1. Deep learning predictive models for terminal call rate prediction during the warranty periodAljaž Ferencek, Davorin Kofjač, Andrej Škraba, Blaž Sašek, Mirjana Kljajić Borštnar, 2020, izvirni znanstveni članek Opis: Background: This paper addresses the problem of products’ terminal call rate (TCR) prediction during the warranty period. TCR refers to the information on the amount of funds to be reserved for product repairs during the warranty period. So far, various methods have been used to address this problem, from discrete event simulation and time series, to machine learning predictive models.
Objectives: In this paper, we address the above named problem by applying deep learning models to predict terminal call rate.
Methods/Approach: We have developed a series of deep learning models on a data set obtained from a manufacturer of home appliances, and we have analysed their quality and performance.
Results: Results showed that a deep neural network with 6 layers and a convolutional neural network gave the best results.
Conclusions: This paper suggests that deep learning is an approach worth exploring further, however, with the disadvantage being that it requires large volumes of quality data.
Ključne besede: manufacturing, product lifecycle, management product failure, machine learning, prediction
Objavljeno v DKUM: 21.01.2025; Ogledov: 0; Prenosov: 0
 Celotno besedilo (834,28 KB)
Gradivo ima več datotek! Več... |
2. Razvoj modela za ocenjevanje delovne uspešnosti policistovBoštjan Oblak, 2024, magistrsko delo Opis: Sistem ocenjevanja v javni upravi predstavlja izziv, saj težje vrednotimo opravljeno delo, kot to lahko storimo v zasebnem sektorju, kjer je v določenih podjetjih produktivnost lahko zlahka merljiva. Prav tako problem predstavlja sistem ocenjevanja, ki je za celotno javno upravo univerzalen oziroma ni prilagojen glede na karakteristike oziroma značilnosti poklica. Sistem plač funkcionarjev in javnih uslužbencev v javnem sektorju, pravila za njihovo določanje, obračunavanje in izplačevanje ter pravila za določanje obsega sredstev za plače določa Zakon o sistemu plač v javnem sektorju (ZSPJS). Ne glede na plačno skupino, ki naj bi ločila zaposlene v javnem sektorju, pa je model za ocenjevanje javnih uslužbencev za vse javne uslužbence enak in ni prilagojen glede na karakteristike dela znotraj javne uprave. Ocenjevanje ima v javnem sektorju velik pomen, saj je neposredno povezano s plačnim napredovanjem. Ocena javnega uslužbenca že znotraj iste plačne skupine ne more biti objektivna, saj ima javni uslužbenec, ki je zaposlen na bolj obremenjeni izpostavi (policijska postaja na območju Ljubljane, Uprava Enota Ljubljana ali Upravna Enota Maribor …), večji obseg dela, kot ga ima javni uslužbenec, ki svoje delo opravlja na območju, kjer je število strank manjše. Prav tako omenjeni zaposleni težje svoje delo opravljajo pravočasno, nimajo časa za razvijanje novih idej in dajanja koristnih predlogov in pobud, hkrati pa je ob večji količini dela pogostost napak lahko večja. Primeren sistem ocenjevanja javnih uslužbencev bi moral biti objektiven in specifičen glede na delo znotraj enote, ki jo »pokriva« ocenjevalec. Model za ocenjevanje delovne uspešnosti bi moral biti pregleden, prilagojen zaposlenim in z jasnimi navodili ocenjevalcu ter po možnosti digitalen. Ena izmed ustreznih rešitev bi bila uporaba večparametrskega oziroma večkriterijskega odločitvenega modela z jasno določeno strukturo kriterijev, opisom zalog vrednosti in določeno funkcijo koristnosti. Omenjen model bi odločevalcu pomagal pri vrednotenju in analizi zaposlenih ter pri oblikovanju poročil.
