1. Optimization-based downscaling of satellite-derived isotropic broadband albedo to high resolutionNiko Lukač, Domen Mongus, Marko Bizjak, 2025, izvirni znanstveni članek Opis: In this paper, a novel method for estimating high-resolution isotropic broadband albedo is proposed, by downscaling satellite-derived albedo using an optimization approach. At first, broadband albedo is calculated from the lower-resolution multispectral satellite image using standard narrow-to-broadband (NTB) conversion, where the surfaces are considered Lambertian with isotropic reflectance. The high-resolution true orthophoto for the same location is segmented with the deep learning-based Segment Anything Model (SAM), and the resulting segments are refined with a classified digital surface model (cDSM) to exclude small transient objects. Afterwards, the remaining segments are grouped using K-means clustering, by considering orthophoto-visible (VIS) and near-infrared (NIR) bands. These segments present surfaces with similar materials and underlying reflectance properties. Next, the Differential Evolution (DE) optimization algorithm is applied to approximate albedo values to these segments so that their spatial aggregate matches the coarse-resolution satellite albedo, by proposing two novel objective functions. Extensive experiments considering different DE parameters over an 0.75 km2 large urban area in Maribor, Slovenia, have been carried out, where Sentinel-2 Level-2A NTB-derived albedo was downscaled to 1 m spatial resolution. Looking at the performed spatiospectral analysis, the proposed method achieved absolute differences of 0.09 per VIS band and below 0.18 per NIR band, in comparison to lower-resolution NTB-derived albedo. Moreover, the proposed method achieved a root mean square error (RMSE) of 0.0179 and a mean absolute percentage error (MAPE) of 4.0299% against ground truth broadband albedo annotations of characteristic materials in the given urban area. The proposed method outperformed the Enhanced Super-Resolution Generative Adversarial Networks (ESRGANs), which achieved an RMSE of 0.0285 and an MAPE of 9.2778%, and the Blind Super-Resolution Generative Adversarial Network (BSRGAN), which achieved an RMSE of 0.0341 and an MAPE of 12.3104%. Ključne besede: isotropic broadband albedo, high-resolution albedo, Sentinel-2 albedo, true orthophoto, anything model, differential evolution Objavljeno v DKUM: 23.04.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (20,47 MB) |
2. A hierarchical universal algorithm for geometric objects’ reflection symmetry detectionBorut Žalik, Damjan Strnad, Štefan Kohek, Ivana Kolingerová, Andrej Nerat, Niko Lukač, David Podgorelec, 2022, izvirni znanstveni članek Opis: A new algorithm is presented for detecting the global reflection symmetry of geometric
objects. The algorithm works for 2D and 3D objects which may be open or closed and may or may
not contain holes. The algorithm accepts a point cloud obtained by sampling the object’s surface at
the input. The points are inserted into a uniform grid and so-called boundary cells are identified.
The centroid of the boundary cells is determined, and a testing symmetry axis/plane is set through
it. In this way, the boundary cells are split into two parts and they are faced with the symmetry
estimation function. If the function estimates the symmetric case, the boundary cells are further split
until a given threshold is reached or a non-symmetric result is obtained. The new testing axis/plane
is then derived and tested by rotation around the centroid. This paper introduces three techniques to
accelerate the computation. Competitive results were obtained when the algorithm was compared
against the state of the art. Ključne besede: computer science, computational geometry, uniform subdivision, centroids Objavljeno v DKUM: 01.04.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (2,99 MB) Gradivo ima več datotek! Več... |
3. STALITA: innovative platform for bank transactions analysisDavid Jesenko, Štefan Kohek, Borut Žalik, Matej Brumen, Domen Kavran, Niko Lukač, Andrej Živec, Aleksander Pur, 2022, izvirni znanstveni članek Opis: Acts of fraud have become much more prevalent in the financial industry with the rise
of technology and the continued economic growth in modern society. Fraudsters are evolving
their approaches continuously to exploit the vulnerabilities of the current prevention measures
in place, many of whom are targeting the financial sector. To overcome and investigate financial
frauds, this paper presents STALITA, which is an innovative platform for the analysis of bank
transactions. STALITA enables graph-based data analysis using a powerful Neo4j graph database
