Iskanje po katalogu digitalne knjižnice

Opis: Tehnologija za tridimenzionalno prikazovanje slik postaja vedno bolj dostopna in popularna. 3D zasloni in naglavni zasloni so že stalnica moderne tehnike, vendar so samo približek 3D prikazovalnikom, kot jih poznamo iz znanstvene fantastike. Napredki in odkritja v laserski tehnologiji v zadnjem desetletju nam danes omogočajo nove, inovativne pristope za razvoj t.i. pravih 3D volumetričnih prikazovalnikov, ki sliko prikazujejo v prostem volumnu poljubne velikosti, brez potrebe po zaslonu ali drugih pripomočkih, kot so recimo 3D očala. Volumetrični prikazovalniki so sicer znani že nekaj časa in so nam nekateri na voljo tudi v komercialni obliki, ampak vsi pristopi so bili do sedaj omejeni na velikosti in obliko volumna, v katerem se slika prikazuje. V pričujočem zaključnem delu smo raziskali področje in preučili različne tehnike za prikaz. Opredelili smo lastnosti in omejitve posameznih pristopov ter jih med seboj primerjali, z namenom da ugotovimo kateri pristop se najbolj približa volumetričnim prikazovalnikom, kot jih poznamo iz znanstvene fantastike.
Ključne besede: volumetrični prikaz, volumetrični zaslon, 3D prikaz, 3D zaslon
Objavljeno v DKUM: 08.08.2024; Ogledov: 189; Prenosov: 26
Celotno besedilo (2,97 MB)

Opis: This thesis explores the development of an augmented reality (AR) application for educational purposes, focusing on human anatomy visualization using the Microsoft HoloLens 2 device. Leveraging Blender, Unity, and the Mixed Reality Toolkit (MRTK), the project aims to create immersive educational experiences. Key stages involve model selection, preparation in Blender, and addressing export challenges to Unity. Performance optimizations and scripting solutions ensure efficient functionality, while the user interface is designed for intuitive navigation. Through features like layer visibility toggling and object manipulation, the application offers a comprehensive learning experience. Ongoing testing ensures optimal performance on the HoloLens 2 device, highlighting the potential of AR in education to enhance engagement and learning outcomes.
Ključne besede: human anatomy, augmented reality, Microsoft HoloLens 2, Unity
Objavljeno v DKUM: 22.05.2024; Ogledov: 234; Prenosov: 16
Celotno besedilo (2,08 MB)

Opis: This paper proposes a new string transformation technique called Move with Interleaving (MwI). Four possible ways of rearranging 2D raster images into 1D sequences of values are applied, including scan-line, left-right, strip-based, and Hilbert arrangements. Experiments on 32 benchmark greyscale raster images of various resolutions demonstrated that the proposed transformation reduces information entropy to a similar extent as the combination of the Burrows–Wheeler transform followed by the Move-To-Front or the Inversion Frequencies. The proposed transformation MwI yields the best result among all the considered transformations when the Hilbert arrangement is applied.
Ključne besede: computer science, algorithm, string transformation, information entropy, Hilbert space filling curve
Objavljeno v DKUM: 22.05.2024; Ogledov: 160; Prenosov: 8
Celotno besedilo (26,44 MB)
Gradivo ima več datotek! Več...

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: 496; Prenosov: 306
Celotno besedilo (1,46 MB)
Gradivo ima več datotek! Več...

Opis: Knowledge Graphs (KGs) describe objective facts in the form of RDF triples, each triple contains sufficient semantic information and triple structure information. Knowledge Graph Completion (KGC) is to acquire new knowledge by predicting hidden relationships between entities and adding the new knowledge to the KG. At present, the mainstream KGC approaches only applied the triple structure information or only utilized the semantic information of the text. This paper proposes an approach (TSTR) using BERT and deep neural networks to fully extract the semantic information of knowledge, and designs an aggregated re-ranking scheme that incorporates existing graph embedding approach to learn the structural information of triples. In experiments, the approach achieves state-of-the-art performance on three benchmark datasets, and outperforms recent KGC approaches on sparsely connected datasets.
Ključne besede: knowledge graph completion, BERT, deep convolutional architecture, re-ranking
Objavljeno v DKUM: 19.02.2024; Ogledov: 229; Prenosov: 18
Celotno besedilo (1,03 MB)
Gradivo ima več datotek! Več...