{"id":51124,"date":"2026-05-19T12:28:05","date_gmt":"2026-05-19T10:28:05","guid":{"rendered":"https:\/\/riteh.uniri.hr\/?p=51124"},"modified":"2026-05-29T11:56:41","modified_gmt":"2026-05-29T09:56:41","slug":"doctoral-candidate-ervin-ceperic-successfully-defended-his-doctoral-dissertation","status":"publish","type":"post","link":"https:\/\/riteh.uniri.hr\/en\/novosti\/doctoral-candidate-ervin-ceperic-successfully-defended-his-doctoral-dissertation\/","title":{"rendered":"Doctoral Candidate Ervin \u010ceperi\u0107 Successfully Defended his Doctoral Dissertation"},"content":{"rendered":"\n<p>This dissertation develops a unified methodological framework for short-term forecasting in energy systems based on Support Vector Regression (SVR). The proposed framework integrates systematic feature engineering, data-driven feature selection procedures, and tailored hyperparameter optimization strategies. In the STLF domain, a seasonality-adjusted model (SSA-SVR, Strategic Seasonality-Adjusted SVR) and a hybrid DNN\u2013SVR model are developed, combining the representational capabilities of deep neural networks with the generalization properties of SVR. To enhance forecasting precision, a structure of separate hour-specific submodels is established. In the ST-NGPF domain, a seasonality-adjusted SVR framework is applied and adapted to the specific dynamics and volatility of market data. Empirical validation is conducted on multiple real-world datasets. The research results demonstrate that the proposed models systematically outperform benchmark statistical and standalone machine learning models.<\/p>\n\n\n\n<p>The doctoral dissertation was supervised by Prof. Kristijan Lenac with Prof. Vlahini\u0107, serving as co-supervisor.<\/p>\n\n\n\n<p>The Doctoral Dissertation Defense Committee consisted of: Prof. Goran Mau\u0161a (Chair), Assoc. Prof. Vedran Kirin\u010di\u0107 (Member) &#8211; both from the Faculty of Engineering, University of Rijeka &#8211; and Prof. Juraj Havelka (Member) from the Faculty of Electrical Engineering and Computing, University of Zagreb.<\/p>\n\n\n\n<p>Congratulations to our colleague!<\/p>\n","protected":false},"excerpt":{"rendered":"<p>On May 15th 2026, doctoral candidate Ervin \u010ceperi\u0107 successfully completed his Doctoral Study Programme after defending his doctoral dissertation titled &#8220;Support Vector Machine-based Predictive Models for Energy Systems&#8221;.<\/p>\n","protected":false},"author":65,"featured_media":50882,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[211],"tags":[],"class_list":["post-51124","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"acf":[],"_links":{"self":[{"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/posts\/51124","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/users\/65"}],"replies":[{"embeddable":true,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/comments?post=51124"}],"version-history":[{"count":1,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/posts\/51124\/revisions"}],"predecessor-version":[{"id":51125,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/posts\/51124\/revisions\/51125"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/media\/50882"}],"wp:attachment":[{"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/media?parent=51124"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/categories?post=51124"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/riteh.uniri.hr\/en\/wp-json\/wp\/v2\/tags?post=51124"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}