1. Izdelava animacij z zajemom gibanja in izrazov obrazaŽiga Pukl, 2024, undergraduate thesis Abstract: Diplomsko delo obravnava izdelavo animacije z zajemanjem gibanja in izrazov obraza ter je razdeljeno na dva dela. Prvi del vključuje teoretični opis animacije, zajemanja gibanja ter ključnih mejnikov na obrazu in strategije za razporeditev označevalcev. V drugem delu je opisana izdelava dveh animacij v programu Blender z zajemanjem gibanja obraza. Pri čemer smo uporabili dve različni razporeditvi označevalcev, eno z več označevalci kot drug. V obeh animacijah smo izrazili šest opredeljenihuniverzalnih čustev. Po primerjavi smo ugotovili, da je animacija z več označevalci v našem primeru imela minimalno, ne takoj očitno vizualno razliko v primerjavi z drugo animacijo.
Keywords: zajemanje gibanja obraza, markerji, univerzalna čustva obraza, računalniška animacija
Published in DKUM: 19.09.2024; Views: 0; Downloads: 17
 Full text (2,37 MB) |
2. |
3. A review of federated learning in agricultureKrista Rizman Žalik, Mitja Žalik, 2023, review article Abstract: Federated learning (FL), with the aim of training machine learning models using data and computational resources on edge devices without sharing raw local data, is essential for improving agricultural management and smart agriculture. This study is a review of FL applications that address various agricultural problems. We compare the types of data partitioning and types of FL (horizontal partitioning and horizontal FL, vertical partitioning and vertical FL, and hybrid partitioning and transfer FL), architectures (centralized and decentralized), levels of federation (cross-device and cross-silo), and the use of aggregation algorithms in different reviewed approaches and applications of FL in agriculture. We also briefly review how the communication challenge is solved by different approaches. This work is useful for gaining an overview of the FL techniques used in agriculture and the progress made in this field.
Keywords: federated learning, agriculture, architecture, data partitioning, federation scal, aggregation algorithms, communication bottleneck
Published in DKUM: 05.06.2024; Views: 142; Downloads: 36
Full text (839,33 KB)
This document has many files! More... |
4. A new transformation technique for reducing information entropy : a case study on greyscale raster imagesBorut Žalik, Damjan Strnad, David Podgorelec, Ivana Kolingerová, Luka Lukač, Niko Lukač, Simon Kolmanič, Krista Rizman Žalik, Štefan Kohek, 2023, original scientific article Abstract: 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.
Keywords: computer science, algorithm, string transformation, information entropy, Hilbert space filling curve
Published in DKUM: 22.05.2024; Views: 160; Downloads: 15
Full text (26,44 MB)
This document has many files! More... |
5. Density-based entropy centrality for community detection in complex networksKrista Rizman Žalik, Mitja Žalik, 2023, original scientific article Abstract: One of the most important problems in complex networks is the location of nodes that are essential or play a main role in the network. Nodes with main local roles are the centers of real communities. Communities are sets of nodes of complex networks and are densely connected internally. Choosing the right nodes as seeds of the communities is crucial in determining real communities. We propose a new centrality measure named density-based entropy centrality for the local identification of the most important nodes. It measures the entropy of the sum of the sizes of the maximal cliques to which each node and its neighbor nodes belong. The proposed centrality is a local measure for explaining the local influence of each node, which provides an efficient way to locally identify the most important nodes and for community detection because communities are local structures. It can be computed independently for individual vertices, for large networks, and for not well-specified networks. The use of the proposed density-based entropy centrality for community seed selection and community detection outperforms other centrality measures.
Keywords: networks, undirected graphs, community detection, node centrality, label propagation
Published in DKUM: 06.02.2024; Views: 335; Downloads: 26
Full text (707,65 KB)
This document has many files! More... |
6. IoT and satellite sensor data integration for assessment of environmental variables: a case study on NO2Jernej Cukjati, Domen Mongus, Krista Rizman Žalik, Borut Žalik, 2022, original scientific article Abstract: This paper introduces a novel approach to increase the spatiotemporal resolution of an arbitrary environmental variable. This is achieved by utilizing machine learning algorithms to construct a satellite-like image at any given time moment, based on the measurements from IoT sensors. The target variables are calculated by an ensemble of regression models. The observed area is gridded, and partitioned into Voronoi cells based on the IoT sensors, whose measurements are available at the considered time. The pixels in each cell have a separate regression model, and take into account the measurements of the central and neighboring IoT sensors. The proposed approach was used to assess NO2 data, which were obtained from the Sentinel-5 Precursor satellite and IoT ground sensors. The approach was tested with three different machine learning algorithms: 1-nearest neighbor, linear regression and a feed-forward neural network. The highest accuracy yield was from the prediction models built with the feed-forward neural network, with an RMSE of 15.49 ×10−6 mol/m2.
