Iskanje po katalogu digitalne knjižnice

Opis: Entity alignment refers to the process of discovering entities representing the same object in different knowledge graphs (KG). Recently, some studies have learned other information about entities, but they are aspect-level simple information associations, and thus only rough entity representations can be obtained, and the advantage of multi-faceted information is lost. In this paper, a novel node-level information strong fusion framework (SFEA) is proposed, based on four aspects: structure, attribute, relation and names. The attribute information and name information are learned first, then structure information is learned based on these two aspects of information through graph convolutional network (GCN), the alignment signals from attribute and name are already carried at the beginning of the learning structure. In the process of continuous propagation of multi-hop neighborhoods, the effect of strong fusion of structure, attribute and name information is achieved and the more meticulous entity representations are obtained. Additionally, through the continuous interaction between sub-alignment tasks, the effect of entity alignment is enhanced. An iterative framework is designed to improve performance while reducing the impact on pre-aligned seed pairs. Furthermore, extensive experiments demonstrate that the model improves the accuracy of entity alignment and significantly outperforms 13 previous state-of-the-art methods.
Ključne besede: knowledge graph, entity ealignment, graph convolutional network, knowledge fusion
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (3,40 MB)
Gradivo ima več datotek! Več...

Opis: Health literacy (HL) and physical literacy (PL) are concepts responsible for achieving and maintaining positive health behaviors. This study aimed to investigate gender-specific associations: (i) between PL and HL; and (ii) among HL, PL, and body composition. We observed 253 students attending health-area high schools from southern Croatia (181 girls; 16.9 ± 1.4 years). HL was assessed by the European Health Literacy Survey Questionnaire, PL by the PLAYself questionnaire, and body composition by bioimpedance analysis. The t-test was used to assess the differences between genders, and Pearson’s correlation coefficients were calculated to establish the associations between variables. The results showed a similar level of HL (t-test = 0.2; p = 0.83) and PL (t-test = 0.01; p = 0.99) in boys and girls. Significant but small correlations were identified between HL and PL only in the girls (<10% of common variance). The body composition indices were significantly correlated with PL only in the boys (15–20% of common variance). Our research highlights the necessity of the independent evaluation of HL and PL in adolescence. Further studies evaluating other indices of health status in relation to PL and HL are warranted.
Ključne besede: health behavior, knowledge translation, public health, community-engaged research, youth, body build
Objavljeno v DKUM: 12.03.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (793,77 KB)
Gradivo ima več datotek! Več...

Opis: Knowledge discovery from databases (KDD) and data mining (DM) belong to the field of artificial intelligence (AI). The integration of artificial intelligence into various segments of the construction industry is still in its infancy, but it is expected to be used more widely soon, driven by the development of databases and data warehouses. By using BIM (Building Information Modelling) technologies in the planning of new buildings, we will be able to obtain valuable data. The situation is different for old, existing buildings and the building engineering associated with these properties. Civil engineers, renovation planners and architects need knowledge of the building before renovation. This knowledge is much less than the possibilities that exist. Information about the building can be found in provincial archives. For historic buildings, 10- 15% of the plans, drawings, descriptions, or projects are available. The remaining 85% must be researched on site, which is a lengthy and costly process and hinders the construction process. The question arose as to how the findings from the study of buildings based on written and preserved sources can be applied to the 85% of buildings for which no data is available. This paper presents the use of the collected data as an idea for an initiative to develop a database and modelling using artificial intelligence algorithms. The research study investigates the feature “load-bearing wall” for residential buildings with basements and floors built between 1857 and 1948 in the former Austro-Hungarian Empire. The aim of this study is to create a model to predict the characteristics of a building for which no archival material is available. The study is based on the use of artificial intelligence in the creation of decision trees to help engineers improve their knowledge of historic buildings in the former Austro-Hungarian Empire and building engineering for historic objects.
Ključne besede: knowledge discovery from data, machine learning, Austro-Hungarian Monarchy buildings
Objavljeno v DKUM: 03.03.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (6,35 MB)
Gradivo ima več datotek! Več...

Ključne besede: selective disclosure, anonymous credentia, verifiable credentials, zero-knowledge proof
Objavljeno v DKUM: 31.01.2025; Ogledov: 0; Prenosov: 9
Celotno besedilo (966,17 KB)

Opis: This paper uses the technology acceptance model (TAM) framework for the research of economic and geography students’ attitudes towards interdisciplinary knowledge. Based on the SmartPLS Structural equation modelling SEM variance-based method, research results were gained through analysis of survey data of economic and geography students. They participated in the Spationomy project in the period of 2017–2019. Online questionnaires were fulfilled before and after students’ participation in the project and their future behavioural intention to use interdisciplinary knowledge was analysed. Based on the research, we can confirm that the Spationomy project has achieved its purpose, as both groups of students (economic and geography students) have acquired interdisciplinary knowledge and students intend to use it also in the future. Therefore, we can argue that the students included in the project in practice gained recognition of systems thinking about the importance of mutual interdisciplinary cooperation towards achieving synergies. The results also show that TAM can be successfully implemented to analyse how students of economics and geography accept the use of interdisciplinary knowledge in the learning process, which is an important implication for management and education as well as from the theoretical implications viewpoint. While effective analysis using TAM has been used successfully and relatively frequently in economics and business field, we have not found relevant examples of its implementation in the broader field of geography. However, the acceptance of geographic information system (GIS) or other information technologies/information software (IT/IS) tool-based approaches of analysis in the geography field may be of most importance. Therefore, also, this represents an important implication for the research area.
Ključne besede: spatial exploration, economic data, economic students, geography students, TAM, PLS SEM, interdisciplinary knowledge, holism, interdependence, strategic management
Objavljeno v DKUM: 07.01.2025; Ogledov: 0; Prenosov: 8
Celotno besedilo (1,98 MB)
Gradivo ima več datotek! Več...