| | 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


1 - 10 / 181
Na začetekNa prejšnjo stran12345678910Na naslednjo stranNa konec
Smart education systems supported by ICT and AI
Boris Aberšek, Andrej Flogie, 2023, predgovor, uvodnik, spremna beseda

Ključne besede: teaching and learning, smart education systems, education and technology, ICT, artificial intelligence
Objavljeno v DKUM: 05.04.2024; Ogledov: 177; Prenosov: 2
.pdf Celotno besedilo (175,31 KB)
Gradivo ima več datotek! Več...

Cross-Hole GPR for Soil Moisture Estimation Using Deep Learning
Blaž Pongrac, Dušan Gleich, Marko Malajner, Andrej Sarjaš, 2023, izvirni znanstveni članek

Opis: This paper presents the design of a high-voltage pulse-based radar and a supervised data processing method for soil moisture estimation. The goal of this research was to design a pulse-based radar to detect changes in soil moisture using a cross-hole approach. The pulse-based radar with three transmitting antennas was placed into a 12 m deep hole, and a receiver with three receive antennas was placed into a different hole separated by 100 m from the transmitter. The pulse generator was based on a Marx generator with an LC filter, and for the receiver, the high-frequency data acquisition card was used, which can acquire signals using 3 Gigabytes per second. Used borehole antennas were designed to operate in the wide frequency band to ensure signal propagation through the soil. A deep regression convolutional network is proposed in this paper to estimate volumetric soil moisture using time-sampled signals. A regression convolutional network is extended to three dimensions to model changes in wave propagation between the transmitted and received signals. The training dataset was acquired during the period of 73 days of acquisition between two boreholes separated by 100 m. The soil moisture measurements were acquired at three points 25 m apart to provide ground truth data. Additionally, water was poured into several specially prepared boreholes between transmitter and receiver antennas to acquire additional dataset for training, validation, and testing of convolutional neural networks. Experimental results showed that the proposed system is able to detect changes in the volumetric soil moisture using Tx and Rx antennas.
Ključne besede: ground penetrating radar, cross-hole, L-band, deep learning, convolutional neural network, soil moisture estimation
Objavljeno v DKUM: 03.04.2024; Ogledov: 117; Prenosov: 9
.pdf Celotno besedilo (3,22 MB)
Gradivo ima več datotek! Več...

E-learning in nursing and midwifery during the COVID-19 pandemic
Nataša Mlinar Reljić, Maja Drešček Dolinar, Gregor Štiglic, Sergej Kmetec, Zvonka Fekonja, Barbara Donik, 2023, pregledni znanstveni članek

Opis: As the COVID-19 pandemic continues to spread, e-learning has increased. This is a challenge for nursing and midwifery students, as clinical training is an essential part of their education. The aim of this review was to identify the advantages and limitations of e-learning for nursing and midwifery students during the COVID-19 pandemic. A systematic review of the literature was conducted following the PRISMA guidelines. The international databases PubMed, CINAHL/MEDLINE, Web of Science, and ScienceDirect were searched. Articles were critically appraised. Thematic analysis was used to synthesise the data. The search resulted in 91 hits. Thirteen studies were included in the final analysis. Three main themes were identified: (1) the benefits of e-learning; (2) the challenges/limitations of e-learning; and (3) recommendations for e-learning. E-learning in nursing and midwifery is an effective alternative learning process during the COVID-19 pandemic. Students perceive several benefits and challenges related to internet access, technical equipment, financial aspects, and work and family commitments.
Ključne besede: e-learning, nursing care, midwifery, pandemic
Objavljeno v DKUM: 03.04.2024; Ogledov: 96; Prenosov: 9
.pdf Celotno besedilo (2,71 MB)
Gradivo ima več datotek! Več...

