1. The role of intelligent data analysis in selected endurance sports : a systematic literature reviewAlen Rajšp, Patrik Rek, Peter Kokol, Iztok Fister, 2025, pregledni znanstveni članek Opis: In endurance sports, athletes and coaches shift increasingly from intuition-based decisionmaking to data-driven approaches powered by modern technology and analytics. Since 2018, the field has experienced significant advances, influencing endurance sports disciplines. This systematic literature review identified 75 peer-reviewed studies on intelligent data analysis in endurance sports training. Each study was categorized by its intelligent method (e.g., machine learning, deep learning, computational intelligence), the types of sensors and wearables used, and the specific training application and approach. Our synthesis reveals that machine learning and deep learning are among the most used approaches, with running and cycling identified as the most extensively studied sports. Physiological and environmental data, such as heart rate, biomechanical signals, and GPS, are often used to aid in generating personalized training plans, predicting injuries, and increasing athletes’ long-term performance. Despite these advancements, challenges remain, related to data quality and the small participant sample sizes.
Ključne besede: smart sports training, endurance sports, intelligent data analysis, machine learning, artificial intelligence, computational intelligence, systematic literature review
Objavljeno v DKUM: 02.10.2025; Ogledov: 0; Prenosov: 7
 Celotno besedilo (655,98 KB) |
2. Impact of developer queries on the effectiveness of conversational large language models in programmingViktor Taneski, Sašo Karakatič, Patrik Rek, Gregor Jošt, 2025, izvirni znanstveni članek Opis: This study investigates the effects of LLM-based coding assistance on web application development by students using a frontend framework. Rather than comparing different models, it focuses on how students interact with LLM tools to isolate the impact of query type on coding success. To this end, participants were instructed to rely exclusively on LLMs for writing code, based on a given set of specifications, and their queries were categorized into seven types: Error Fixing (EF), Feature Implementation (FI), Code Optimization (CO), Code Understanding (CU), Best Practices (BP), Documentation (DOC), and Concept Clarification (CC). The results reveal that students who queried LLMs for error fixing (EF) were statistically more likely to have runnable code, regardless of prior knowledge. Additionally, students seeking code understanding (CU) and error fixing performed better, even when normalizing for previous coding ability. These findings suggest that the nature of the queries made to LLMs influences the success of programming tasks and provides insights into how AI tools can assist learning in software development.
Ključne besede: large language models, LLMs, prompt engineering, query type analysis, AI-assisted programming, educational software development
Objavljeno v DKUM: 23.06.2025; Ogledov: 0; Prenosov: 12
Celotno besedilo (994,41 KB)
Gradivo ima več datotek! Več... |
3. Analiza kompleksnosti uporabe orodja Vortex za ustvarjanje celovitih rešitev decentraliziranih aplikacij : magistrsko deloPatrik Rek, 2019, magistrsko delo Opis: Decentralizirane aplikacije predstavljajo hitro napredujočo tehnologijo. Njihovo trenutno stanje je še v dokaj začetnih fazah, kar pomeni, da je njihov razvoj, sicer šibkeje dokumentiran, tudi precej kompleksen. S tem namenom so nastala orodja za razvoj celovitih rešitev decentraliziranih aplikacij. Eno takšnih orodij je tudi orodje Vortex, ki smo ga v magistrskem delu natančneje raziskali. Razvili smo primer aplikacije brez
uporabe povezovalnih orodij in z uporabo orodja Vortex ter primerjali kompleksnost kode s pomočjo različnih metrik. Ugotovili smo, da se kompleksnost kode z uporabo orodja Vortex ne zmanjša, razvijalcem pa orodje prinaša druge prednosti, ki smo jih opisali v nalogi.
Ključne besede: JavaScript, tehnologija veriženja blokov, decentralizirane aplikacije, Web3, Ethereum
Objavljeno v DKUM: 12.07.2019; Ogledov: 2360; Prenosov: 224
Celotno besedilo (1,73 MB) |
4. Vtičnik Visual Studio za oblikovanje in pregledovanje spletnih vmesnikovPatrik Rek, 2017, diplomsko delo Opis: Visual Studio je priljubljeno orodje za razvoj različnih aplikacij. Uporablja se tudi za oblikovanje spletnih vmesnikov HTML. Njegova pomanjkljivost je spletni brskalnik za predogled, ki ni prilagojen novim standardom. Zato smo ustvarili vtičnik, ki v Visual Studio vključi brskalnik Chromium. V diplomskem delu smo raziskali rešitev za vgradnjo brskalnika v aplikacije .NET in trenutne primere vtičnikov za Visual Studio, na katerih smo zasnovali svoj vtičnik. Uporabili smo orodje CEFSharp za vgradnjo brskalnika, ki prikaže trenutno odprt dokument HTML in se osveži ob vsakem shranjevanju.
Ključne besede: Visual Studio, dodatek, spletno oblikovanje, brskalnik po meri
Objavljeno v DKUM: 06.10.2017; Ogledov: 1204; Prenosov: 112
Celotno besedilo (2,23 MB) |