and the Cypher query language. Additionally, a diversity of other supporting tools, such as support
for heterogeneous data sources, force-based graph visualisation, pivot tables, and time charts, enable
in-depth investigation of the available data. In the Results section, we present the usability of the
platform through real-world case scenarios. Ključne besede: Neo4j, platform, bank transactions, graph analysis, graph visualisation, fraud, investigation Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (1,44 MB) Gradivo ima več datotek! Več... |
4. Knowledge graph alignment network with node-level strong fusionShuang Liu, Man Xu, Yufeng Qin, Niko Lukač, 2022, izvirni znanstveni članek 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: 4
Celotno besedilo (3,40 MB) Gradivo ima več datotek! Več... |
5. Enhancing trust in automated 3D point cloud data interpretation through explainable counterfactualsAndreas Holzinger, Niko Lukač, Dzemail Rozajac, Emil Johnston, Veljka Kocic, Bernhard Hoerl, Christoph Gollob, Arne Nothdurft, Karl Stampfer, Stefan Schweng, Javier Del Ser, 2025, izvirni znanstveni članek Opis: This paper introduces a novel framework for augmenting explainability in the interpretation of point cloud data by fusing expert knowledge with counterfactual reasoning. Given the complexity and voluminous nature of point cloud datasets, derived predominantly from LiDAR and 3D scanning technologies, achieving interpretability remains a significant challenge, particularly in smart cities, smart agriculture, and smart forestry. This research posits that integrating expert knowledge with counterfactual explanations – speculative scenarios illustrating how altering input data points could lead to different outcomes – can significantly reduce the opacity of deep learning models processing point cloud data. The proposed optimization-driven framework utilizes expert-informed ad-hoc perturbation techniques to generate meaningful counterfactual scenarios when employing state-of-the-art deep learning architectures. The optimization process minimizes a multi-criteria objective comprising counterfactual metrics such as similarity, validity, and sparsity, which are specifically tailored for point cloud datasets. These metrics provide a quantitative lens for evaluating the interpretability of the counterfactuals. Furthermore, the proposed framework allows for the definition of explicit interpretable counterfactual perturbations at its core, thereby involving the audience of the model in the counterfactual generation pipeline and ultimately, improving their overall trust in the process. Results demonstrate a notable improvement in both the interpretability of the model’s decisions and the actionable insights delivered to end-users. Additionally, the study explores the role of counterfactual reasoning, coupled with expert input, in enhancing trustworthiness and enabling human-in-the-loop decision-making processes. By bridging the gap between complex data interpretations and user comprehension, this research advances the field of explainable AI, contributing to the development of transparent, accountable, and human-centered artificial intelligence systems. Ključne besede: explainable AI, point cloud data, counterfactual reasoning, information fusion, interpretability, human-centered AI Objavljeno v DKUM: 06.03.2025; Ogledov: 0; Prenosov: 4
Celotno besedilo (186,97 KB) |
6. Improved relation extraction through key phrase identification using community detection on dependency treesShuang Liu, Xunqin Chen, Jiana Meng, Niko Lukač, 2025, izvirni znanstveni članek Opis: A method for extracting relations from sentences by utilizing their dependency trees to identify key phrases is presented in this paper. Dependency trees are commonly used in natural language processing to represent the grammatical structure of a sentence, and this approach builds upon this representation to extract meaningful relations between phrases. Identifying key phrases is crucial in relation extraction as they often indicate the entities and actions involved in a relation. The method uses community detection algorithms on the dependency tree to identify groups of related words that form key phrases, such as subject-verb-object structures. The experiments on the Semeval-2010 task8 dataset and the TACRED dataset demonstrate that the proposed method outperforms existing baseline methods. Ključne besede: community detection algorithms, dependency trees, relation extraction Objavljeno v DKUM: 17.01.2025; Ogledov: 0; Prenosov: 5
Celotno besedilo (3,12 MB) |
