1. Model za ocenjevanje vrednosti projektov razvoja spletnih programskih rešitevNina Milinković, 2024, magistrsko delo Opis: V nalogi predstavljamo zasnovo in implementacijo modela multiple linearne regresije v »Podjetju X«, ki se ukvarja z razvojem spletnih programskih rešitev. Model je bil zasnovan za izboljšanje natančnosti pri napovedovanju presežka ur v projektih, kar omogoča boljše planiranje in oceno projektov. S sistematično analizo podatkov iz preteklih projektov in oblikovanjem vprašalnika, ki upošteva ključna področja, kot so «inovativne rešitve in razvoj«, «upravljanje in vodenje«, »infrastruktura in procesi« ter »ocenjevanje in odnosi s strankami«, in pripadajoče parametre smo razvili model, ki omogoča natančnejše planiranje in ocenjevanje prihodnjih projektov. Model multiple linearne regresije smo razvili v skladu s smernicami za razvoj linearnih regresijskih modelov, ki vključujejo preverjanje sedmih ključnih predpostavk ustreznosti modela, ki smo jih v nalogi potrdili. Za validacijo modela smo uporabili metodo validacije s pomočjo prilagojenega koeficienta determinacije in validacijo ponovnega vzorčenja z zamenjavo –, model pa smo testirali na dejanskem primeru projekta v »Podjetju X«. Rezultati validacije s statističnimi metodami kažejo na statistično značilne korelacije v obeh vzorcih, kar potrjuje, da so napovedi modela tesno usklajene z dejanskimi podatki. Validacija na konkretnem primeru pa je pokazala, da uvedba modela multiple linearne regresije uspešno napoveduje presežek ur že pred začetkom projekta. Z napovedjo, ki od dejanskega stanja glede presežka ur odstopa za le 3 odstotke, model zmanjšuje izgube zaradi neoptimalnega napovedovanja ur pri projektih in podjetju potencialno omogoča ustvarjanje dodatnega zaslužka – če seveda podjetje dodatne ure proda.
Ključne besede: Planiranje in ocenjevanje vrednosti projekta, model multiple linearne regresije, projektni vodja, spletne programske rešitve.
Objavljeno v DKUM: 05.06.2025; Ogledov: 0; Prenosov: 3
 Celotno besedilo (3,95 MB) |
2. Razvoj modela vključenosti mladih pri vpeljavi ciljev trajnostnega razvojaTatjana Borojević, 2024, doktorska disertacija Opis: Predmet doktorske disertacije je razvoj modela za povečanje sodelovanja mladih pri doseganju ciljev trajnostnega razvoja (SD) in trajnostnega razvoja (SDG). Rezultati, pridobljeni z izvedeno raziskavo, so pripomogli k prepoznavanju soodvisnosti ter opredelitvi elementov in dejavnikov, ki naj bodo izhodišče za aktivnejše sodelovanje mladih pri doseganju ciljev trajnostnega razvoja in področij trajnostnega razvoja.
Mladi imajo odločilno vlogo pri učinkovitem oblikovanju in izvajanju politik in strategij SD. Glede na aktualne družbene, ekonomske in okoljske izzive je potrebno mlade prepoznati kot nosilce insektnih sprememb in bodoče voditelje na tem ključnem področju, ki bodo omogočili otipljive rezultate v SD.
Rezultati raziskav so pokazali, da na stopnjo sodelovanja mladih pri doseganju ciljev trajnostnega razvoja ugodno vpliva vzpostavljen institucionalni okvir (na nacionalni in lokalni ravni). Razvoj modelov participacije mladih pomeni visoko stopnjo ozaveščenosti in znanja o SD ter pozitiven odnos mladih do SD. Na ta način so pridobljeni predpogoji za proces določanja prednostnih ciljev trajnostnega razvoja. Glede na to, da imajo številne lokalne skupnosti omejena sredstva za uresničevanje vseh ciljev trajnostnega razvoja, je opredelitev prioritet neizogiben in nujen proces.
Ključne besede: sodelovanje mladih, SD, cilji trajnostnega razvoja, model za povečanje sodelovanja mladih pri doseganju ciljev trajnostnega razvoja
Objavljeno v DKUM: 05.06.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (3,73 MB) |
3. Določitev večplastnega modela zemlje z optimizacijskimi metodami : magistrsko deloNejc Gošnjak, 2025, magistrsko delo Opis: Magistrska naloga obravnava večplastne modele zemlje in strategije diferencialne evolucije na raznolikih testnih podatkih. Cilj je določiti najprimernejšo strategijo in večplastni model za testne podatke. Uporabljene so 3 optimizacijske metode, ki so med seboj primerjane. Primerjajo se DE/best/1/bin, DE/rand/1/bin in DE/rand/1/exp. Med seboj se tudi primerjajo 2, 3, 4, 5 in 6 plastni modeli. Za čim bolj raznolike vhodne podatke je uporabljenih šest različnih kompletov testnih podatkov za določitev parametrov zemlje. Ker izračuni delujejo na osnovi naključnih vrednosti, se pri istih začetnih pogojih rezultati med seboj po navadi razlikujejo. Da bi se zmanjšal vpliv naključja se vsak izračun ponovi 30 krat.
