add_css","data":[{"rel":"stylesheet","media":"all","href":"\/modules\/contrib\/addtocal\/addtocal.css?t2408i"},{"rel":"stylesheet","media":"all","href":"\/themes\/custom\/cest2025\/css\/components\/node.css?t2408i"}]},{"command":"add_js","selector":"body","data":[{"src":"\/core\/assets\/vendor\/jquery\/jquery.min.js?v=3.7.1"},{"src":"\/core\/assets\/vendor\/once\/once.min.js?v=1.0.1"},{"src":"\/core\/misc\/drupalSettingsLoader.js?v=10.5.1"},{"src":"\/core\/misc\/drupal.js?v=10.5.1"},{"src":"\/core\/misc\/drupal.init.js?v=10.5.1"},{"src":"\/modules\/contrib\/addtocal\/addtocal.js?v=10.5.1"},{"src":"\/modules\/contrib\/addtocal\/addtocal-download.js?v=10.5.1"}]},{"command":"openDialog","selector":"#drupal-modal","settings":null,"data":"\n\u003Carticle class=\u0022node node--type-presentation node--promoted node--view-mode-modal\u0022\u003E\n  \n      \u003Cb\u003E\u003Cspan\u003EThe use of the BigML platform for the analysis of geological-mining parameters influencing the rockbursts hazard\u003C\/span\u003E\n\u003C\/b\u003E\n  \n      \u003Cdiv\u003E\u003Cb\u003ECEST ID: cest2025_00475\u003C\/b\u003E\u003C\/div\u003E\n  \n        \u003Cdiv class=\u0022mb-3\u0022\u003E\n      \u003Cb\u003ERoom  | Sat 6 Sep 2025 | 17:00 - 18:00 pm\u003C\/b\u003E\n    \u003C\/div\u003E\n  \n          \n    \n  \n      \u003Cdiv class=\u0022mt-10\u0022\u003E\n            \u003Cdiv class=\u0022clearfix text-formatted field field--name-presentation-body field--type-text-long field--label-hidden field__item\u0022\u003EAn analysis of geological-mining parameters, characterizing rockbursts that occurred in the mines of the Upper Silesian Coal Basin, was carried out using the BigML machine learning platform. The analyses included data relating to selected groups of parameters: structural, mechanical and geometric, characterizing the conditions of occurrence of rockburst hazard. The collected were used to build machine learning models for predicting the values of selected parameters of the effects of rockbursts, i.e. distance between the focus and the effect of a seismic tremor (1) and the length of damage and\/or destruction of the excavations (2). Models based on a decision tree and a random decision forest were developed for each of the predicted parameters. The performance of the models was then determined on test data. For both forecast parameters, better results were obtained using the random decision forest. The R2 coefficients of determination of the developed models were 0.782 and 0.883 for the (1) and (2) parameter respectively.\u003C\/div\u003E\n      \u003C\/div\u003E\n  \n  \u003Cdiv class=\u0022mt-5 mb-5\u0022\u003E\n          \u003Cspan\u003E\n          \u003Cb\u003EPresenter:\u003C\/b\u003E\n                      \u003Cp\u003E\n            Dr Marta Skiba\n            \u003C\/p\u003E\n                  \u003C\/span\u003E\n      \u003C\/div\u003E\n\n  \u003Cdiv class=\u0022mb-5\u0022\u003E\n          \u003Cdiv class=\u0022field__label\u0022\u003E\n        Authors\n      \u003C\/div\u003E\n              \u003Cp\u003E\n          Marta Skiba\n        \u003C\/p\u003E\n              \u003Cp\u003E\n          Pawe\u0142 Baran\n        \u003C\/p\u003E\n            \u003C\/div\u003E\n\n\u003C\/article\u003E\n","dialogOptions":{"width":"700","position":{"my":"right top","at":"right top"},"closeOnEscape":true,"dialogClass":"presentation-dialog","modal":true,"title":"","classes":{"ui-dialog":"presentation-dialog"}}}]