Digitalni repozitorij raziskovalnih organizacij Slovenije

Iskanje po repozitoriju
A+ | A- | Pomoč | SLO | ENG

Iskalni niz: išči po
išči po
išči po
išči po

Možnosti:
  Ponastavi


Iskalni niz: "polno besedilo" AND "organizacija" (Institut Jožef Stefan) .

31 - 40 / 150
Na začetekNa prejšnjo stran12345678910Na naslednjo stranNa konec
31.
FooDis : a food-disease relation mining pipeline
Gjorgjina Cenikj, Tome Eftimov, Barbara Koroušić-Seljak, 2023, izvirni znanstveni članek

Povzetek: Nowadays, it is really important and crucial to follow the new biomedical knowledge that is presented in scientific literature. To this end, Information Extraction pipelines can help to automatically extract meaningful relations from textual data that further require additional checks by domain experts. In the last two decades, a lot of work has been performed for extracting relations between phenotype and health concepts, however, the relations with food entities which are one of the most important environmental concepts have never been explored. In this study, we propose FooDis, a novel Information Extraction pipeline that employs state-of-the-art approaches in Natural Language Processing to mine abstracts of biomedical scientific papers and automatically suggests potential cause or treat relations between food and disease entities in different existing semantic resources. A comparison with already known relations indicates that the relations predicted by our pipeline match for 90% of the food-disease pairs that are common in our results and the NutriChem database, and 93% of the common pairs in the DietRx platform. The comparison also shows that the FooDis pipeline can suggest relations with high precision. The FooDis pipeline can be further used to dynamically discover new relations between food and diseases that should be checked by domain experts and further used to populate some of the existing resources used by NutriChem and DietRx.
Ključne besede: text mining, relation extraction, named entity recognition, named entity linking, food-disease relations
Objavljeno v DiRROS: 25.05.2023; Ogledov: 319; Prenosov: 149
.pdf Celotno besedilo (1,11 MB)
Gradivo ima več datotek! Več...

32.
Evaluation of parallel hierarchical differential evolution for min-max optimization problems using SciPy
Margarita Antoniou, Gregor Papa, 2022, objavljeni znanstveni prispevek na konferenci

Ključne besede: min-max optimization, parallelization, differential evolution, SciPy
Objavljeno v DiRROS: 19.05.2023; Ogledov: 229; Prenosov: 130
.pdf Celotno besedilo (1,39 MB)
Gradivo ima več datotek! Več...

33.
Optimisation techniques under uncertainty
Margarita Antoniou, Thomas Krak, Alexander Erreygers, Jasper De Bock, Gert De Cooman, 2019, objavljeni povzetek znanstvenega prispevka na konferenci

Ključne besede: Markov chains, evolutionary algorithms, limit expectations
Objavljeno v DiRROS: 18.05.2023; Ogledov: 231; Prenosov: 63
.pdf Celotno besedilo (555,72 KB)

34.
From language models to large-scale food and biomedical knowledge graphs
Gjorgjina Cenikj, Lidija Strojnik, Risto Angelski, Nives Ogrinc, Barbara Koroušić-Seljak, Tome Eftimov, 2023, izvirni znanstveni članek

Povzetek: Knowledge about the interactions between dietary and biomedical factors is scattered throughout uncountable research articles in an unstructured form (e.g., text, images, etc.) and requires automatic structuring so that it can be provided to medical professionals in a suitable format. Various biomedical knowledge graphs exist, however, they require further extension with relations between food and biomedical entities. In this study, we evaluate the performance of three state-of-the-art relation-mining pipelines (FooDis, FoodChem and ChemDis) which extract relations between food, chemical and disease entities from textual data. We perform two case studies, where relations were automatically extracted by the pipelines and validated by domain experts. The results show that the pipelines can extract relations with an average precision around 70%, making new discoveries available to domain experts with reduced human effort, since the domain experts should only evaluate the results, instead of finding, and reading all new scientific papers.
Ključne besede: biomedical knowledge graphs, relation-mining pipelines, relation extraction, validation
Objavljeno v DiRROS: 17.05.2023; Ogledov: 335; Prenosov: 138
.pdf Celotno besedilo (2,39 MB)
Gradivo ima več datotek! Več...

35.
The association between day-to-day stress experiences, recovery, and work engagement among office workers in academia : an Ecological Momentary Assessment study
Larissa Bolliger, Ellen Baele, Elena Colman, Gillian Debra, Junoš Lukan, Mitja Luštrek, Dirk De Bacquer, Els Clays, 2023, izvirni znanstveni članek

Povzetek: Objectives. This study aimed to investigate the associations between day-to-day work-related stress exposures (i.e., job demands and lack of job control), job strain, and next-day work engagement among office workers in academic settings. Additionally, we assessed the influence of psychological detachment and relaxation on next-day work engagement and tested for interaction effects of these recovery variables on the relationship between work-related stressors and next-day work engagement. Methods. Office workers from two academic settings in Belgium and Slovenia were recruited. This study is based on an Ecological Momentary Assessment (EMA) with a 15-working day data collection period using our self-developed STRAW smartphone application. Participants were asked repeatedly about their work-related stressors, work engagement, and recovery experiences. Fixed-effect model testing using random intercepts was applied to investigate within- and between-participant levels. Results. Our sample consisted of 55 participants and 2710 item measurements were analysed. A significant positive association was found between job control and next-day work engagement (β = 0.28, p < 0.001). Further, a significant negative association was found between job strain and next-day work engagement (β = −0.32, p = 0.05). Furthermore, relaxation was negatively associated with work engagement (β = −0.08, p = 0.03). Conclusions. This study confirmed previous results, such as higher job control being associated with higher work engagement and higher job strain predicting lower work engagement. An interesting result was the association of higher relaxation after the working day with a lower next-day work engagement. Further research investigating fluctuations in work-related stressors, work engagement, and recovery experiences is required.
Ključne besede: work-related stress, stress exposure, work engagement, office workers, academia
Objavljeno v DiRROS: 04.05.2023; Ogledov: 310; Prenosov: 141
.pdf Celotno besedilo (734,96 KB)
Gradivo ima več datotek! Več...