A graph pointer network-based multi-objective deep reinforcement learning algorithm for solving the traveling salesman problem
Jeewaka Perera, Shih-Hsi Liu, Marjan Mernik, Matej Črepinšek, Miha Ravber, 2023, izvirni znanstveni članek

Opis: Traveling Salesman Problems (TSPs) have been a long-lasting interesting challenge to researchers in different areas. The difficulty of such problems scales up further when multiple objectives are considered concurrently. Plenty of work in evolutionary algorithms has been introduced to solve multi-objective TSPs with promising results, and the work in deep learning and reinforcement learning has been surging. This paper introduces a multi-objective deep graph pointer network-based reinforcement learning (MODGRL) algorithm for multi-objective TSPs. The MODGRL improves an earlier multi-objective deep reinforcement learning algorithm, called DRL-MOA, by utilizing a graph pointer network to learn the graphical structures of TSPs. Such improvements allow MODGRL to be trained on a small-scale TSP, but can find optimal solutions for large scale TSPs. NSGA-II, MOEA/D and SPEA2 are selected to compare with MODGRL and DRL-MOA. Hypervolume, spread and coverage over Pareto front (CPF) quality indicators were selected to assess the algorithms’ performance. In terms of the hypervolume indicator that represents the convergence and diversity of Pareto-frontiers, MODGRL outperformed all the competitors on the three well-known benchmark problems. Such findings proved that MODGRL, with the improved graph pointer network, indeed performed better, measured by the hypervolume indicator, than DRL-MOA and the three other evolutionary algorithms. MODGRL and DRL-MOA were comparable in the leading group, measured by the spread indicator. Although MODGRL performed better than DRL-MOA, both of them were just average regarding the evenness and diversity measured by the CPF indicator. Such findings remind that different performance indicators measure Pareto-frontiers from different perspectives. Choosing a well-accepted and suitable performance indicator to one’s experimental design is very critical, and may affect the conclusions. Three evolutionary algorithms were also experimented on with extra iterations, to validate whether extra iterations affected the performance. The results show that NSGA-II and SPEA2 were greatly improved measured by the Spread and CPF indicators. Such findings raise fairness concerns on algorithm comparisons using different fixed stopping criteria for different algorithms, which appeared in the DRL-MOA work and many others. Through these lessons, we concluded that MODGRL indeed performed better than DRL-MOA in terms of hypervolumne, and we also urge researchers on fair experimental designs and comparisons, in order to derive scientifically sound conclusions.
Ključne besede: multi-objective optimization, traveling salesman problems, deep reinforcement learning
Objavljeno v DKUM: 28.03.2024; Ogledov: 93; Prenosov: 9
.pdf Celotno besedilo (7,89 MB)
Gradivo ima več datotek! Več...

Reduction of surface defects by optimization of casting speed using genetic programming : an industrial case study
Miha Kovačič, Uroš Župerl, Leo Gusel, Miran Brezočnik, 2023, izvirni znanstveni članek

Opis: Štore Steel Ltd. produces more than 200 different types of steel with a continuous caster installed in 2016. Several defects, mostly related to thermomechanical behaviour in the mould, originate from the continuous casting process. The same casting speed of 1.6 m/min was used for all steel grades. In May 2023, a project was launched to adjust the casting speed according to the casting temperature. This adjustment included the steel grades with the highest number of surface defects and different carbon content: 16MnCrS5, C22, 30MnVS5, and 46MnVS5. For every 10 °C deviation from the prescribed casting temperature, the speed was changed by 0.02 m/min. During the 2-month period, the ratio of rolled bars with detected surface defects (inspected by an automatic control line) decreased for the mentioned steel grades. The decreases were from 11.27 % to 7.93 %, from 12.73 % to 4.11 %, from 16.28 % to 13.40 %, and from 25.52 % to 16.99 % for 16MnCrS5, C22, 30MnVS5, and 46MnVS5, respectively. Based on the collected chemical composition and casting parameters from these two months, models were obtained using linear regression and genetic programming. These models predict the ratio of rolled bars with detected surface defects and the length of detected surface defects. According to the modelling results, the ratio of rolled bars with detected surface defects and the length of detected surface defects could be minimally reduced by 14 % and 189 %, respectively, using casting speed adjustments. A similar result was achieved from July to November 2023 by adjusting the casting speed for the other 27 types of steel. The same was predicted with the already obtained models. Genetic programming outperformed linear regression.
Ključne besede: continuous casting of steel, surface defects, automatic control, machine learning, modelling, optimisation, prediction, linear regression, genetic programming
Objavljeno v DKUM: 25.03.2024; Ogledov: 150; Prenosov: 9
.pdf Celotno besedilo (1,19 MB)
Gradivo ima več datotek! Več...

