| | SLO | ENG | Piškotki in zasebnost

Večja pisava | Manjša pisava

Iskanje po katalogu digitalne knjižnice Pomoč

Iskalni niz: išči po
išči po
išči po
išči po
* po starem in bolonjskem študiju

Opcije:
  Ponastavi


1 - 10 / 54
Na začetekNa prejšnjo stran123456Na naslednjo stranNa konec
1.
Hybrid reality development - can social responsibility concepts provide guidance?
Igor Perko, 2021, izvirni znanstveni članek

Opis: Purpose: This paper aims to define hybrid reality (HyR) as an ongoing process in which artificial intelligence (AI) technology is gradually introduced as an active stakeholder by using reasoning to execute real-life activities. Also, to examine the implications of social responsibility (SR) concepts as featured in the HyR underlying common framework to progress towards the redefinition of global society. Design/methodology/approach: A combination of systemic tools is used to examine and assess the development of HyR. The research is based on evolutionary and learning concepts, leading to the new meta-system development. It also builds upon the viable system model and AI, invoking SR as a conceptual framework. The research is conducted by using a new approach: using system dynamics based interactions modelling, the following two models have been proposed. The state-of-the-art HyR interactions model, examined using SR concepts; and a SR concept-based HyR model, examined using a smart vehicle case. Findings: In the HyR model, interaction asymmetry between stakeholders is identified, possibly leading to pathological behaviour and AI technology learning corruption. To resolve these asymmetry issues, an interaction model based on SR concepts is proposed and examined on the example of an autonomous vehicle transport service. The examination results display significant changes in the conceptual understanding of transport services, their utilisation and data-sharing concepts. Research limitations/implications: As the research proposal is theoretical in nature, the projection may not display a fully holistic perspective and can/should be complemented with empirical research results. Practical implications: For researchers, HyR provides a new paradigm and can thereby articulate potential research frameworks. HyR designers can recognise projected development paths and the resources required for the implication of SR concepts. Individuals and organisations should be aware of their not necessarily passive role in HyR and can therefore use the necessary social force to activate their status. Originality/value: For the first time, to the best of the author’s knowledge, the term HyR is openly elaborated and systemically examined by invoking concepts of SR. The proposed model provides an overview of the current and potential states of HyR and examines the gap between them.
Ključne besede: artificial intelligence, social responsibility, systems thinking, cybernetics, hybrid reality, interactions model
Objavljeno v DKUM: 04.02.2025; Ogledov: 0; Prenosov: 2
.pdf Celotno besedilo (796,19 KB)
Gradivo ima več datotek! Več...

2.
3.
4.
Automatic classification of older electronic texts into the Universal Decimal Classification-UDC
Matjaž Kragelj, Mirjana Kljajić Borštnar, 2021, izvirni znanstveni članek

Opis: Purpose:The purpose of this study is to develop a model for automated classification of old digitised texts to the Universal Decimal Classification (UDC), using machine-learning methods. Design/methodology/approach: The general research approach is inherent to design science research, in which the problem of UDC assignment of the old, digitised texts is addressed by developing a machine-learning classification model. A corpus of 70,000 scholarly texts, fully bibliographically processed by librarians, was used to train and test the model, which was used for classification of old texts on a corpus of 200,000 items. Human experts evaluated the performance of the model. Findings: Results suggest that machine-learning models can correctly assign the UDC at some level for almost any scholarly text. Furthermore, the model can be recommended for the UDC assignment of older texts. Ten librarians corroborated this on 150 randomly selected texts. Research limitations/implications: The main limitations of this study were unavailability of labelled older texts and the limited availability of librarians. Practical implications: The classification model can provide a recommendation to the librarians during their classification work; furthermore, it can be implemented as an add-on to full-text search in the library databases. Social implications: The proposed methodology supports librarians by recommending UDC classifiers, thus saving time in their daily work. By automatically classifying older texts, digital libraries can provide a better user experience by enabling structured searches. These contribute to making knowledge more widely available and useable. Originality/value: These findings contribute to the field of automated classification of bibliographical information with the usage of full texts, especially in cases in which the texts are old, unstructured and in which archaic language and vocabulary are used.
Ključne besede: digital library, artificial intelligence, machine learning, text classification, older texts, Universal Decimal Classification
Objavljeno v DKUM: 28.01.2025; Ogledov: 0; Prenosov: 2
.pdf Celotno besedilo (1,91 MB)
Gradivo ima več datotek! Več...

