Digitalni repozitorij raziskovalnih organizacij Slovenije

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

Na voljo sta dva načina iskanja: enostavno in napredno. Enostavno iskanje lahko zajema niz več besed iz naslova, povzetka, ključnih besed, celotnega besedila in avtorja, zaenkrat pa ne omogoča uporabe operatorjev iskanja. Napredno iskanje omogoča omejevanje števila rezultatov iskanja z vnosom iskalnih pojmov različnih kategorij v iskalna okna in uporabo logičnih operatorjev (IN, ALI ter IN NE). V rezultatih iskanja se izpišejo krajši zapisi podatkov o gradivu, ki vsebujejo različne povezave, ki omogočajo vpogled v podroben opis gradiva (povezava iz naslova) ali sprožijo novo iskanje (po avtorjih ali ključnih besedah).

Pomoč
Išči po:
Možnosti:
 


1401 - 1410 / 2000
Na začetekNa prejšnjo stran137138139140141142143144145146Na naslednjo stranNa konec
1401.
Benchmarking sentence encoders in associating indicators with sustainable development goals and targets
Ana Gjorgjevikj, Kostadin Mishev, Dimitar Trajanov, Ljupčo Kocarev, 2025, izvirni znanstveni članek

Povzetek: The United Nations’ 2030 Agenda for Sustainable Development balances the economic, environmental, and social dimension of sustainable development in 17 Sustainable Development Goals (SDGs), monitored through a well-defined set of targets and global indicators. Although essential for humanity’s future well-being, this monitoring is still challenging due to the variable quality of the statistical data of global indicators compiled at the national level and the diversity of indicators used to monitor sustainable development at the subnational level. Associating indicators other than the global ones with the SDGs/targets may help not only to expand the statistical data, but to better align the efforts toward sustainable development taken at (sub)national level. This article presents a model-agnostic framework for associating such indicators with the SDGs and targets by comparing their textual descriptions in a common representation space. While removing the dependence on the quantity and quality of the statistical data of the indicators, it provides human experts with data-driven suggestions on the complex and not always obvious associations between the indicators and the SDGs/targets. A comprehensive domain-specific benchmarking of a diverse sentence encoder portfolio was performed first, followed by fine-tuning of the best ones on a newly created dataset. Five sets of indicators used at the (sub)national level of governance (around 800 indicators in total) were used for the evaluation. Finally, the influence of 40 factors on the results was analyzed using explainable artificial intelligence (xAI) methods. The results show that 1) certain sentence encoders are better suited to solving the task than others (potentially due to their diverse pre-training datasets), 2) the fine-tuning not only improves the predictive performance over the baselines but also reduces the sensitivity to changes in indicator description length (performance drops even by up to 17% for baseline models as length increases, but remains comparable for fine-tuned models), and 3) better selected training instances have the potential to improve the performance even further (taking into account the limited fine-tuning dataset currently used and the insights from the xAI analysis). Most importantly, this article contributes to filling the existing gap in comprehensive benchmarking of AI models in solving the problem.
Ključne besede: representation learning
Objavljeno v DiRROS: 21.08.2025; Ogledov: 344; Prenosov: 130
.pdf Celotno besedilo (6,64 MB)
Gradivo ima več datotek! Več...

1402.
Geometric learning in black-box optimization : a GNN framework for algorithm performance prediction
Ana Kostovska, Carola Doerr, Sašo Džeroski, Panče Panov, Tome Eftimov, 2025, objavljeni znanstveni prispevek na konferenci

Ključne besede: algorithm performance prediction, graph neural networks
Objavljeno v DiRROS: 21.08.2025; Ogledov: 413; Prenosov: 157
.pdf Celotno besedilo (1,08 MB)
Gradivo ima več datotek! Več...

1403.
Recent advances in meta-features used for representing black-box single-objective continuous optimization
Gjorgjina Cenikj, Ana Nikolikj, Tome Eftimov, 2025, objavljeni povzetek znanstvenega prispevka na konferenci

Ključne besede: learning algorithm features, learning problem landscape features, machine learning
Objavljeno v DiRROS: 21.08.2025; Ogledov: 402; Prenosov: 162
.pdf Celotno besedilo (8,97 MB)
Gradivo ima več datotek! Več...

1404.
Tracing the interactions of modular CMA-ES configurations across problem landscapes
Ana Nikolikj, Mario Andrés Muñoz, Eva Tuba, Tome Eftimov, 2025, objavljeni znanstveni prispevek na konferenci

Ključne besede: single-objective continuous optimization, landscape analysis, algorithm configuration footprint
Objavljeno v DiRROS: 21.08.2025; Ogledov: 386; Prenosov: 165
.pdf Celotno besedilo (1,79 MB)
Gradivo ima več datotek! Več...