Ključne besede: ocenjevanje delovne uspešnosti, policija, večkriterijski model odločanja
Objavljeno v DKUM: 15.11.2024; Ogledov: 0; Prenosov: 7
Celotno besedilo (4,43 MB) |
3. Varnost poslovnih podatkov pri implementaciji inteligentnega sistema chatgptMarija Koleva, 2024, diplomsko delo Opis: Namen diplomske naloge je bil raziskati implementacijo in uporabo generativnih modelov, predvsem modelov generative pre-trained transformer (GPT), v poslovnem okolju podjetja X in razumeti njihov vpliv na poslovne procese. S poudarkom na varnosti in produktivnosti smo preučili prednosti in izzive integracije teh tehnologij ter opredelili ključne ugotovitve, ki vključujejo izboljšano učinkovitost, inovativnost, kakovost storitev in varnost podatkov. Uporabljene metode vključujejo študijo primera, intervju z vodjo projekta, analizo podatkov in pregled literature. Glavni zaključki vključujejo poudarek na potrebi po implementaciji varnostnih protokolov, upoštevanju etičnih vidikov in implementaciji najboljših praks pri implementaciji generativnih modelov. Priporočila vključujejo uporabo robustnih varnostnih mehanizmov, optimizacijo poslovnih procesov in nadaljnje raziskovanje možnosti uporabe generativnih modelov v poslovnem okolju.
Ključne besede: generativni modeli, GPT, poslovno okolje, varnost, produktivnost
Objavljeno v DKUM: 03.10.2024; Ogledov: 0; Prenosov: 16
Celotno besedilo (1,04 MB) |
4. Multi-attribute assessment of digital maturity of SMEsMirjana Kljajić Borštnar, Andreja Pucihar, 2021, izvirni znanstveni članek Opis: Small and medium-sized enterprises (SMEs) need to keep pace with large enterprises, thus they need to digitally transform. Since they usually lack resources (budget, knowledge, and time) many countries have their support environment to help SMEs in this endeavor. To be able to ensure the right kinds of support, it is crucial to assess the digital maturity of an enterprise. There are many models and assessment tools for digital maturity, however, they are either theoretical models, partial, vendor oriented, or suited for large enterprises. In this paper, we address the problem of assessing digital maturity for SMEs. For this purpose, we developed a multi-attribute model for assessment of the digital maturity of an SME. We followed the design science research approach, where the multi-attribute model is considered as an IT artifact. Within the design cycle, the decision expert (DEX) methodology of a broader multi-attribute decision making methodologies was applied. The developed model was validated by a group of experts and upgraded according to their feedback and finally evaluated on seven real-life cases. Results show that the model can be used in real business situations.
Ključne besede: digital transformation, digital maturity assessment, multi-attribute model, small and medium-sized enterprises
Objavljeno v DKUM: 07.08.2024; Ogledov: 108; Prenosov: 14
Celotno besedilo (3,07 MB)
Gradivo ima več datotek! Več... |
5. Uporaba metod strojnega učenja za oblikovanje profila obremenitve spletnih aplikacijYauhen Unuchak, 2024, magistrsko delo Opis: V magistrskem delu je predstavljen razvoj modelov gručenja s pomočjo programskega jezika Python. Cilj dela je razviti prototip orodij za oblikovanje profila obremenitve pri testiranju zmogljivosti spletnih aplikacij na podlagi analize preteklega delovanja spletne aplikacije v produkcijskem okolju.
Izdelava profila obremenitve za testiranje zmogljivosti spletnih aplikacij predstavlja ključno fazo obremenitvenega testiranja. Ta faza omogoča usklajevanje testnih podatkov in obsega z zahtevami naročnika ter dejanskimi uporabniškimi izkušnjami. Pri izdelavi profila je treba upoštevati uporabniške vloge, tipične scenarije delovanja in razmerje med različnimi scenariji, saj različne funkcionalnosti aplikacije porabijo različne vire strežnika.
Obremenitveno testiranje vključuje simulacijo uporabniških scenarijev s specializirano programsko opremo, kot sta JMeter in LoadRunner. To rešitev lahko uporabljajo inženirji in IT-strokovnjaki pri oblikovanju profila obremenitve, ki se ukvarjajo z obremenitvenim testiranjem zmogljivosti spletnih aplikacij.
