1. |
2. |
3. Transparent Persona Generation With LLMs : An Evidence-based and Traceable Method for User-centred DesignBojan Blažica, Manca Topole, Marko Debeljak, 2025, independent scientific component part or a chapter in a monograph Abstract: Personas are a cornerstone of user-centred design, but traditional methods for developing them are difficult to validate, prone to bias and labour-intensive. Data-driven approaches have improved scalability, but often lack the narrative richness and empathy that make personas effective. We present a methodology that uses large language models (LLMs) to accelerate the creation of personas while underpinning and constraining the results with contextual and empirical data. Our approach emphasises transparency and traceability: each generated persona attribute can be linked to its source material, including project documentation, workshop transcripts, survey results or other contextual corpora. By combining the narrative strengths of LLMs with the rigour of an evidence-based foundation, the method generates personas that are both descriptive and verifiable. We present a five-step workflow methodology: (1) generation of persona candidates from contextual data using LLMs, (2) iterative refinement to ensure representativeness of personas, (3) selection of the most relevant profiles through expert evaluation, (4) design of detailed persona profiles, and (5) enrichment with empirical evidence to ensure traceability and validation. The methodology is illustrated with a case study from the field of soil health, but can also be applied to other design contexts where alignment between different stakeholders is crucial. We argue that this approach positions LLMs not as a substitute for human expertise, but as an accelerator of persona work that improves accountability, reduces bias and facilitates communication in collaborative design processes.
Keywords: personas, large language model, traceability, user-centered design, decision support systems
Published in RUP: 30.01.2026; Views: 179; Downloads: 2
 Full text (275,89 KB) |
4. |
5. Agricultural-Induced Environmental Kuznets Curve for South Africa : A Threshold Regression and ARIMA Forecasting ApproachAndrew Phiri, Rasaq Raimi, 2025, original scientific article Abstract: The purpose of the paper is to examine the impact of the agricultural sector on agricultural emissions in South Africa. To this end, we estimate an agricultural-induced environmental Kuznets curve (EKC) for South Africa between 1990 and 2022 using conventional and threshold regression frameworks. Our regression estimates reveal a ‘humped-shaped’ relationship between agricultural production and agricultural emissions, whereby agricultural production produces lower agricultural emissions above threshold estimates of 4,876 and 6,100 metric tons of CO2 emissions. Further investigations show that the South African economy has consistently remained above these thresholds since 2010. Moreover, a forecast analysis of the time series using ARIMA models shows that agricultural productionis (emissions are) on an upward (a downward) trajectory. However, the forecasting analysis also shows that the South African agricultural sector is not scheduled to reach the net-zero emissions target by 2050. Altogether, these findings imply that whilst South Africa had followed a trajectory of sustainable development prior to the COVID-19 pandemic, the current trajectory may not be sufficient to attain the 2050 Sustainable Development Goals.