Assessment of supporting visual learning technologies in the immersive VET cyber-physical learning model
Matej Veber, Igor Pesek, Boris Aberšek, 2023, izvirni znanstveni članek

Opis: Humanity faces diverse technological, societal, and sociological challenges. Digitalization is being integrated into every aspect of our lives. Technologies are developing rapidly and the ways in which we live and learn are changing. Young people are acquiring information and learning in a different way than in the recent past. Education systems are no longer keeping up with the development of technology. Education systems need to adapt and introduce technologies that motivate students and ultimately contribute to higher learning goals. To this end, we need to develop modern learning models that support education and technological development. In previous research, we developed and evaluated a state-of-the-art learning model, the CPLM. We built on this with a new study, in which we assessed the difference between the cognitive activities of attention and meditation in students during the viewing of a classical educational video, a 360° video, and an AR app on a screen. We found that the 360° video had the greatest impact on students' attention and is consequently suitable for initially motivating students in the proposed learning model. We made a proposal for a modern educational model and possibilities for further research.
Ključne besede: XR immersive technologies, VET education, 360° video, educational video, innovative learning method development, assessment
Objavljeno v DKUM: 18.03.2024; Ogledov: 210; Prenosov: 243
.pdf Celotno besedilo (3,98 MB)
Gradivo ima več datotek! Več...

Graph theory approaches to maturity models : master thesis
Špela Kajzer, 2024, magistrsko delo

Opis: The masters thesis, which follows the paper Graph drawing applications in combinatorial theory of maturity models, in preparation, coauthored by the author of the thesis, introduces the tiled graphs as models of learning and maturing processes. In the thesis, we show how tiled graphs can combine graphs of learning spaces or antimatroids (partial cubes) and maturity models (total orders) to yield models of learning processes. We visualise processes with optimal drawings. In the thesis, we show NP-hardness of visualisation problems resulting from most detailed models. Further, we introduce a simpler model, which ignores the details of learning and for which the visualisation problem can be solved in a polynomial time. For the rest of the thesis, we consider this model. We describe an algorithm, which finds a drawing of an ordinal panel data graph with a minimal number of edge crossings. For this problem we further define an extremal crossing number for a chosen family of ordinal panel data. Further, we explore a certain type of random instances of ordinal panel data and the expected value of a crossing number for this type of random instances. After that, we define a problem of finding the most suitable ordering on categories in panel data, in other words finding the best maturity model to fit the data. We prove the NP-hardness of the problem and formulate an integer linear program. Master thesis consists of nine chapters. The first chapter contains known results and definitions from set and graph theory and a section of computational complexity theory (NP-hardness), which will be used throughout the thesis. The following chapters present the new theory introduced in the aforementioned paper in preparation and the needed additional results and definitions. In the last chapter we present the thesis and some selected parts of the thesis with the help of learning space theory. The chapter serves as both the overview of the thesis and the use case for the theory of learning spaces, presented in the thesis.
Ključne besede: Maturity models, learning spaces, crossing number, crossing minimisation, tile crossing number.
Objavljeno v DKUM: 14.03.2024; Ogledov: 248; Prenosov: 7
.pdf Celotno besedilo (1,46 MB)

Agile Machine Learning Model Development Using Data Canyons in Medicine : A Step towards Explainable Artificial Intelligence and Flexible Expert-Based Model Improvement
Bojan Žlahtič, Jernej Završnik, Helena Blažun Vošner, Peter Kokol, David Šuran, Tadej Završnik, 2023, izvirni znanstveni članek

Opis: Over the past few decades, machine learning has emerged as a valuable tool in the field of medicine, driven by the accumulation of vast amounts of medical data and the imperative to harness this data for the betterment of humanity. However, many of the prevailing machine learning algorithms in use today are characterized as black-box models, lacking transparency in their decision-making processes and are often devoid of clear visualization capabilities. The transparency of these machine learning models impedes medical experts from effectively leveraging them due to the high-stakes nature of their decisions. Consequently, the need for explainable artificial intelligence (XAI) that aims to address the demand for transparency in the decision-making mechanisms of black-box algorithms has arisen. Alternatively, employing white-box algorithms can empower medical experts by allowing them to contribute their knowledge to the decision-making process and obtain a clear and transparent output. This approach offers an opportunity to personalize machine learning models through an agile process. A novel white-box machine learning algorithm known as Data canyons was employed as a transparent and robust foundation for the proposed solution. By providing medical experts with a web framework where their expertise is transferred to a machine learning model and enabling the utilization of this process in an agile manner, a symbiotic relationship is fostered between the domains of medical expertise and machine learning. The flexibility to manipulate the output machine learning model and visually validate it, even without expertise in machine learning, establishes a crucial link between these two expert domains.
Ključne besede: XAI, explainable artificial intelligence, data canyons, machine learning, transparency, agile development, white-box model
Objavljeno v DKUM: 14.03.2024; Ogledov: 153; Prenosov: 10
.pdf Celotno besedilo (5,28 MB)
Gradivo ima več datotek! Več...

A VAN-Based Multi-Scale Cross-Attention Mechanism for Skin Lesion Segmentation Network
Shuang Liu, Zeng Zhuang, Yanfeng Zheng, Simon Kolmanič, 2023, izvirni znanstveni članek

Opis: With the rise of deep learning technology, the field of medical image segmentation has undergone rapid development. In recent years, convolutional neural networks (CNNs) have brought many achievements and become the consensus in medical image segmentation tasks. Although many neural networks based on U-shaped structures and methods, such as skip connections have achieved excellent results in medical image segmentation tasks, the properties of convolutional operations limit their ability to effectively learn local and global features. To address this problem, the Transformer from the field of natural language processing (NLP) was introduced to the image segmentation field. Various Transformer-based networks have shown significant performance advantages over mainstream neural networks in different visual tasks, demonstrating the huge potential of Transformers in the field of image segmentation. However, Transformers were originally designed for NLP and ignore the multidimensional nature of images. In the process of operation, they may destroy the 2D structure of the image and cannot effectively capture low-level features. Therefore, we propose a new multi-scale cross-attention method called M-VAN Unet, which is designed based on the Visual Attention Network (VAN) and can effectively learn local and global features. We propose two attention mechanisms, namely MSC-Attention and LKA-Cross-Attention, for capturing low-level features and promoting global information interaction. MSC-Attention is designed for multi-scale channel attention, while LKA-Cross-Attention is a cross-attention mechanism based on the large kernel attention (LKA). Extensive experiments show that our method outperforms current mainstream methods in evaluation metrics such as Dice coefficient and Hausdorff 95 coefficient.
Ključne besede: CNNs, deep learning, medical image processing, NLP, semantic segmentation
Objavljeno v DKUM: 14.03.2024; Ogledov: 388; Prenosov: 297
.pdf Celotno besedilo (1,46 MB)
Gradivo ima več datotek! Več...

Iskanje izvedeno v 0.26 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici