1. Exploring the feasibility of generative AI in persona research : a omparative analysis of large language model-generated and human-crafted personas in obesity researchUrška Smrke, Ana Dimič, Nejc Plohl, Izidor Mlakar, 2025, izvirni znanstveni članek Opis: This study investigates the perceptions of Persona descriptions generated using three different large language models (LLMs) and qualitatively developed Personas by an expert panel involved in obesity research. Six different Personas were defined, three from the clinical domain and three from the educational domain. The descriptions of Personas were generated using qualitative methods and the LLMs (i.e., Bard, Llama, and ChatGPT). The perception of the developed Personas was evaluated by experts in the respective fields. The results show that, in general, the perception of Personas did not significantly differ between those generated using LLMs and those qualitatively developed by human experts. This indicates that LLMs have the potential to generate a consistent and valid representation of human stakeholders. The LLM-generated Personas were perceived as believable, relatable, and informative. However, post-hoc comparisons revealed some differences, with descriptions generated using the Bard model being in several Persona descriptions that were evaluated most favorably in terms of empathy, likability, and clarity. This study contributes to the understanding of the potential and challenges of LLM-generated Personas. Although the study focuses on obesity research, it highlights the importance of considering the specific context and the potential issues that researchers should be aware of when using generative AI for generating Personas.
Ključne besede: user personas, obesity, large language models, value sensitive design, digital health interventions
Objavljeno v DKUM: 14.02.2025; Ogledov: 0; Prenosov: 0
 Celotno besedilo (812,18 KB) |
2. Modeling and optimization of anaerobic digestion technology : current status and future outlookTina Kegl, Eloisa Torres Jiménez, Breda Kegl, Anita Kovač Kralj, Marko Kegl, 2025, pregledni znanstveni članek Ključne besede: renewable energy, anaerobic digestion, biogas plant, mathematical models, optimization algorithms, products utilization
Objavljeno v DKUM: 31.01.2025; Ogledov: 0; Prenosov: 7
Celotno besedilo (19,46 MB) |
3. Long-term temperature prediction with hybrid autoencoder algorithmsJorge Pérez-Aracil, Dušan Fister, C. M. Marina, César Peláez-Rodriguez, L. Cornejo-Bueno, P. A. Gutiérrez, Matteo Giuliani, A. Castelleti, Sancho Salcedo-Sanz, 2024, izvirni znanstveni članek Opis: This paper proposes two hybrid approaches based on Autoencoders (AEs) for long-term temperature prediction. The first algorithm comprises an AE trained to learn temperature patterns, which is then linked to a second AE, used to detect possible anomalies and provide a final temperature prediction. The second proposed approach involves training an AE and then using the resulting latent space as input of a neural network, which will provide the final prediction output. Both approaches are tested in long-term air temperature prediction in European cities: seven European locations where major heat waves occurred have been considered. The longterm temperature prediction for the entire year of the heatwave events has been analysed. Results show that the proposed approaches can obtain accurate long-term (up to 4 weeks) temperature prediction, improving Persistence and Climatology in the benchmark models compared. In heatwave periods, where the persistence of the temperature is extremely high, our approach beat the persistence operator in three locations and works similarly in the rest of the cases, showing the potential of this AE-based method for long-term temperature prediction.
Ključne besede: autoencoder, temperature prediction, hybrid models, heatwave
Objavljeno v DKUM: 29.01.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (1,82 MB) |
4. Efficient encoding and decoding of voxelized models for machine learning-based applicationsDamjan Strnad, Štefan Kohek, Borut Žalik, Libor Váša, Andrej Nerat, 2025, izvirni znanstveni članek Opis: Point clouds have become a popular training data for many practical applications of machine learning in the fields of environmental modeling and precision agriculture. In order to reduce high space requirements and the effect of noise in the data, point clouds are often transformed to a structured representation such as a voxel grid. Storing, transmitting and consuming voxelized geometry, however, remains a challenging problem for machine learning pipelines running on devices with limited amount of on-chip memory with low access latency. A viable solution is to store the data in a compact encoded format, and perform on-the-fly decoding when it is needed for processing. Such on-demand expansion must be fast in order to avoid introducing substantial additional delay to the pipeline. This can be achieved by parallel decoding, which is particularly suitable for massively parallel architecture of GPUs on which the majority of machine learning is currently executed. In this paper, we present such method for efficient and parallelizable encoding/decoding of voxelized geometry. The method employs multi-level context-aware prediction of voxel occupancy based on the extracted binary feature prediction table, and encodes the residual grid with a pointerless sparse voxel octree (PSVO). We particularly focused on encoding the datasets of voxelized trees, obtained from both synthetic tree models and LiDAR point clouds of real trees. The method achieved 15.6% and 12.8% reduction of storage size with respect to plain PSVO on synthetic and real dataset, respectively. We also tested the method on a general set of diverse voxelized objects, where an average 11% improvement of storage space was achieved.