Ključne besede: večplastni model zemlje, diferencialna evolucija
Objavljeno v DKUM: 03.06.2025; Ogledov: 0; Prenosov: 11
Celotno besedilo (1,76 MB) |
4. Omissions by design in a survey : is this a good choice when using Structural Equation Models?Paula Cristina Ribeiro Vicente, 2024, izvirni znanstveni članek Opis: Missing observations can arise due to the effort required to answer many questions in long surveys and the cost required to obtain some responses. Implementing a planned missing design in surveys helps reduce the number of questions each respondent needs to answer, thereby lowering survey fatigue and cutting down on implementation costs. The three-form and the two-method design are two different types of planned missing designs. An important consideration when designing a study with omissions by design is to know how it will affect statistical results. In this work, a simulation study is conducted to analyze how the usual fit measures, root mean square error of approximation (RMSEA), standardized root mean square residual (SRMR), comparative fit index (CFI), and Tucker-Lewis index (TLI) perform in the adjustment of a Structural Equation Model. The results revealed that the CFI, TLI, and SRMR indices exhibit sensitivity to omissions with small samples, low factor loadings and large models. Overall, this study contributes to our understanding of the importance of considering omissions by design in market research.
Ključne besede: omissions by design, Structural Equation Model, survey
Objavljeno v DKUM: 02.06.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (548,29 KB)
Gradivo ima več datotek! Več... |
5. Is there a relationship between macroeconomic variables and stock market indices in Bosnia and Herzegovina?Adem Abdić, Ademir Abdić, Lejla Lazović-Pita, Fahir Kanlić, 2024, izvirni znanstveni članek Opis: The economic growth and development of a country are reflected in many aspects, one of them being the stock market indices. The purpose of the article is to examine and determine the relationship between selected macroeconomic variables and stock market indices in Bosnia and Herzegovina (BiH). Using quarterly data over the 2010q1-2019q4 period, a cointegration analysis was applied to model this relationship. The Vector Error Correction Model (VECM) was used to explore the short-run relationship as well as the long-run relationship. The article examined the predictive ability among variables of interest by applying the Granger causality test. The results indicate a stable long-run relationship between the analysed macroeconomic variables and stock market indices in BiH, while no short-run relationship was found. The results contribute to the scientific discussions about the relationship between selected macroeconomic variables and representative stock market indices in BiH which considers their direction and strength.
Ključne besede: stock market indices, macroeconomic variables, BiH, VECM model, Granger causality test
Objavljeno v DKUM: 30.05.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (989,46 KB)
Gradivo ima več datotek! Več... |
6. Parameter estimation for the basic Zirka-Moroz history-dependent hysteresis model for electrical steelsMartin Petrun, Ermin Rahmanović, 2025, izvirni znanstveni članek Opis: History-dependent hysteresis models can potentially describe magnetization curves of all orders accurately. This property is essential for modeling magnetization and power loss in magnetic components subjected to distorted excitation waveforms, which result in complex magnetization patterns such as offset minor loops. The basic Zirka–Moroz history-dependent hysteresis model offers a good balance between the model’s complexity and accuracy. However, estimating the model’s parameters can be challenging. This research provides insight into the parameter estimation procedure for the discussed hysteresis model. Based on the measured first-order reversal curves, the fundamental two-step parameter estimation procedure was employed and analyzed for two non-oriented and one grain-oriented electrical steel types used widely in contemporary electric drives and electromagnetic devices. For each sample evaluated, two sets of parameters were estimated and compared to the reference parameters recommended for non-oriented electrical steels. The performed analysis is essential for gaining a comprehensive understanding of the capabilities, challenges, requirements, and limitations associated with estimating the parameters and performance of the analyzed model for specific electrical steel types.
Ključne besede: history-dependent hysteresis model, grain-oriented electrical steel, magnetic hysteresis, non-oriented electrical steel, parameter estimation, static hysteresis
Objavljeno v DKUM: 30.05.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (5,11 MB) |
7. Incorporating enriched empirical models into optimization algorithm to enhance biogas productionTina Kegl, Andreja Goršek, Darja Pečar, 2025, izvirni znanstveni članek Opis: This paper introduces a novel approach to optimization of the anaerobic co-digestion (AcoD) process by developing enriched versions of first-order kinetic, modified Gompertz, and single-stage combined kinetic models. The key innovation of these enriched models lies in the introduction of new kinetic parameters that depend on both temperature and substrate composition, resulting in a set of new model parameters. These parameters are calibrated simultaneously across various process conditions, unlike existing models where kinetic constants are calibrated for only one operating regime. The enriched models are successfully calibrated and validated with experimental data from a batch AcoD of chicken manure with sawdust and fungal-pretreated Miscanthus; the relative index of agreement is higher than 0.99 for the produced biogas under all considered process conditions. By using the calibrated models to optimize the substrate composition and the AcoD process temperature profile, the results indicate that biogas production can increase by up to 50 %. Moreover, the proposed optimization allows for a favorable cost-benefit ratio; the estimated net energy gain can increase by up to 40 %. The proposed enriched models enable accurate prediction of biogas production at various process conditions and optimization of the AcoD process, representing a significant advancement over existing empirical models.