7. Energy flexibility in aluminium smelting : a long-term feasibility study based on the prospects of electricity load and photovoltaic productionMarko Bizjak, Niko Uremović, Domen Mongus, Primož Sukič, Gorazd Štumberger, Haris Salihagić Hrenko, Dragan Mikša, Stanislav Kores, Niko Lukač, 2024, izvirni znanstveni članek Ključne besede: energy flexibility, aluminium smelting, renewable energy, virtual battery, solar production Objavljeno v DKUM: 17.12.2024; Ogledov: 0; Prenosov: 16
Celotno besedilo (1,91 MB) |
8. Novel GPU-accelerated high-resolution solar potential estimation in urban areas by using a modified diffuse irradiance modelNiko Lukač, Domen Mongus, Borut Žalik, Gorazd Štumberger, Marko Bizjak, 2024, izvirni znanstveni članek Opis: In the past years various methods have been developed to estimate high-resolution solar potential in urban areas, by simulating solar irradiance over surface models that originate from remote sensing data. In general, this requires discretisation of solar irradiance models that estimate direct, reflective, and diffuse irradiances. The latter is most accurately estimated by an anisotropic model, where the hemispherical sky dome from arbitrary surface’s viewpoint consists of the horizon, the circumsolar and sky regions. Such model can be modified to incorporate the effects of shadowing from obstruction with a view factor for each sky region. However, state-of-the-art using such models for estimating solar potential in urban areas, only considers the sky view factor, and not circumsolar view factor, due to high computational load. In this paper, a novel parallelisation of solar potential estimation is proposed by using General Purpose computing on Graphics Processing Units (GPGPU). Modified anisotropic Perez model is used by considering diffuse shadowing with all three sky view factors. Moreover, we provide validation based on sensitivity analysis of the method’s accuracy with independent meteorological measurements, by changing circumsolar sky region’s half-angle and resolution of the hemispherical sky dome. Finally, the presented method using GPPGU was compared to multithreaded Central Processing Unit (CPU) approach, where on average a 70x computational speedup was achieved. Finally, the proposed method was applied over a urban area, obtained from Light Detection And Ranging (LiDAR) data, where the computation of solar potential was performed in a reasonable time. Ključne besede: solar energy, solar potential, anisotropic diffuse irradiance, LiDAR, GPGPU Objavljeno v DKUM: 17.12.2024; Ogledov: 0; Prenosov: 4
Celotno besedilo (8,06 MB) |
9. Proceedings of the 10th Student Computing Research Symposium : (SCORES'24)2024, zbornik Opis: The 2024 Student Computing Research Symposium (SCORES 2024), organized by the Faculty of Electrical Engineering and Computer Science at the University of Maribor (UM FERI) in collabora-tion with the University of Ljubljana and the University of Primorska, showcases innovative student research in computer science. This year’s symposium highlights advancements in fields such as ar-tificial intelligence, data science, machine learning algorithms, computational problem-solving, and healthcare data analysis. The primary goal of SCORES 2024 is to provide a platform for students to present their research, fostering early engagement in academic inquiry. Beyond research presen-tations, the symposium seeks to create an environment where students from different institutions can meet, exchange ideas, and build lasting connections. It aims to cultivate friendships and future research collaborations among emerging scholars. Additionally, the conference offers an opportu-nity for students to interact with senior researchers from institutions beyond their own, promoting mentorship and broader academic networking. Ključne besede: evaluacija, optimizacija, strojno učenje, podatki, zborniki Objavljeno v DKUM: 26.11.2024; Ogledov: 0; Prenosov: 77
Celotno besedilo (35,41 MB) Gradivo ima več datotek! Več... |
10. Spletni katalog za ocenjevanje in priporočanje knjigVanesa Tot, 2024, diplomsko delo Opis: V diplomskem delu predstavimo razvoj spletnega kataloga za ocenjevanje in priporočanje knjig, ki uporablja kolaborativno filtriranje za personalizirano uporabniško izkušnjo. Spoznamo sorodne rešitve na trgu, ki uporabljajo priporočilne sisteme. Obravnavamo glavne pristope priporočilnih sistemov, kot sta kolaborativno in vsebinsko filtriranje in se pri razvoju aplikacije osredotočimo na kolaborativno filtriranje. Na koncu izvedemo analizo in testiramo delovanje izbranega algoritma na množici uporabnikov, kjer preverimo, kako učinkovito algoritem priporoča knjige na podlagi sosednjih uporabnikov. Ključne besede: priporočilni sistem, spletna aplikacija, kolaborativno filtriranje, vsebinsko filtriranje Objavljeno v DKUM: 22.10.2024; Ogledov: 0; Prenosov: 82
Celotno besedilo (2,70 MB) |