Ključne besede: voxel grid, feature prediction, tree models, prediction-based encoding, key voxels, residuals, sparse voxel octree
Objavljeno v DKUM: 09.01.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (20,93 MB) |
5. Kratek pregled platform za ADME testiranjeTina Maver, Boštjan Vihar, Uroš Maver, 2024, izvirni znanstveni članek Opis: V zadnjem času je bil dosežen pomemben napredek pri razvoju ADME (absorpcija, distribucija, metabolizem, ekskrecija) modelov, vendar izziv ostaja vzpostaviti platforme, ki bi zmanjšale testiranje na živalih in stroške raziskav. Naraščajoča pomembnost farmakokinetičnih interakcij poudarja potrebo po zanesljivih in
ponovljivih ADME modelih, ki so vse bolj ključni za razvoj zdravil in zagotavljanje varnosti z željo po preprečevanju
resnih kliničnih zapletov in hospitalizacije.
Ključne besede: ADME, drug interaction studies, in vitro models, pharmacokinetics, multi-organ models
Objavljeno v DKUM: 07.01.2025; Ogledov: 0; Prenosov: 17
Celotno besedilo (405,16 KB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo! |
6. In vitro disease models of the endocrine pancreasMarko Milojević, Jan Rožanc, Jernej Vajda, Laura Činč Ćurić, Eva Paradiž, Andraž Stožer, Uroš Maver, Boštjan Vihar, 2021, pregledni znanstveni članek Opis: The ethical constraints and shortcomings of animal models, combined with the demand to study disease pathogenesis under controlled conditions, are giving rise to a new field at the interface of tissue engineering and pathophysiology, which focuses on the development of in vitro models of disease. In vitro models are defined as synthetic experimental systems that contain living human cells and mimic tissue- and organ-level physiology in vitro by taking advantage of recent advances in tissue engineering and microfabrication. This review provides an overview of in vitro models and focuses specifically on in vitro disease models of the endocrine pancreas and diabetes. First, we briefly review the anatomy, physiology, and pathophysiology of the human pancreas, with an emphasis on islets of Langerhans and beta cell dysfunction. We then discuss different types of in vitro models and fundamental elements that should be considered when developing an in vitro disease model. Finally, we review the current state and breakthroughs in the field of pancreatic in vitro models and conclude with some challenges that need to be addressed in the future development of in vitro models.
Ključne besede: in vitro disease models, pancreas, islet of Langerhans, 3D cell culture, scaffolds, acute tissue slices
Objavljeno v DKUM: 01.10.2024; Ogledov: 0; Prenosov: 7
Celotno besedilo (4,42 MB)
Gradivo ima več datotek! Več... |
7. Understanding cognitive transport mode choice structures : means-ends chains as a type of second-order cyberneticsTomaž Kolar, Iztok Kolar, 2022, izvirni znanstveni članek Opis: Purpose: This paper aims to inform the promotion of sustainable modes of transport. For this purpose, it deploys a means-ends framework as a type of second-order cybernetics and uses it to explore cognitive transport mode choice structures.
Design/methodology/approach: The empirical study relies on a purposive sample and a qualitative research methodology known as laddering. It is aimed at the identification and comparative analysis of the cognitive means-ends structures of transport users.
Findings: The results reveal more positive and complex associations for the car than for public transport. Two main positive means-ends structures are identified for public transport, one related with the relaxation and the other with doing useful things while travelling. Dominant positive structures for the car are related with self-confidence, satisfaction and personal freedom. Negative means-ends structures in addition reveal important justifications and rationalizations for car use.
Practical implications: Based on the identified distinct means-ends elements and structures, this study holds important implications for developing a communications strategy and policy interventions seeking to promote public transport.
Originality/value: Means-ends theory is proposed as an integrative cybernetic framework for the study of stakeholders' (customers') mental models. The empirical study is the first to concurrently and comparatively examine positive and negative means-ends chains for the car and for the public transport modes.
