31. Efficient material selection for training occluded mmWave radar-based gesture recognisersNuwan Attygalle, Luis A. Leiva, Matjaž Kljun, Klen Čopič Pucihar, 2026, izvirni znanstveni članek Opis: Radar-based gesture recognition has emerged as a promising approach for unobtrusive interaction. Unlike camera-based systems, radar sensors can detect gestures through opaque materials, enabling seamless embedding into various everyday objects. However, it remains unclear how to train models efficiently for robust gesture recognition through diverse materials. To investigate this, we collected a dataset of 17,520 gesture recordings performed through 73 everyday materials. By comparing several material-sampling and data-augmentation strategies, we found that a small carefully selected representative subset of training materials was sufficient to match performance of a classifier trained on the full material dataset. Our results showed that the models trained on 14 quota-sampled materials achieved accuracies of 95.8% and 91.2%, comparable to training on all 73 materials (96.8% and 91.6%) and significantly better than training without material data (66.8% and 65.8%). Among the evaluated sampling approaches, Quota sampling also provided the best overall trade-off between performance and practicality. In contrast, classifiers trained on augmented data performed worse than those trained on actual material-specific data. Taken together, these findings indicate that, for the tested sensor, gesture set, and material collection, carefully selected real-material data offer a practical route to reducing material-specific data collection in radar-based gesture recognition while preserving generalisation. Code, models, and data are available in the public repository, with additional details provided in the supplementary materials: https://gitlab.com/hicuplab/seeing-through. Ključne besede: deep learning, training optimization for neural networks, millimetre-wave radar, gesture recognition, material selection, sampling, synthetic noise Objavljeno v RUP: 19.06.2026; Ogledov: 412; Prenosov: 12
Celotno besedilo (15,56 MB) Gradivo ima več datotek! Več... |
32. On the uniform structure of bipartite graphs admitting a dual adjacency matrix candidateBlas Fernández, Roghayeh Maleki, Štefko Miklavič, Giusy Monzillo, 2026, izvirni znanstveni članek Opis: Let Γ denote a finite, bipartite, connected graph with vertex set X. Fix x ∈ X and let ε ≥ 3 denote the eccentricity of x. For mutually distinct scalars {θ ∗ i }ε i=0 define a diagonal matrix A∗ = A∗(θ ∗ 0 , θ ∗ 1 , . . . , θ ∗ ε ) ∈ Mat X (R) as follows: for y ∈ X set (A∗)yy = θ ∗ ∂(x,y), where ∂ denotes the shortest path-length distance function of Γ. We say that A∗ is a dual adjacency matrix candidate of Γ with respect to x if the adjacency matrix A ∈ Mat X (R) of Γ and A∗ satisfy A3 A∗ − A∗ A3 + (β + 1)(A A∗ A2 − A2 A∗ A) = ρ(A A∗ − A∗ A) for some scalars β, ρ ∈ R. In this paper, we investigate when bipartite graphs that admit a dual adjacency matrix candidate also admit a uniform structure (in the sense of Terwilliger [6]). To do that, we first define a weakly uniform structure by slightly relaxing the conditions of uniform structure. The main result of this paper is that Γ admits a dual adjacency matrix candidate with respect to x if and only if Γ admits a weakly uniform structure with respect to x whose parameters satisfy some additional conditions. In particular, for β = 2, the weakly uniform structure is indeed a uniform structure. Ključne besede: uniform property, dual adjacency matrix, Q-polynomial property Objavljeno v RUP: 18.06.2026; Ogledov: 479; Prenosov: 10
Celotno besedilo (318,25 KB) Gradivo ima več datotek! Več... |
33. |
34. On the role of dwell time for implicitly profiling museum visitorsAlessio Ferrato, Giuseppe Sansonetti, Marko Tkalčič, 2026, objavljeni znanstveni prispevek na konferenci Opis: How long visitors spend viewing artworks, often referred to as dwell time, has long been studied in museology as a potential behavioral indicator of engagement. However, dwell time may encode both genuine preference and situational factors such as fatigue, and disentangling these signals for computational modeling has received limited attention. This study investigates whether dwell time can serve as a valid preference indicator for implicit user modeling and whether incorporating it can improve artwork recommendation. Using the BIRD dataset, which includes eye-tracking data for extracting dwell times and explicit preferences from 51 museum visitors, we report three main findings. First, visitors spend significantly longer (9.27 seconds on average) viewing artworks they like, with a large effect size (Cohen’s d = 1.47). Second, we confirm the museum fatigue phenomenon, the progressive decline in visitor attention throughout a visit, observing a 34% reduction in dwell time from visit start to end. Third, we evaluate collaborative filtering approaches and find that while purely implicit models using dwell time alone perform near-chance level, a hybrid approach that uses dwell time to compute item similarities while predicting preferences from explicit likes achieves the best performance (AUC-ROC = 0.755, AP = 0.522). These findings suggest that dwell time provides complementary information to explicit feedback and can enhance museum recommendation systems when appropriately integrated. Ključne besede: implicit, user modeling, recommender systems, artwork, museum Objavljeno v RUP: 09.06.2026; Ogledov: 563; Prenosov: 72
Celotno besedilo (672,97 KB) Gradivo ima več datotek! Več... |
35. Progress feedback for countering selective exposure : when visualization can backfireJanine Riemann, Jasmin Alt, Uroš Sergaš, Marko Tkalčič, Bruce Ferwerda, 2026, objavljeni znanstveni prispevek na konferenci Opis: Selective exposure in online news is often attributed to person- alization mechanisms and user modeling. Recent work proposes interface-level interventions that visualize reading balance or frame cross-cutting exposure as progress. However, we lack empirical evidence on whether alternative representations of user-model feedback meaningfully influence engagement with belief-opposing content. We conducted a between-subject experiment (N = 84) in a controlled news environment comparing two representations of diversity feedback: (1) an analytic bias visualization summarizing viewpoint balance and (2) a metaphorical growth visualization fram- ing cross-cutting exposure as personal development. Across behav- ioral and attitudinal measures of open-minded engagement, neither feedback representation increased engagement relative to control, and the two designs did not differ reliably. Our results suggest that lightweight representations of diversity signals—without adaptive personalization or structural changes to recommendations—may be insufficient to alter selective exposure in single-session settings. We discuss implications for designing user-model feedback and depolarization objectives in recommender systems. Ključne besede: human-centered computing, human computer interaction, information systems, recommender systems Objavljeno v RUP: 05.06.2026; Ogledov: 467; Prenosov: 26
Celotno besedilo (534,45 KB) Gradivo ima več datotek! Več... |
36. Game on for news : stance-aware gamification in a news aggregator to promote engagement with diverse viewpointsCaroline Frössling, Uroš Sergaš, Marko Tkalčič, Bruce Ferwerda, 2026, objavljeni znanstveni prispevek na konferenci Opis: Personalized news systems often adapt ranking to user preferences, which can reinforce selective exposure. We investigate an alterna- tive personalization strategy: stance-aware incentive shaping. In- stead of modifying content ranking, we use a minimal per-topic stance user model to adapt reward gradients, awarding more points for engaging with counter-attitudinal content. In a between-subject experiment (� = 98), we compare a non- adaptive baseline with two adaptive incentive framings (levels vs. leaderboards). Stance-aware gamification increased behavioral en- gagement (clicks and time), while subjective engagement and com- prehension did not differ reliably. Only the level-based framing produced significant pre–post increases in stance change and open- minded thinking, with effects varying by topic. We position stance-aware incentive shaping as a lightweight user-model intervention that adapts motivational feedback rather than ranking, offering an alternative pathway for diversity-aware personalization in recommender systems. Ključne besede: information systems, recommender systems, personalization, human-centered computing, user studies Objavljeno v RUP: 05.06.2026; Ogledov: 487; Prenosov: 12
Celotno besedilo (1,05 MB) Gradivo ima več datotek! Več... |
37. Impact of the invasive South African ragwort on germination and growth of radishKatarina Šoln, 2026, izvirni znanstveni članek Opis: The South African ragwort Senecio inaequidens is among the most invasive plant species in Europe, especially in mountainous and Mediterranean regions, and is suspected to exert allelopathic effects (release of chemical inhibitors) on native vegetation. This study investigated the allelopathic potential of South African ragwort using radish Raphanus sativus as a model species. In laboratory experiments, I treated radish seeds with ragwort leaf extracts at varying concentrations. After three days, the extract reduced radish seed germination by up to 40% in a concentration-dependent manner. High extract concentrations significantly inhibited radish seedling root length, whereas lower concentrations rather stimulated root growth. Measurements of oxidative stress-related parameters, including lipid peroxidation and total antioxidative ca- pacity, showed no changes in treated roots. In a complementary pot experiment, I exposed radish seeds for 36 days to pul- verised ragwort leaves mixed with vermiculite. This treatment delayed, but did not suppress seed germination. Subsequent plant growth and physiological status remained unaffected. The results suggest that South African ragwort exerts moder- ate allelopathic effects, primarily influencing seedlings, whereas mature plants appear less sensitive to its allelochemicals. Ključne besede: allelopathy, oxidative stress, phytotoxicity, Raphanus sativus, South African ragwort, Senecio inaequidens Objavljeno v RUP: 04.06.2026; Ogledov: 408; Prenosov: 13
Celotno besedilo (347,75 KB) Gradivo ima več datotek! Več... |
38. Extremal totally regular mixed graphs and partially oriented incidence graphs of projective and biaffine planesTatiana Bagin Jajcay, Robert Jajcay, György Kiss, István Porupsánszki, 2025, izvirni znanstveni članek Opis: An (r, z; g)-mixed graph is a graph containing both edges and darts satisfying the regularity property that each vertex of the graph is incident to r edges, z ingoing and z outgoing darts (called total regularity), and being of oriented girth g, i.e., containing an oriented cycle of length g, and no shorter oriented cycles. The problem addressed in this paper is analogous to the Cage Problem and calls for determining the orders of the smallest totally regular (r, z; g)-mixed graphs. We derive several upper and lower bounds on the orders of such minimal graphs, study the relations between these extremal graphs and their non-oriented or digraphical counterparts, and focus on properties of totally regular mixed graphs obtained by replacing some of the edges of the incidence graphs of projective and biaffine planes by darts. We also introduce two constructions based on introducing additional edges or darts into induced subgraphs of these incidence graphs. Ključne besede: totally regular mixed graph, girth, projective plane, biaffine plane Objavljeno v RUP: 04.06.2026; Ogledov: 463; Prenosov: 25
Celotno besedilo (480,02 KB) Gradivo ima več datotek! Več... |
39. Evaluating depolarization-oriented news ranking strategies using LLM-generated articlesUroš Sergaš, Marko Tkalčič, Bruce Ferwerda, 2026, objavljeni znanstveni prispevek na konferenci Opis: Algorithmic news ranking and large language models (LLMs) increasingly mediate how citizens receive political information. While personalization is often criticized for reinforcing echo chambers, ranking has also been proposed as a lever for depolarization by shaping exposure to cross-cutting viewpoints. We test this claim in an online experiment (N=100, Prolific) using five LLM-generated news articles on gun legislation spanning pro–gun freedom to pro–gun control. All participants read the same articles; the only manipulation was article order, instantiated as a random baseline and six stance-aware depolarization-oriented strategies (counter-narrative sandwich, balanced alternation, and directional gradients). Pre–post questionnaires measured ideological self- placement (feeling thermometer) and affective evaluations of gun-control and gun-freedom advocates. Across six research questions, we find no statistically reliable evidence that any ranking strategy reduces ideological or affective polarization relative to the baseline, nor that stance-conditioned assignment improves outcomes. These results suggest that, under the constraints of a short, single-session, single-topic exposure study with LLM-generated article stimuli, article ordering alone did not produce detectable depolarization effects. The findings motivate future work to design longer-term, multi-topic, and more interactive solutions for mitigating affective polarization. Ključne besede: news recommendation, political polarization, affective polarization, ranking strategies, large language models Objavljeno v RUP: 02.06.2026; Ogledov: 527; Prenosov: 10
Celotno besedilo (1,09 MB) Gradivo ima več datotek! Več... |
40. Bridging mountains and seas : genomic and plastid data evidence for two migration routes of Drypis spinosa across the Adriatic–Ionian regionPeter Glasnović, Ivan Radosavljević, Sara Laura Šarančić, Damjan Mitić, Boštjan Surina, 2026, izvirni znanstveni članek Opis: Aim Amphi–Adriatic–Ionian plant taxa, distributed on both the Balkan and Apennine peninsulas, exemplify one of the many diversity patterns characteristic of the Mediterranean biodiversity hotspot. To better understand these patterns, we examined the genetic and morphological variability, as well as the present day and Last Glacial Maximum (LGM) potential distribution of a scree-dwelling plant endemic to the study region. Location Amphi–Adriatic–Ionian region within the Mediterranean basin. Taxon Drypis spinosa L. (Caryophyllaceae). Methods Population genomics and phylogeographic patterns were investigated by analysing single–nucleotide polymorphisms (SNPs) and plastid DNA markers. Morphometric techniques were additionally used to assess taxonomic relationships. Environmental niche modelling (ENM) was applied to evaluate potential occurrences under present-day and LGM conditions. Results Genetic data revealed concordant patterns of genetic diversity, indicating that the mountainous areas of the western Balkans harbour the highest genetic variability in D. spinosa. Historical connections were detected among populations from the Kvarner area, the central and southern Apennines, and the Scardo–Pindic Mountains. Neither molecular nor morphological analyses supported the historically proposed lower-rank taxonomic distinctions. ENM suggests a substantial increase in favourable conditions during the LGM compared to the present day. Main Conclusions Our findings indicate two primary links between the Balkan Peninsula and the Apennines: one spanning the northern and central Adriatic Sea, involving populations from the Kvarner area and the central Dinaric Alps, and another connecting the Scardo–Pindic Mountains across the Ionian Sea. This reveals a biogeographical pattern not previously documented in plants with an Amphi–Adriatic–Ionian distribution. Ključne besede: Amphi–Adriatic–Ionian distribution, environmental niche modelling, genomics, Mediterranean, morphometrics, phylogeography, plastid DNA Objavljeno v RUP: 25.05.2026; Ogledov: 478; Prenosov: 11
Celotno besedilo (7,75 MB) Gradivo ima več datotek! Več... |