Keywords: Internet of Things, IoT, remote sensing, sensor integration, machine learning, ensemble method
Published in DKUM: 22.09.2023; Views: 514; Downloads: 116
Full text (3,72 MB)
This document has many files! More... |
7. Modeliranje in animiranje las : diplomsko deloJulija Pestiček, 2022, undergraduate thesis Abstract: Znotraj področja računalniške grafike je modeliranje las eden izmed temeljnih del za ustvarjanje virtualnih ljudi. Te lahko ustvarimo s pomočjo programske opreme, kot je npr. Blender. Namen diplomskega dela v teoretičnem delu je s pomočjo deskriptivne in kompilacijske metode predstaviti računalniško grafiko, modeliranje ter animiranje las. Prav tako smo predstavili sistem delcev in programsko opremo Blender. V praktičnem delu smo z eksperimentalno metodo preizkusili način modeliranja las s pomočjo sistema delcev znotraj Blenderja. Izdelali smo animacijo, pri kateri lasje plapolajo v vetru.
Keywords: računalniška grafika, lasje, Blender, sistem delcev
Published in DKUM: 21.10.2022; Views: 606; Downloads: 123
Full text (1,63 MB) |
8. 3D modeliranje realnega prostora v okolju Blender : diplomsko deloNikita Plej, 2022, undergraduate thesis Abstract: Diplomsko delo 3D modeliranje realnega prostora v okolju Blender je sestavljeno iz dveh delov. Prvi del predstavlja teorijo iz področja fotorealizma, grafičnega modeliranja in krajšo predstavitvijo vseh komponent in korakov, ki jih zajema proces grafičnega modeliranja. Na kratko je predstavljen tudi program Blender, v katerem je potekal proces tridimenzionalnega modeliranja scene, ki je kot celota predstavljen v drugem delu našega diplomskega dela. Tam so predstavljeni vsi postopki modeliranja posameznih modelov, ki predstavljajo komponente naše scene. Sledi implementacija materialov in tekstur na izdelane modele, sestavljanje celotne scene prostora, osvetlitev scene ter končna fotorealistična upodobitev našega prostora.
Keywords: 3D modeliranje, Blender, fotorealizem
Published in DKUM: 17.10.2022; Views: 842; Downloads: 130
Full text (3,26 MB) |
9. Uporaba orodij Blender in Maya za izdelavo 3D simulacij : diplomsko deloMagdalena Dolenčić, 2022, undergraduate thesis Abstract: Osnovni namen diplomskega dela je izdelati 3D simulacije ognja, tekočine in tkanine v programa za izdelavo 3D animacij in simulacij Blender in Maya. Pri izdelavi smo uporabili orodja za izdelavo scene, v katero smo kasneje s pomočjo orodji in vgrajenih vtičnikov umestili simulacije. Postopke izdelave scene in simulacij smo podrobno opisali. Na koncu smo primerjali orodja, ki jih ponujata programa Blender in Maya za izdelavo simulacij, izglede simulacij ter časa potrebna za upodabljanje.
Keywords: Blender, Maya, simulacija, računalna grafika
Published in DKUM: 17.10.2022; Views: 833; Downloads: 97
Full text (3,24 MB) |
10. Zajemanje 3D objektov s pomočjo fotogrametrije za potrebe animacije in 3D tiskanja : diplomsko deloNika Tomšič, 2021, undergraduate thesis Abstract: V diplomski nalogi smo raziskali fotogrametrijo v povezavi z računalniško animacijo in 3D tiskanjem. Fotogrametrija je zaenkrat še slabo poznana tehnika zajemanja tridimenzionalnih objektov, uporablja pa se že v mnogih velikih podjetjih na različnih področjih, do neke mere pa je dostopna že skoraj vsakemu posamezniku. Tudi 3D tiskanje je v zadnjem desetletju postalo zelo popularen hobi, animacija pa se praktično že pojavlja povsod v zabavni industriji in oglaševanju. Cilj diplomske naloge je ustvariti čim boljšo repliko izbranega objekta s pomočjo fotogrametrije. Pridobljeni 3D model smo še prototipirali s 3D tiskalnikom in ga uporabili v animaciji.
Keywords: fotogrametrija, 3D tiskanje, animacija, geometrijsko modeliranje
Published in DKUM: 18.10.2021; Views: 1167; Downloads: 156
Full text (2,78 MB) |