1405.
1406.
Developing chemical literacy in non-formal learning environments : a systematic literature review
Alenka Dražić, Iztok Devetak, 2025, izvirni znanstveni članek

Objavljeno v DiRROS: 21.08.2025; Ogledov: 334; Prenosov: 159
.pdf Celotno besedilo (631,97 KB)
Gradivo ima več datotek! Več...

1407.
Using eye-movements to explain processing triple level of chemical information : systematic review
Miha Slapničar, Luka Ribič, Iztok Devetak, 2025, izvirni znanstveni članek

Objavljeno v DiRROS: 21.08.2025; Ogledov: 332; Prenosov: 160
.pdf Celotno besedilo (634,86 KB)
Gradivo ima več datotek! Več...

1408.
Upcycling of plastic waste into multi-walled carbon nanotubes as efficient organic dye adsorbent
Gordana Bogoeva Gaceva, Meri Sokolovska, Viktor Stefov, Metodija Najdoski, Sebastijan Kovačič, 2025, izvirni znanstveni članek

Povzetek: Multi-walled CNTs with an average diameter of about 80 nm, a length of several micrometers and surface area (SBET) of 100 m2 g–1 were obtained by pyrolysis of low-density polyethylene waste. The potential of the resulting MWCNTs material to purify water containing organic dyes was tested with Bezaktiv Blau HE-RM (BB) and Bezaktiv Rot S-3B (BR) reactive dyes. 200 mg L–1 MWCNT material was used to follow the adsorption of 30 mg L–1, 40 mg L–1, 50 mg L–1 and 60 mg L–1 BB and BR at pH 3 and a temperature of ~25 °C. The results have shown that this material has a high potential as a sorbent, and its adsorption capacity of 257 mg g–1 (for Bezaktiv BlauHE-RM) and 213 mg g–1 (for Bezaktiv Rot) is close to some commercial MWCNTs and functionalized MWCNT-based adsorbents. The adsorption process was very fast, reaching 80–90% of the dye removal in 10–15 minutes, and the equilibrium time was reached in 40–60 minutes. The adsorption isotherm showed that the Langmuir model was more suitable than the Freundlich model for describing the adsorption properties of the pollutants.
Ključne besede: adsorption, anionic dyes, upcycling plastic waste, carbon nanotubes
Objavljeno v DiRROS: 21.08.2025; Ogledov: 399; Prenosov: 176
.pdf Celotno besedilo (1,09 MB)
Gradivo ima več datotek! Več...

1409.
Manganese, cobalt, nickel and zinc complexes with pyrazine-2-carboxylic acid
Saša Petriček, 2025, izvirni znanstveni članek

Ključne besede: complex, zinc, manganese(II), pyrazine-2-carboxylic acid, structure, thermal stability
Objavljeno v DiRROS: 21.08.2025; Ogledov: 342; Prenosov: 181
.pdf Celotno besedilo (1,70 MB)
Gradivo ima več datotek! Več...

1410.
Comprehensive framework of sport events management
Edvard Kolar, Elnur E. Mammadov, 2025, izvirni znanstveni članek

Povzetek: Sports events are the main part of the organizational culture of sport with an impact on the promotion of the environ-ment in which they take place and also deve-lop tourism and other economies. The impacts of major sports events are a direct or indirect result of their management and organization and can be negative or positive. In accordance with this, the purpose of this article is to pre-sent the comprehensive conceptual framework (model) of the sports events management. To design the research, we used the methodology of writing a conceptual paper and the method approach called "model paper" which seeks to build a theoretical framework that predicts re-lationships that provides a bridge or connec-tion between different concepts and scientific disciplines. The developed conceptual frame-work presented in thisarticle comprehensively coverstheissueof management of major sports events and takes into account the specifics or characteristics of this type of project. The mu-tual coherence and connectivity of threemo-dels(strategic management models, projectmanagement methodology, sports event mana-gement theory and practice) define the general management model of a major sport events which holistically covers the problem of mana-gement of large sports events and provides the user of the framework with direct guidance on activities and requirements formanaging of this type of projects.
Ključne besede: major sport event, strategic management, project management, general framework, benefits of sport events
Objavljeno v DiRROS: 21.08.2025; Ogledov: 332; Prenosov: 161
.pdf Celotno besedilo (1,33 MB)
Gradivo ima več datotek! Več...

Iskanje izvedeno v 0.74 sek.
Na vrh