36.
Influence of the calcination duration of ▫$g-C_3N_4/TiO_2$▫ veggie-toast-like photocatalyst on the visible-light triggered photocatalytic oxidation of bisphenol A
Matevž Roškarič, Gregor Žerjav, Matjaž Finšgar, Janez Zavašnik, Albin Pintar, 2023, izvirni znanstveni članek

Povzetek: Two commercially available TiO2 (hexagonal-like and spherical-like particles) were used to investigate the effect of g-C3N4 “melting” on the photocatalytic properties of g-C3N4/TiO2 composites. Improvement in the contact between the components was observed when they were thermally treated at 350 °C for an extended period of time (between 2 and 72 h) due to the partial melting and phase fusion of g-C3N4. Consequently, the enhanced contact between the phases allows easier injection of photogenerated electrons from the conduction band of g-C3N4 into TiO2, improving charge carrier separation. The prepared composites were tested for bisphenol A degradation under visible-light illumination, which showed that the components that had been calcined for 24 h performed better due to the improved charge carrier separation. Superoxide anionic radicals and photogenerated holes were identified as active species in the photooxidation experiments conducted under visible-light illumination.
Ključne besede: titanium dioxide, photocatalyst, calcination time, photocatalysis under visible-light illumination, water remediation, bisphenol A
Objavljeno v DiRROS: 17.03.2023; Ogledov: 490; Prenosov: 234
.pdf Celotno besedilo (3,13 MB)
Gradivo ima več datotek! Več...

37.
38.
SciFoodNER : food named entity recognition for scientific text
Gjorgjina Cenikj, Gašper Petelin, Barbara Koroušić-Seljak, Tome Eftimov, 2022, objavljeni znanstveni prispevek na konferenci

Ključne besede: food, named entity recognition, named entity linking, information extraction
Objavljeno v DiRROS: 09.03.2023; Ogledov: 422; Prenosov: 213
.pdf Celotno besedilo (551,39 KB)
Gradivo ima več datotek! Več...

39.
Deposition of chitosan on plasma-treated polymers : a review
Alenka Vesel, 2023, pregledni znanstveni članek

Povzetek: Materials for biomedical applications often need to be coated to enhance their performance, such as their biocompatibility, antibacterial, antioxidant, and anti-inflammatory properties, or to assist the regeneration process and influence cell adhesion. Among naturally available substances, chitosan meets the above criteria. Most synthetic polymer materials do not enable the immobilization of the chitosan film. Therefore, their surface should be altered to ensure the interaction between the surface functional groups and the amino or hydroxyl groups in the chitosan chain. Plasma treatment can provide an effective solution to this problem. This work aims to review plasma methods for surface modification of polymers for improved chitosan immobilization. The obtained surface finish is explained in view of the different mechanisms involved in treating polymers with reactive plasma species. The reviewed literature showed that researchers usually use two different approaches: direct immobilization of chitosan on the plasma-treated surface or indirect immobilization by additional chemistry and coupling agents, which are also reviewed. Although plasma treatment leads to remarkably improved surface wettability, this was not the case for chitosan-coated samples, where a wide range of wettability was reported ranging from almost superhydrophilic to hydrophobic, which may have a negative effect on the formation of chitosan-based hydrogels.
Ključne besede: polymer surfaces, chitosan, coatings, plasma-surface modification, adhesion
Objavljeno v DiRROS: 24.02.2023; Ogledov: 357; Prenosov: 199
.pdf Celotno besedilo (6,88 MB)
Gradivo ima več datotek! Več...

40.
Tools for landscape analysis of optimisation problems in Procedural Content Generation for games
Vanessa Volz, Boris Naujoks, Pascal Kerschke, Tea Tušar, 2023, izvirni znanstveni članek

Povzetek: The term Procedural Content Generation (PCG) refers to the (semi-)automatic generation of game content by algorithmic means, and its methods are becoming increasingly popular in game-oriented research and industry. A special class of these methods, which is commonly known as search-based PCG, treats the given task as an optimisation problem. Such problems are predominantly tackled by evolutionary algorithms. We will demonstrate in this paper that obtaining more information about the defined optimisation problem can substantially improve our understanding of how to approach the generation of content. To do so, we present and discuss three efficient analysis tools, namely diagonal walks, the estimation of high-level properties, as well as problem similarity measures. We discuss the purpose of each of the considered methods in the context of PCG and provide guidelines for the interpretation of the results received. This way we aim to provide methods for the comparison of PCG approaches and eventually, increase the quality and practicality of generated content in industry.
Ključne besede: optimization, search-based procedural content generation, exploratory landscape analysis, Mario level generation
Objavljeno v DiRROS: 24.02.2023; Ogledov: 384; Prenosov: 157
.pdf Celotno besedilo (745,09 KB)

Iskanje izvedeno v 0.6 sek.
Na vrh