5.
An end-to-end framework for extracting observable cues of depression from diary recordings
Izidor Mlakar, Umut Arioz, Urška Smrke, Nejc Plohl, Valentino Šafran, Matej Rojc, 2024, izvirni znanstveni članek

Opis: Because of the prevalence of depression, its often-chronic course, relapse and associated disability, early detection and non-intrusive monitoring is a crucial tool for timely diagnosis and treatment, remission of depression and prevention of relapse. In this way, its impact on quality of life and well-being can be limited. Current attempts to use artificial intelligence for the early classification of depression are mostly data-driven and thus non-transparent and lack effective means to deal with uncertainties. Therefore, in this paper, we propose an end-to-end framework for extracting observable depression cues from diary recordings. Furthermore, we also explore its feasibility for automatic detection of depression symptoms using observable behavioural cues. The proposed end-to-end framework for extracting depression was used to evaluate 28 video recordings from the Symptom Media dataset and 27 recordings from the DAIC-WOZ dataset. We compared the presence of the extracted features between recordings of individuals with and without a depressive disorder. We identified several cues consistent with previous studies in terms of their differentiation between individuals with and without depressive disorder across both datasets among language (i.e., use of negatively valanced words, use of first-person singular pronouns, some features of language complexity, explicit mentions of treatment for depression), speech (i.e., monotonous speech, voiced speech and pauses, speaking rate, low articulation rate), and facial cues (i.e., rotational energy of head movements). The nature/context of the discourse, the impact of other disorders and physical/psychological stress, and the quality and resolution of the recordings all play an important role in matching the digital features to the relevant background. In this way, the work presented in this paper provides a novel approach to extracting a wide range of cues relevant to the classification of depression and opens up new opportunities for further research.
Ključne besede: digital biomarkers of depression, facial cues, speech cues, language cues, deep learning, end-to-end pipeline, artificial intelligence
Objavljeno v DKUM: 17.01.2025; Ogledov: 0; Prenosov: 1
.pdf Celotno besedilo (2,34 MB)

6.
Advanced tools for education : ChatGPT-based learning preparations
Dejan Zemljak, 2023, izvirni znanstveni članek

Opis: Artificial intelligence (AI) is increasingly permeating our daily lives, and the field of education is no exception. Technology already plays a significant role in education, and AI is rapidly advancing. Chatbots, for instance, have been used as a valuable tool in schools for decades. With the emergence of tools like ChatGPT, their usage has expanded even further. The presence of such tools can be highly beneficial for teachers in the educational setting. The study focused on the fact that ChatGPT can serve as an excellent support for teachers in lesson planning. The usefulness of the tool and the challenges that teachers may encounter when using it to create lesson plans were explored. The results of the study, based on the analysis of 58 lesson plans created using ChatGPT, revealed certain limitations. Therefore, it is crucial to empower teachers to make prudent use of this tool.
Ključne besede: artificial intelligence, learning preparation, technology and engineering, natural science
Objavljeno v DKUM: 10.12.2024; Ogledov: 0; Prenosov: 5
.pdf Celotno besedilo (410,59 KB)
Gradivo ima več datotek! Več...

7.
Comparative analysis of human and artificial intelligence planning in production processes
Matjaž Roblek, Tomaž Kern, Eva Krhač Andrašec, Alenka Brezavšček, 2024, izvirni znanstveni članek

Opis: Artificial intelligence (AI) has found applications in enterprises′ production planning processes. However, a critical question remains: could AI replace human planners? We conducted a comparative analysis to evaluate the main task of planners in an intermittent process: planning the duration of production orders. Specifically, we analysed the results of a human planner using master data and those of an AI algorithm compared to the actual realisation. The case study was conducted in a large production company using a sample of production products and machines. We were able to confirm two of the three research questions (RQ1 and RQ3), while the results of the third question (RQ2) did not meet our expectations. The AI algorithms demonstrated significant improvement with each iteration. Despite this progress, it is still difficult to determine the exact threshold at which AI outperforms human planners due to the unpredictability of unexpected events. Even though AI significantly improves prediction accuracy, the inherent variability and incomplete input data pose a major challenge. As progress is made, robust data collection and management strategies need to be integrated to bridge the gap between the potential of AI and its practical application, fostering the symbiosis between human expertise and AI capabilities in production planning.
Ključne besede: artificial intelligence, machine learning, production processes, production planning, production scheduling
Objavljeno v DKUM: 04.12.2024; Ogledov: 0; Prenosov: 13
.pdf Celotno besedilo (3,27 MB)
Gradivo ima več datotek! Več...