Ključne besede: public transport, second-order cybernetics, laddering methodology, means-ends theory, private car, mental models, personal values, marketing, consumer
Objavljeno v DKUM: 27.08.2024; Ogledov: 93; Prenosov: 11
Celotno besedilo (692,92 KB)
Gradivo ima več datotek! Več... |
8. Methods and models for electric load forecasting : a comprehensive reviewMahmoud A. Hammad, Borut Jereb, Bojan Rosi, Dejan Dragan, 2020, izvirni znanstveni članek Opis: Electric load forecasting (ELF) is a vital process in the planning of the electricity industry and plays a crucial role in electric capacity scheduling and power systems management and, therefore, it has attracted increasing academic interest. Hence, the accuracy of electric load forecasting has great importance for energy generating capacity scheduling and power system management. This paper presents a review of forecasting methods and models for electricity load. About 45 academic papers have been used for the comparison based on specified criteria such as time frame, inputs, outputs, the scale of the project, and value. The review reveals that despite the relative simplicity of all reviewed models, the regression analysis is still widely used and efficient for long-term forecasting. As for short-term predictions, machine learning or artificial intelligence-based models such as Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Fuzzy logic are favored.
Ključne besede: methods, models, electric load forecasting, modeling electricity loads, electricity industry, power management, logistics
Objavljeno v DKUM: 22.08.2024; Ogledov: 95; Prenosov: 8
Celotno besedilo (1,23 MB)
Gradivo ima več datotek! Več... |
9. 7th International Conference on Technologies & Business Models for Circular Economy : book of abstracts2024 Opis: The 7th International Conference on Technologies & Business Models for Circular Economy (TBMCE) was organized by the Faculty of Chemistry and Chemical Engineering, University of Maribor in collaboration with the Strategic Research and Innovation Partnership - Networks for the Transition into Circular Economy (SRIP- Circular Economy), managed by the Chamber of Commerce and Industry of Štajerska. The conference was held in Portorož, Slovenia, at the Grand Hotel Bernardin from September 4th to September 6th, 2024. EIT RawMaterials RIS Hub Adria, SPIRIT Slovenia Business Development Agency and Pomurje Technology Park (as part of the GREENE 4.0 and CI-Hub projects) have joined us as co-organizers. TBMCE 2024 was devoted to presentations of circular economy concepts, technologies and methodologies that contribute to the shift of business entities and society as a whole to a more responsible, circular management of resources. The conference program included panel discussions, plenary and keynote sessions, oral and poster presentations on the following topics: Sustainable Energy, Biomass and Alternative Raw Materials, Circular Business Models, Secondary Raw Materials and Functional Materials, ICT in Circular Economy, Processes and Technologies. Panel discussions addressed following topics: Circular Economy Transition in South East Europe, The transition to carbon neutrality in energy intensive industry, Valorization of used and contaminated wood, Circular economy trends in construction, Critical raw materials and circular economy transition, Industrial Symbiosis and its opportunities for industry, AI and circular economy. The event was under the patronage of Ministry of the Economy, Tourism and Sport and Ministry of Cohesion and Regional Development.
Ključne besede: circular economy, sustainable development, processes and technologies, circular business models, research and development
Objavljeno v DKUM: 22.08.2024; Ogledov: 93; Prenosov: 24
Celotno besedilo (3,27 MB)
Gradivo ima več datotek! Več... |
10. Computer science education in ChatGPT Era: experiences from an experiment in a programming course for novice programmersTomaž Kosar, Dragana Ostojić, Yu David Liu, Marjan Mernik, 2024, izvirni znanstveni članek Opis: The use of large language models with chatbots like ChatGPT has become increasingly popular among students, especially in Computer Science education. However, significant debates exist in the education community on the role of ChatGPT in learning. Therefore, it is critical to understand the potential impact of ChatGPT on the learning, engagement, and overall success of students in classrooms. In this empirical study, we report on a controlled experiment with 182 participants in a first-year undergraduate course on object-oriented programming. Our differential study divided students into two groups, one using ChatGPT and the other not using it for practical programming assignments. The study results showed that the students’ performance is not influenced by ChatGPT usage (no statistical significance between groups with a p-value of 0.730), nor are the grading results of practical assignments (p-value 0.760) and midterm exams (p-value 0.856). Our findings from the controlled experiment suggest that it is safe for novice programmers to use ChatGPT if specific measures and adjustments are adopted in the education process.
Ključne besede: large language models, ChatGPT, artificial intelligence, controlled experiment, object-oriented programming, software engineering education
Objavljeno v DKUM: 12.08.2024; Ogledov: 59; Prenosov: 6
Celotno besedilo (492,37 KB) |