Keywords: agricultural sector, agricultural emissions, environmental Kuznets curve (EKC), threshold regression model, ARIMA forecasting, South Africa
Published in RUP: 16.01.2026; Views: 178; Downloads: 0
Full text (1,03 MB) |
6. Optimizacija oskrbe pacientov v onkološki zdravstveni negi na podlagi McGillovega sodelovalnega modelaValentina Masten, Tamara Milić, Matic Petrovič, Mirko Prosen, Sabina Ličen, 2025, original scientific article Abstract: Izhodišča: McGillov model zdravstvene nege je celostni, sodelovalni pristop, ki poudarja aktivno vlogo pacienta, vključevanje bližnjih in krepitev psihosocialne podpore. Kljub uveljavljenosti v mednarodnem prostoru njegova uporaba v slovenski klinični praksi še ni bila raziskana. Namen raziskave je bil ovrednotiti, v kolikšni meri medicinske sestre na področju onkološke zdravstvene nege uporabljajo pristope McGillovega modela, ki vključujejo sodelovanje pacientov, vključevanje družinskih članov in krepitev psihosocialne podpore. Metode: V kvantitativni presečni raziskavi je bilo k sodelovanju povabljenih približno 400 medicinskih sester, zaposlenih na področju onkološke zdravstvene nege. Vprašalnik je pričelo izpolnjevati 166 oseb, od tega ga je popolnoma izpolnilo 126 (odzivnost 31,5 % glede na populacijo medicinskih sester zaposlenih na področju onkološke zdravstvene nege). Večina anketirancev je bila ženskega spola (77,8 %). Povprečna starost anketirancev je bila 37,71 leta (s = 8,07) s povprečno delovno dobo na področju onkološke zdravstvene nege 9,66 leta (s = 7,93). Analiza je temeljila le na popolnoma rešenih vprašalnikih. Podatke smo zbrali z novo razvito lestvico, ki temelji na McGillovem sodelovalnem modelu. Anketiranci so trditve ocenjevali na petstopenjski lestvici, ki meri pogostost izvajanja pristopov ali stopnjo strinjanja z izjavo. Izvedli smo eksploratorno in konfirmatorno faktorsko analizo, Wilcoxonove in Mann–Whitneyjeve teste ter Spearmanovo korelacijo. Rezultati: Faktorska analiza je potrdila tri konstrukte, ki pojasnjujejo 65,3 % skupne variance (KMO = 0,896; Bartlett p < 0,001). Empirične mediane vseh treh konstruktov so bile statistično značilno višje od teoretičnih (p < 0,001), kar pomeni, da so anketiranci poročali o uporabi pristopov McGillovega modela. Anketiranci z dostopom do pisnih protokolov ali organizacijsko podporo so dosegali višje rezultate (p < 0,001). Ugotovljene so bile zmerne do visoke pozitivne korelacije med uporabo pristopov in zaznavo izboljšanja oskrbe ter psihosocialnega stanja onkoloških pacientov (p < 0,001). Zaključek: Rezultati potrjujejo, da se v onkološki zdravstveni negi pogosto uporabljajo pristopi McGillovega modela, kar pozitivno sovpada z zaznanim izboljšanjem kakovosti oskrbe. Model ima potencial za širšo in bolj formalizirano implementacijo v klinično prakso.
Keywords: McGillov model zdravstvene nege, medicinske sestre, onkološka zdravstvena nega, psihosocialna podpora, sodelovanje pacienta
Published in RUP: 29.12.2025; Views: 235; Downloads: 8
Full text (209,66 KB)
This document has more files! More... |
7. AI and Musical InterpretationWolfgang Marx, 2025, independent scientific component part or a chapter in a monograph Abstract: Generative AI is used to create music more and more. This chapter explores how this phenomenon affects aspects of musical interpretation. The way in which AI generates texts, pictures, music and other media indicates that compared to human creators – it is likely to reduce the range of interpretative variants in its output. This argument is developed in three steps: firstly, a number of examples of AI-generated songs are presented in order to outline what AI can do at the moment. Secondly, the way in which large language models (LLMs) – the underlying systems of many AI generators work is discussed, showing that LLMs have a tendency to standardise their results, while also removing any quirk or idiosyncrasy that human creators would (unconsciously) include. AI outputs are “depersonalised”, as it were. Thirdly, the concept of “model collapse” is introduced. It leads to further homogenisation as AI systems will inevitably include more and more data in their processes that are already AI-created, setting in motion a spiral of self-referentiality that is likely to lead to a collapse of the systems in the long run. While this may not be inevitable it poses enough of a risk to give us food for thought and spend more time assessing the danger posed to interpretative variety by generative AI.
Keywords: AI-generated music, music and model collapse, deepfakes of singers’ voices, AI and musical interpretation
Published in RUP: 18.12.2025; Views: 187; Downloads: 2
Full text (225,01 KB) |
8. Experimental and analytical evaluation of shear capacity of reclaimed timber connections with thermo-mechanically densified wooden dowelsMohammad Derikvand, Donya Bazyar Khoshroodi, 2025, original scientific article Abstract: The reuse of reclaimed timber in structural applications is increasingly recognized as a strategy to extend ma- terial life cycles and reduce waste. Particular attention has recently turned to reusing reclaimed timber in adhesive-free laminated products with wooden dowels, where connection performance is critical. The aim of this study was to investigate the mechanical performance of double-shear connections assembled from reclaimed spruce timber using thermo-mechanically densified wooden dowels. The dowels were first evaluated in bending and embedment tests on lamellae made from both reclaimed and virgin spruce timber. The shear capacity of the connections was then evaluated in three layups: two homogeneous (all-reclaimed lamellae and all-virgin spruce lamellae) and one hybrid (reclaimed side lamellae with a central virgin spruce lamella). Analytical predictions were performed based on the draft of the new Eurocode 5, however, with two alternative definitions of dowel bending resistance (ultimate moment Mu and yield moment My), and three alternative definitions of embedment strength (f 0.05d h calculated using the 0.05 d offset method, f Fmax h calculated from Fmax, and f 0.8Fmax h calculated from 0.8 Fmax). The three lamellae layups exhibited relatively similar mean capacities (7.3–8.3 kN). The all-reclaimed connections were on average 13 % stronger than the other assemblies, but this was not statistically significant. Among the model input variants, Mu with f 0.05d h showed the closest agreement with the experimental mean values, while My with f 0.05d h led to more conservative predictions preferable for design. In both cases, excluding outliers from the embedment test results reduced overestimation in the predictions. All other input variants overestimated the shear capacity. Overall, both homogeneous and hybrid connections with reclaimed timber lamellae performed comparably to virgin timber connections and exhibited predictable mechanical behavior.
Keywords: reclaimed timber, wood densification, structural reuse, embedment strength, dowel connections, European yield model, Eurocode 5
Published in RUP: 17.12.2025; Views: 237; Downloads: 4
Full text (23,08 MB)
This document has more files! More... |
9. |
10. Evaluation of changes in prediction modelling in biomedicine using systematic reviewsLara Lusa, Franziska Kappenberg, Gary S. Collins, Matthias Schmid, Willi Sauerbrei, Jörg Rahnenführer, 2025, original scientific article Abstract: The number of prediction models proposed in the biomedical literature has been growing year on year. In the last few years there has been an increasing attention to the changes occurring in the prediction modeling landscape. It is suggested that machine learning techniques are becoming more popular to develop prediction models to exploit complex data structures, higher-dimensional predictor spaces, very large number of participants, heterogeneous subgroups, with the ability to capture higher-order interactions. We examine the changes in modelling practices by investigating a selection of systematic reviews on prediction models published in the biomedical literature. We selected systematic reviews published between 2020 and 2022 which included at least 50 prediction models. Information was extracted guided by the CHARMS checklist. Time trends were explored using the models published since 2005. We identified 8 reviews, which included 1448 prediction models published in 887 papers. The average number of study participants and outcome events increased considerably between 2015 and 2019 but remained stable afterwards. The number of candidate and final predictors did not noticeably increase over the study period, with a few recent studies using very large numbers of predictors. Internal validation and reporting of discrimination measures became more common, but assessing calibration and carrying out external validation were less common. Information about missing values was not reported in about half of the papers, however the use of imputation methods increased. There was no sign of an increase in using of machine learning methods. Overall, most of the findings were heterogeneous across reviews. Our findings indicate that changes in the prediction modeling landscape in biomedicine are smaller than expected and that poor reporting is still common; adherence to well established best practice recommendations from the traditional biostatistics literature is still needed. For machine learning best practice recommendations are still missing, whereas such recommendations are available in the traditional biostatistics literature, but adherence is still inadequate.
Keywords: predictive model, medicine, changes
Published in RUP: 14.10.2025; Views: 295; Downloads: 7
Full text (6,00 MB)
This document has more files! More... |