8.
Language-based game theory in the age of artificial intelligence
Valerio Capraro, Roberto Di Paolo, Matjaž Perc, Veronica Pizziol, 2024, pregledni znanstveni članek

Opis: Understanding human behaviour in decision problems and strategicinteractions has wide-ranging applications in economics, psychology andartificial intelligence. Game theory offers a robust foundation for this under-standing, based on the idea that individuals aim to maximize a utilityfunction. However, the exact factors influencing strategy choices remainelusive. While traditional models try to explain human behaviour as a func-tion of the outcomes of available actions, recent experimental researchreveals that linguistic content significantly impacts decision-making, thusprompting a paradigm shift from outcome-based to language-based utilityfunctions. This shift is more urgent than ever, given the advancement ofgenerative AI, which has the potential to support humans in making criticaldecisions through language-based interactions. We propose sentiment analy-sis as a fundamental tool for this shift and take an initial step by analysing61 experimental instructions from the dictator game, an economic gamecapturing the balance between self-interest and the interest of others,which is at the core of many social interactions. Our meta-analysis showsthat sentiment analysis can explain human behaviour beyond economicoutcomes. We discuss future research directions. We hope this worksets the stage for a novel game-theoretical approach that emphasizes theimportance of language in human decisions.
Ključne besede: game theory, artificial intelligence, social preferences, language-based preferences, social physics, moral behavior, trust
Objavljeno v DKUM: 27.11.2024; Ogledov: 0; Prenosov: 6
.pdf Celotno besedilo (487,71 KB)
Gradivo ima več datotek! Več...

9.
Using generative artificial intelligence in bibliometric analysis : 10 years of research trends from the European Resuscitation congresses
Nino Fijačko, Ruth Masterson Creber, Benjamin S. Abella, Primož Kocbek, Špela Metličar, Robert Greif, Gregor Štiglic, 2024, drugi znanstveni članki

Opis: Aims: The aim of this study is to use generative artificial intelligence to perform bibliometric analysis on abstracts published at European Resuscitation Council (ERC) annual scientific congress and define trends in ERC guidelines topics over the last decade. Methods: In this bibliometric analysis, the WebHarvy software (SysNucleus, India) was used to download data from the Resuscitation journal’s website through the technique of web scraping. Next, the Chat Generative Pre-trained Transformer 4 (ChatGPT-4) application programming interface (Open AI, USA) was used to implement the multinomial classification of abstract titles following the ERC 2021 guidelines topics. Results: From 2012 to 2022 a total of 2491 abstracts have been published at ERC congresses. Published abstracts ranged from 88 (in 2020) to 368 (in 2015). On average, the most common ERC guidelines topics were Adult basic life support (50.1%), followed by Adult advanced life support (41.5%), while Newborn resuscitation and support of transition of infants at birth (2.1%) was the least common topic. The findings also highlight that the Basic Life Support and Adult Advanced Life Support ERC guidelines topics have the strongest co-occurrence to all ERC guidelines topics, where the Newborn resuscitation and support of transition of infants at birth (2.1%; 52/2491) ERC guidelines topic has the weakest co-occurrence. Conclusion: This study demonstrates the capabilities of generative artificial intelligence in the bibliometric analysis of abstract titles using the example of resuscitation medicine research over the last decade at ERC conferences using large language models.
Ključne besede: generative artificial intelligence, bibliometric analysis, congress, emergency medicine, European Resuscitation Council
Objavljeno v DKUM: 27.11.2024; Ogledov: 0; Prenosov: 0
.pdf Celotno besedilo (964,04 KB)

10.
Learning physical properties of liquid crystals with deep convolutional neural networks
Higor Y. D. Sigaki, Ervin K. Lenzi, Rafael S. Zola, Matjaž Perc, Haroldo V. Ribeiro, 2020, izvirni znanstveni članek

Opis: Machine learning algorithms have been available since the 1990s, but it is much more recently that they have come into use also in the physical sciences. While these algorithms have already proven to be useful in uncovering new properties of materials and in simplifying experimental protocols, their usage in liquid crystals research is still limited. This is surprising because optical imaging techniques are often applied in this line of research, and it is precisely with images that machine learning algorithms have achieved major breakthroughs in recent years. Here we use convolutional neural networks to probe several properties of liquid crystals directly from their optical images and without using manual feature engineering. By optimizing simple architectures, we fnd that convolutional neural networks can predict physical properties of liquid crystals with exceptional accuracy. We show that these deep neural networks identify liquid crystal phases and predict the order parameter of simulated nematic liquid crystals almost perfectly. We also show that convolutional neural networks identify the pitch length of simulated samples of cholesteric liquid crystals and the sample temperature of an experimental liquid crystal with very high precision.
Ključne besede: liquid crystal, neural network, artificial intelligence, soft matter
Objavljeno v DKUM: 20.11.2024; Ogledov: 0; Prenosov: 2
.pdf Celotno besedilo (1,94 MB)
Gradivo ima več datotek! Več...

Iskanje izvedeno v 0.31 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici