1. |
2. Intraspecific geographical variability of Phlebotomus perniciosus assessed by MALDI-TOF MS protein profilingVít Dvořák, Carla Maia, Rafael Marmé, José Risueño, Pedro Pérez-Cutillas, Eduardo Berriatua, Julie Sevila, Nalia Mekarnia, Jorian Prudhomme, Fano José Randriananambinintsoa, Vladimir Ivović, Katja Adam, 2026, original scientific article Abstract: Background Matrix‑assisted laser desorption/ionization time‑of‑flight mass spectrometry (MALDI‑TOF MS) pro‑ tein profiling has emerged over the last decade as a method of choice for species identification of many medically important arthropods. However, the influence of intraspecific variability on the performance of this popular technique has seldom been tested. This study provides the first standardized comparison of different geographical popula‑ tions of Phlebotomus perniciosus, a vector of Leishmania infantum and Toscana virus in the western Mediterranean, by MALDI‑TOF MS protein profiling. Methods Phlebotomus perniciosus males were collected in five countries (Portugal, Spain, France, Italy, Croa‑ tia) that represent most of its distribution in Europe. All samples were trapped, stored and processed according to a highly standardized protocol to avoid effects other than geographical origin on their protein spectra acquired by MALDI‑TOF MS protein profiling. The obtained protein spectra were compared with laboratory‑reared specimens of Ph. perniciosus. Results Twenty‑two analysed specimens from five geographical populations provided protein spectra that were highly similar, species‑specific and clustering according to their quality. No grouping according to geographical origin was observed, and the protein spectra of field‑collected specimens showed similar composition and complexity to spectra from Ph. perniciosus laboratory colony‑reared in captivity for several decades. Conclusions Our findings demonstrate that in samples of a same sex, with the same collection method and storage time, MALDI‑TOF MS protein profiling does not reflect the geographical origin of analysed specimens, confirming the value of this technique for high‑fidelity and reproducible species identification of sand flies regardless of their geographical origin.
Keywords: intraspecific geographical variability, Phlebotomus perniciosus, MALDI-TOF
Published in RUP: 29.06.2026; Views: 172; Downloads: 5
 Full text (944,26 KB)
This document has more files! More... |
3. What do listeners attend to when listening to music? : Toward explainable music recommendationsKosar Seyyedhosseinzadeh, Matevž Pesek, Marko Tkalčič, 2026, published scientific conference contribution Abstract: Personalized explanations in recommender systems can be useful when they reflect the aspects of an item that matter to the user. To account for individual preferences regarding different aspects of songs in music recommender systems, it is first necessary to identify which song aspects explain meaningful variation among listeners. This paper introduces a questionnaire instrument designed to operationalize these differences as a measurable user characteristic. The instrument was developed through item generation, expert review, pilot testing, and a main study. Data from the main study (� = 245) were analyzed using exploratory factor analysis to examine the questionnaire’s internal structure. The results supported a two-factor solution, interpreted as Lyric- Engagement and Music-Engagement, with both dimensions showing good internal consistency. These findings suggest that listeners’ orientations toward lyrical and musical elements can be measured in an interpretable way. The contribution of this study lies not in proposing a new explanation algorithm, but in providing an empirical basis for user modeling that may help align explanation content with the song characteristics most relevant to different listeners.
Keywords: music recommender systems, explainable recommendation, personalized explanations, user modeling, questionnaire development, exploratory factor analysis
Published in RUP: 26.06.2026; Views: 195; Downloads: 4
Full text (1,04 MB)
This document has more files! More... |
4. Eco-sustainable food packaging : biobased multi-active films to mitigate migration of mineral oils and polyolefin oligomeric saturated hydrocarbonsAna Miklavčič Višnjevec, Laura Barp, Donatella Peressini, Sabrina Moret, 2026, review article Abstract: The migration of mineral oils from recycled paper and cardboard packaging to food has raised increasing con- cerns in recent years. In addition to mineral oil hydrocarbons (MOH), polyolefin oligomeric hydrocarbons (POH), a class of synthetic hydrocarbons derived from the polymerization of olefins such as ethylene and propylene, and often analytically mistaken for MOH, also pose a risk. POH can migrate from plastic materials into food, espe- cially those made with polyolefins like polyethylene (PE) and polypropylene (PP), which are widely used in food packaging (films, trays, containers, etc.). Several solutions have been proposed, and others are still under development to address this issue. Currently, the most promising approach is the introduction of polymeric materials as a barrier to prevent the migration of these contaminants. The primary aim of this review is to provide an updated overview of the migration of MOH and POH from conventional packaging materials into foods, the parameters influencing this process, recent advances in innovative eco-sustainable barrier materials, and the testing methods used to measure their migration. Special attention is given to biopolymers, as they enhance the sustainability of paper and cardboard packaging while maintaining their recyclability.
Keywords: mineral oil hydrocarbons, polyolefin oligomeric saturated hydrocarbons, food packaging, sustainability, barrier materials
Published in RUP: 26.06.2026; Views: 166; Downloads: 11
Full text (2,80 MB)
This document has more files! More... |
5. |
6. Uporaba algoritmov strojnega učenja za ugotavljanje stopnje stresa na podlagi digitalnih navad : zaključno deloBor Dovč, 2026, undergraduate thesis Keywords: strojno učenje, napovedni modeli, digitalne navade, stopnja stresa, klasifikacija, regresija, CSV format, ARFF format, WEKA, ZeroR, Naivni Bayes, Random Forest, J48, Linearna regresija, SMOreg, M5P, zaključno delo
Published in RUP: 21.06.2026; Views: 173; Downloads: 12
Full text (492,47 KB) |
7. |
8. |
9. |
10. Efficient material selection for training occluded mmWave radar-based gesture recognisersNuwan Attygalle, Luis A. Leiva, Matjaž Kljun, Klen Čopič Pucihar, 2026, original scientific article Abstract: 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.
Keywords: deep learning, training optimization for neural networks, millimetre-wave radar, gesture recognition, material selection, sampling, synthetic noise
Published in RUP: 19.06.2026; Views: 201; Downloads: 9
Full text (15,56 MB)
This document has more files! More... |
