| | 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 / 35
Na začetekNa prejšnjo stran1234Na naslednjo stranNa konec
1.
Fostering fairness in image classification through awareness of sensitive data
Ivona Colakovic, Sašo Karakatič, 2025, izvirni znanstveni članek

Opis: Machine learning (ML) has demonstrated remarkable ability to uncover hidden patterns in data. However, the presence of biases and discrimination originating from the data itself and, consequently, emerging in the ML outcomes, remains a pressing concern. With the exponential growth of unstructured data, such as images, fairness has become increasingly critical, as neural network (NN) models may inadvertently learn and perpetuate societal and historical biases. To address this challenge, we propose a fairness-aware loss function that iteratively prioritizes the worst-performing sensitive group during NN training. This approach aims to balance treatment quality across sensitive groups, achieving fairer image classification outcomes while incurring only a slight compromise in overall performance. Our method, evaluated on the FairFace dataset, demonstrates significant improvements in fairness metrics while maintaining comparable overall quality. These trade-offs highlight that the minor decrease in overall quality is justified by the improvement in fairness of the models.
Ključne besede: fairness, search-basimage classification, machine learning, supervised learnign, neural networks
Objavljeno v DKUM: 23.04.2025; Ogledov: 0; Prenosov: 2
.pdf Celotno besedilo (2,01 MB)

2.
Cephalometric landmark detection in lateral skull X-ray images by using improved spatialconfiguration-net
Martin Šavc, Gašper Sedej, Božidar Potočnik, 2022, izvirni znanstveni članek

Opis: Accurate automated localization of cephalometric landmarks in skull X-ray images is the basis for planning orthodontic treatments, predicting skull growth, or diagnosing face discrepancies. Such diagnoses require as many landmarks as possible to be detected on cephalograms. Today’s best methods are adapted to detect just 19 landmarks accurately in images varying not too much. This paper describes the development of the SCN-EXT convolutional neural network (CNN), which is designed to localize 72 landmarks in strongly varying images. The proposed method is based on the SpatialConfiguration-Net network, which is upgraded by adding replications of the simpler local appearance and spatial configuration components. The CNN capacity can be increased without increasing the number of free parameters simultaneously by such modification of an architecture. The successfulness of our approach was confirmed experimentally on two datasets. The SCN-EXT method was, with respect to its effectiveness, around 4% behind the state-of-the-art on the small ISBI database with 250 testing images and 19 cephalometric landmarks. On the other hand, our method surpassed the state-of-the-art on the demanding AUDAX database with 4695 highly variable testing images and 72 landmarks statistically significantly by around 3%. Increasing the CNN capacity as proposed is especially important for a small learning set and limited computer resources. Our algorithm is already utilized in orthodontic clinical practice.
Ključne besede: detection of cephalometric landmarks, skull X-ray images, convolutional neural networks, deep learning, SpatialConfiguration-Net architecture, AUDAX database
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 6
.pdf Celotno besedilo (2,46 MB)
Gradivo ima več datotek! Več...

3.
Deeply-supervised 3D convolutional neural networks for automated ovary and follicle detection from ultrasound volumes
Božidar Potočnik, Martin Šavc, 2022, izvirni znanstveni članek

Opis: Automated detection of ovarian follicles in ultrasound images is much appreciated when its effectiveness is comparable with the experts’ annotations. Today’s best methods estimate follicles notably worse than the experts. This paper describes the development of two-stage deeply-supervised 3D Convolutional Neural Networks (CNN) based on the established U-Net. Either the entire U-Net or specific parts of the U-Net decoder were replicated in order to integrate the prior knowledge into the detection. Methods were trained end-to-end by follicle detection, while transfer learning was employed for ovary detection. The USOVA3D database of annotated ultrasound volumes, with its verification protocol, was used to verify the effectiveness. In follicle detection, the proposed methods estimate follicles up to 2.9% more accurately than the compared methods. With our two-stage CNNs trained by transfer learning, the effectiveness of ovary detection surpasses the up-to-date automated detection methods by about 7.6%. The obtained results demonstrated that our methods estimate follicles only slightly worse than the experts, while the ovaries are detected almost as accurately as by the experts. Statistical analysis of 50 repetitions of CNN model training proved that the training is stable, and that the effectiveness improvements are not only due to random initialisation. Our deeply-supervised 3D CNNs can be adapted easily to other problem domains.
Ključne besede: 3D deep neural networks, 3D ultrasound images of ovaries, deep supervision, detection of follicles and ovaries, U-Net based architecture
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 6
.pdf Celotno besedilo (1,28 MB)
Gradivo ima več datotek! Več...