Ključne besede: biogas production, Pleurothus ostreatus, kinetic model parameters calibration, process optimization, gradient-based optimization, energy trade-offs
Objavljeno v DKUM: 29.05.2025; Ogledov: 0; Prenosov: 0
 Povezava na datoteko |
8. Carbon credits and crude oil : an investigation of the price returns interaction in the international marketAndré Assis de Salles, Renato Barros Lima, 2024, izvirni znanstveni članek Opis: This paper aims to verify the relationship between the international markets for crude oil and carbon credits. We studied the returns of prices practiced in these markets, focusing on the transmission of shocks between oil prices and carbon credit prices. The methodological approach used financial econometrics to study these variables' risk and return relationships. Besides causality and cointegration hypothesis tests, the VECM and GARCH models were estimates. There is a shortand long-term interaction between these variables. The volatility models show a significant association between the volatilities of the two variables of interest. Fossil fuels, mainly crude oil, generate energy that has substantial restrictions. At the same time, the carbon credits market has shown significant growth that can contribute to the use of energy from fossil fuels with parsimony and responsibility. Studying these variables and their interactions contributes to understanding the importance of the carbon market.
Ključne besede: carbon credit, crude oil price, VECM model, volatility model
Objavljeno v DKUM: 28.05.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (773,79 KB)
Gradivo ima več datotek! Več... |
9. Materialni model kompozitne strukture in optimizacija topologije kompozitnega monokoka : magistrsko deloPatrik Gnus, 2025, magistrsko delo Opis: Magistrska naloga se osredotoča na razvoj materialnega modela kompozitne strukture in optimizacijo topologije karbonskega monokoka za dirkalnik ekipe Formula Student, UNI Maribor Grand Prix Engineering. Cilj naloge je pridobiti natančne podatke o mehanskih lastnostih kompozitne strukture, ki bodo uporabljeni v numeričnih simulacijah z metodo končnih elementov v programu Ansys. Na podlagi teh podatkov bo izvedena osnovna topološka optimizacija monokoka, pri čemer bo glavni poudarek na zmanjšanju mase ob ohranjanju strukturne trdnosti.
V okviru raziskave bo izvedena analiza obstoječih materialnih modelov, optimizacija geometrije in strukture monokoka ter validacija rezultatov s pomočjo eksperimentalnih podatkov. Glavne predpostavke vključujejo obravnavo karbonskih vlaken kot linearno elastičnega materiala v določenem območju obremenitev ter homogeno obravnavo monokoka, čeprav je sestavljen iz več slojev. Omejitve raziskave zajemajo osredotočenost na statične in dinamične obremenitve brez upoštevanja toplotnih vplivov ter prilagajanje optimizacije v skladu s tekmovalnimi predpisi.
Rezultati naloge bodo prispevali k izboljšanju procesov načrtovanja kompozitnih struktur ter omogočili nadaljnji razvoj lahkih in zmogljivih monokokov v okviru ekipe Formula Student.
Ključne besede: kompozitna struktura, karbonska vlakna, monokok, Formula Student, materialni model, optimizacija topologije, metoda končnih elementov, numerične simulacije, zmanjšanje mase, vzvojna togost, eksperimentalna validacija.
Objavljeno v DKUM: 28.05.2025; Ogledov: 0; Prenosov: 27
Celotno besedilo (5,75 MB) |
10. Wages and income impacts of a liberal migration policy : an experimental studyVeronika Mitkova, Sona Kralova, 2023, izvirni znanstveni članek Opis: This article investigates the impact of a liberal migration policy that increases
labour quotas by 5% on wages and income of residents, native migrants, and
new migrants. The article focuses on the impact of migration in 21 areas, with
particular attention given to Slovakia and Germany. It is based on data collected
from the Global Trade Analysis Project database and the experimental design
by Walmsley, Ahmed, and Parsons, with adjustments to capture current global
migration flows. The findings indicate that the immigration of new unskilled
workers negatively impacts the real wages of unskilled residents, decreasing
them by almost 3%, while the arrival of skilled workers increases them by
0.73%. Similarly, the real wages of skilled residents decrease by 2.62% due
to the arrival of new skilled migrants, while unskilled migration results in its
increase by 0.53%. These findings can aid policymakers in developing policies
that maximize the benefits of migration. This research provides new insights
into the wage effects of migration in different areas, focusing on Germany
and Slovakia.
Ključne besede: CGE Model, labour migration, wages, migrant workers, labour policy
Objavljeno v DKUM: 28.05.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (739,82 KB)
Gradivo ima več datotek! Več... |