V delu raziskujemo, kako odkriti uporabniške vzorce za izboljšanje oblikovanja profila obremenitve za testiranje zmogljivosti na podlagi analize zapisov (rudarjenja podatkov iz log-datotek) o delovanju spletne aplikacije v produkcijskem okolju. S pravilno zasnovanim profilom obremenitve je mogoče oceniti zmogljivost in stabilnost sistema ter simulirati realne uporabniške pogoje.
Ključne besede: profil obremenitve spletnih aplikacij, testiranje, podatkovno rudarjenje spletnih zapisov
Objavljeno v DKUM: 05.07.2024; Ogledov: 106; Prenosov: 11
Celotno besedilo (8,02 MB) |
6. Uporaba metod strojnega učenja za izboljšanje procesa vodenja nalog pri projektnih dejavnostihTatyana Unuchak, 2024, magistrsko delo Opis: Namen te raziskave je ugotoviti, kako lahko uporaba tehnik strojnega učenja izboljša procese upravljanja nalog v projektnih dejavnostih podjetij. Študija je bila izvedena z uporabo metodologije CRISP-DM na podatkih iz dveh virov o projektih Jira. Glavni koraki priprave podatkov so vključevali čiščenje podatkov, tokenizacijo, lematizacijo in uravnoteženje. Modeliranje je bilo izvedeno z uporabo petih klasifikatorjev: Random Forest, SVC (angl. support vector classifier), Logistic Regression, Gradient Boosting in kNN. Upoštevani so bili različni pristopi k razvrstitvi podatkov: razvrstitev v dva, tri in štiri razrede. Analiza je pokazala, da čiščenje podatkov iz tehničnih informacij ne vpliva na rezultate razvrščanja. Uravnoteženje je izboljšalo rezultate. Po našem mnenju je razvrstitev podatkov v dva, tri in celo štiri razrede pokazala dobre rezultate. Uvedba sentimentalne sestavine v model ni izboljšala rezultatov razvrščanja.
Menimo, da je bil cilj raziskave dosežen. Nadaljnje raziskave so lahko usmerjene v izboljšanje algoritmov za čiščenje opisov projektnih nalog iz tehničnih informacij. Naši rezultati in priporočila bodo pripomogli k izboljšanju procesov upravljanja nalog v projektih in povečanju njihove učinkovitosti.
Ključne besede: vodenje projektov, strojno učenje, prioriteta nalog, algoritmi za razvrščanje
Objavljeno v DKUM: 05.07.2024; Ogledov: 93; Prenosov: 14
Celotno besedilo (6,35 MB) |
7. Categorisation of open government data literatureAljaž Ferencek, Mirjana Kljajić Borštnar, Ajda Pretnar Žagar, 2022, pregledni znanstveni članek Opis: Background: Due to the emerging global interest in Open Government Data, research papers on various topics in this area have increased.
Objectives: This paper aims to categorise Open government data research.
Methods/Approach: A literature review was conducted to provide a complete overview and classification of open government data research. Hierarchical clustering, a cluster analysis method, was used, and a hierarchy of clusters on selected data sets emerged.
Results: The results of this study suggest that there are two distinct clusters of research, which either focus on government perspectives and policies on OGD, initiatives, and portals or focus on regional studies, adoption of OGD, platforms, and barriers to implementation. Further findings suggest that research gaps could be segmented into many thematic areas, focusing on success factors, best practices, the impact of open government data, barriers/challenges in implementing open government data, etc.
Conclusions: The extension of the paper, which was first presented at the Entrenova conference, provides a comprehensive overview of research to date on the implementation of OGD and points out that this topic has already received research attention, which focuses on specific segments of the phenomenon and signifies in which direction new research should be made.