4.
Contour maps for simultaneous increase in yield strength and elongation of hot extruded aluminum alloy 6082
Iztok Peruš, Goran Kugler, Simon Malej, Milan Terčelj, 2022, izvirni znanstveni članek

Opis: In this paper, the Conditional Average Estimator artificial neural network (CAE ANN) was used to analyze the influence of chemical composition in conjunction with selected process parameters on the yield strength and elongation of an extruded 6082 aluminum alloy (AA6082) profile. Analysis focused on the optimization of mechanical properties as a function of casting temperature, casting speed, addition rate of alloy wire, ram speed, extrusion ratio, and number of extrusion strands on one side, and different contents of chemical elements, i.e., Si, Mn, Mg, and Fe, on the other side. The obtained results revealed very complex non-linear relationships between all of these parameters. Using the proposed approach, it was possible to identify the combinations of chemical composition and process parameters as well as their values for a simultaneous increase of yield strength and elongation of extruded profiles. These results are a contribution of the presented study in comparison with published research results of similar studies in this field. Application of the proposed approach, either in the research and/or in industrial aluminum production, suggests a further increase in the relevant mechanical properties.
Ključne besede: AA6082, hot extrusion, mechanical properties, yield strength, elongation, artificial neural networks, analysis
Objavljeno v DKUM: 12.03.2025; Ogledov: 0; Prenosov: 8
.pdf Celotno besedilo (4,40 MB)
Gradivo ima več datotek! Več...

5.
CAE artificial neural network applied to the design of incrementally launched prestressed concrete bridges
Tomaž Goričan, Milan Kuhta, Iztok Peruš, 2025, izvirni znanstveni članek

Opis: Bridges are typically designed by reputable, specialized engineering and design companies with years of experience. In these firms, experienced engineers share and pass on their knowledge to younger colleagues. However, when these experts retire, some of the knowledge is lost forever. As a subset of artificial intelligence methods, artificial neural networks (ANNs) can solve the problem of acquiring, transferring, and preserving specialized expert knowledge. This article describes the possible application of CAE ANN to acquire knowledge and to assist in the design of incrementally launched prestressed concrete bridges. Therefore, multidimensional graphs in the form of iso-curves of equal values were created, allowing practicing engineers to understand complex relationships between design parameters. The graphs also contain information about the reliability of the results, which is defined by an estimated parameter. The general rule is that results based on a larger number of actual data points are more reliable. Finally, an ANN BD assistant is proposed as an application that assists engineers and designers in the early stages of design and/or established engineers and designers in variant studies and design parameter optimization.
Ključne besede: artificial neural networks, bridge design, incremental launching method, expert knowledge, reliability of predictions, prestressed concrete bridges
Objavljeno v DKUM: 10.03.2025; Ogledov: 0; Prenosov: 12
.pdf Celotno besedilo (5,54 MB)
Gradivo ima več datotek! Več...

6.
New approach for automated explanation of material phenomena (AA6082) using artificial neural networks and ChatGPT
Tomaž Goričan, Milan Terčelj, Iztok Peruš, 2024, izvirni znanstveni članek

Opis: Artificial intelligence methods, especially artificial neural networks (ANNs), have increasingly been utilized for the mathematical description of physical phenomena in (metallic) material processing. Traditional methods often fall short in explaining the complex, real-world data observed in production. While ANN models, typically functioning as “black boxes”, improve production efficiency, a deeper understanding of the phenomena, akin to that provided by explicit mathematical formulas, could enhance this efficiency further. This article proposes a general framework that leverages ANNs (i.e., Conditional Average Estimator—CAE) to explain predicted results alongside their graphical presentation, marking a significant improvement over previous approaches and those relying on expert assessments. Unlike existing Explainable AI (XAI) methods, the proposed framework mimics the standard scientific methodology, utilizing minimal parameters for the mathematical representation of physical phenomena and their derivatives. Additionally, it analyzes the reliability and accuracy of the predictions using well-known statistical metrics, transitioning from deterministic to probabilistic descriptions for better handling of real-world phenomena. The proposed approach addresses both aleatory and epistemic uncertainties inherent in the data. The concept is demonstrated through the hot extrusion of aluminum alloy 6082, where CAE ANN models and predicts key parameters, and ChatGPT explains the results, enabling researchers and/or engineers to better understand the phenomena and outcomes obtained by ANNs.
Ključne besede: artificial neural networks, automatic explanation, hot extrusion, aluminum alloy, large language models, ChatGPT
Objavljeno v DKUM: 27.02.2025; Ogledov: 0; Prenosov: 6
.pdf Celotno besedilo (3,18 MB)
Gradivo ima več datotek! Več...

7.
8.
Topological features of spike trains in recurrent spiking neural networks that are trained to generate spatiotemporal patterns
Oleg Maslennikov, Matjaž Perc, Vladimir Nekorkin, 2024, izvirni znanstveni članek

Opis: In this study, we focus on training recurrent spiking neural networks to generate spatiotemporal patterns in the form of closed two-dimensional trajectories. Spike trains in the trained networks are examined in terms of their dissimilarity using the Victor-Purpura distance. We apply algebraic topology methods to the matrices obtained by rank-ordering the entries of the distance matrices, specifically calculating the persistence barcodes and Betti curves. By comparing the features of dierent types of output patterns, we uncover the complex relations between low-dimensional target signals and the underlying multidimensional spike trains.
Ključne besede: topological features, neural networks, spatiotemporal patterns, nonlinear dynamics
Objavljeno v DKUM: 27.11.2024; Ogledov: 0; Prenosov: 2
.pdf Celotno besedilo (6,96 MB)
Gradivo ima več datotek! Več...

9.
Rapid assessment of steel machinability through spark analysis and data-mining techniques
Goran Munđar, Miha Kovačič, Miran Brezočnik, Krzysztof Stępień, Uroš Župerl, 2024, izvirni znanstveni članek

Opis: The machinability of steel is a crucial factor in manufacturing, influencing tool life, cutting forces, surface finish, and production costs. Traditional machinability assessments are labor-intensive and costly. This study presents a novel methodology to rapidly determine steel machinability using spark testing and convolutional neural networks (CNNs). We evaluated 45 steel samples, including various low-alloy and high-alloy steels, with most samples being calcium steels known for their superior machinability. Grinding experiments were conducted using a CNC machine with a ceramic grinding wheel under controlled conditions to ensure a constant cutting force. Spark images captured during grinding were analyzed using CNN models with the ResNet18 architecture to predict V15 values, which were measured using the standard ISO 3685 test. Our results demonstrate that the created prediction models achieved a mean absolute percentage error (MAPE) of 12.88%. While some samples exhibited high MAPE values, the method overall provided accurate machinability predictions. Compared to the standard ISO test, which takes several hours to complete, our method is significantly faster, taking only a few minutes. This study highlights the potential for a cost-effective and time-efficient alternative testing method, thereby supporting improved manufacturing processes.
Ključne besede: steel machinability, spark testing, data mining, machine vision, convolutional neural networks
Objavljeno v DKUM: 12.09.2024; Ogledov: 15; Prenosov: 22
.pdf Celotno besedilo (5,24 MB)
Gradivo ima več datotek! Več...

10.
Iskanje izvedeno v 0.1 sek.
Na vrh
Logotipi partnerjev Univerza v Mariboru Univerza v Ljubljani Univerza na Primorskem Univerza v Novi Gorici