Ključne besede: open government data, open government data research, hierarchical clustering, OGD classification, OGD literature overview
Objavljeno v DKUM: 12.06.2024; Ogledov: 134; Prenosov: 11
Celotno besedilo (539,06 KB)
Gradivo ima več datotek! Več... |
8. 37th Bled eConference - Resilience Through Digital Innovation: Enabling the Twin Transition : June 9 – 12, 2024, Bled, Slovenia, Conference Proceedin2024, zbornik Opis: The Bled eConference, organised by the University of Maribor, Faculty of Organizational Sciences, has been shaping electronic interactions since 1988. The theme of the 37th conference is "Resilience through digital innovation: enabling the twin transition". The theme addresses the critical convergence of digital transformation and sustainability, in line with the European Commission’s top priorities and policy initiatives. At the conference, we aim to highlight the opportunities of digital technologies that can contribute to building organisational and societal resilience, with a focus on social and environmental goals. The papers in this conference proceedings explore a range of topics including the opportunities and challenges of the twin transition, emerging technologies, artificial intelligence and data science, decision analytics for business and societal changes, digital innovation and business models, restructured work and the future workplace, digital health, digital ethics, digital education, smart sustainable cities, digital consumers, and the digital transformation of the public sector.
Ključne besede: resilience, digital transformation, innovation, twin transition, sustainability, digital transition, green transition
Objavljeno v DKUM: 28.05.2024; Ogledov: 337; Prenosov: 77
Celotno besedilo (21,98 MB)
Gradivo ima več datotek! Več... |
9. 43rd International Conference on Organizational Science Development: Green and Digital Transition – Challenge or Opportunity : Conference Proceedings2024, zbornik recenziranih znanstvenih prispevkov na mednarodni ali tuji konferenci Opis: The 43rd International Scientific Conference on the Development of Organisational Science was held in Portorož from the 20th to the 22nd of March 2024. The main aim of the conference was to promote the importance of knowledge in the context of green and digital transtition of organizations, through academic and scientific debates and professional developments from the economic and non-economic worlds. The conference, which was held under the umbrella title " Green and Digital Transition - Challenge or Opportunity", aimed to highlight the importance of the green and digital transition for the successful achievement of organisational objectives and the appropriate overcoming of societal challenges. The objectives pursued in this context are related to the natural dimensions on the one hand, and to stimulating the economy through green technology, sustainable development and pollution reduction on the other. The green and digital transition is also an opportunity for organisations to make changes towards overarching environmental challenges. It is undoubtedly more important than ever to take decisions that generate synergies between innovation, different sciences, and applied approaches, and to promote changes in business models that will lead to a sustainable and socially responsible development environment. In Portorož, we have reconnected opinions, views, and scientific and professional debates that will stimulate all of us to act in the future, both in organizations and in society at large.
Ključne besede: organization, knowledge, interdisciplinarity, science, economy
Objavljeno v DKUM: 22.03.2024; Ogledov: 456; Prenosov: 101
Celotno besedilo (21,17 MB)
Gradivo ima več datotek! Več... |
10. 36th Bled eConference – Digital Economy and Society: The Balancing Act for Digital Innovation in Times of Instability : June 25 – 28, 2023, Bled, Slovenia, Conference Proceedings, Second Edition2023, zbornik Opis: The Bled eConference, organised by the University of Maribor, Faculty of Organizational Sciences, has been shaping electronic interactions since 1988. The theme of the 36th conference is "Digital Economy and Society: The Balancing Act for Digital Innovation in Times of Instability". In times of instability, which include political, economic, resource, health, and environmental challenges on the one hand, and technological disruption on the other, it is critical to ensure that digital innovation continues to lead to the right and sustainable solutions that are tailored to the needs of all people, enterprises and society. It is very important to keep in mind the protection of our planet, including fauna and flora. These efforts include adopting appropriate regulatory frameworks, fostering digital literacy and skills development, promoting inclusive access to digital technologies, and addressing the ethical, social and environmental implications of digital transformation. The papers in this conference proceedings address digital transformation of enterprises, artificial intelligence and data science solutions, decision analytics for business and societal challenges, new, digital and data driven business models, digital consumer, digital education, digital health, digital ethics, restructured work and solutions for smart and sustainable cities. We continue to provide an open forum for academia, including students, industry, and policy makers where everyone can contribute to creating a better world.
Ključne besede: digital economy, digital society, digital transformation, digital innovation, instability, balancing
Objavljeno v DKUM: 12.12.2023; Ogledov: 472; Prenosov: 62
Celotno besedilo (17,32 MB)
Gradivo ima več datotek! Več... |
