1. Weakly-supervised multilingual medical NER for symptom extraction for low-resource languagesRigon Sallauka, Umut Arioz, Matej Rojc, Izidor Mlakar, 2025, izvirni znanstveni članek Opis: Patient-reported health data, especially patient-reported outcomes measures, are vital for improving clinical care but are often limited by memory bias, cognitive load, and inflexible questionnaires. Patients prefer conversational symptom reporting, highlighting the need for robust methods in symptom extraction and conversational intelligence. This study presents a weakly-supervised pipeline for training and evaluating medical Named Entity Recognition (NER) models across eight languages, with a focus on low-resource settings. A merged English medical corpus, annotated using the Stanza i2b2 model, was translated into German, Greek, Spanish, Italian, Portuguese, Polish, and Slovenian, preserving the entity annotations medical problems, diagnostic tests, and treatments. Data augmentation addressed the class imbalance, and the fine-tuned BERT-based models outperformed baselines consistently. The English model achieved the highest F1 score (80.07%), followed by German (78.70%), Spanish (77.61%), Portuguese (77.21%), Slovenian (75.72%), Italian (75.60%), Polish (75.56%), and Greek (69.10%). Compared to the existing baselines, our models demonstrated notable performance gains, particularly in English, Spanish, and Italian. This research underscores the feasibility and effectiveness of weakly-supervised multilingual approaches for medical entity extraction, contributing to improved information access in clinical narratives—especially in under-resourced languages.
Ključne besede: low-resource languages, machine translation, medical entity extraction, NER, NLP, patient-reported outcomes, weakly-supervised learning
Objavljeno v DKUM: 19.05.2025; Ogledov: 0; Prenosov: 1
 Celotno besedilo (338,94 KB) |
2. Motivation for training at Paul Hartmann Adriatic d.o.o.Ivana Savić, 2025, diplomsko delo Opis: The motivation of adult learners in the workplace is an area of research that focuses on
understanding the factors that influence adults' desire to engage in learning activities
within an organizational context. We studied various internal and external factors that
contribute to the motivation of adult employees to acquire new knowledge, skills, and
competencies to accelerate their professional development and career advancement.
Understanding the motivations of adult learners at work is crucial for organizations that
want to design effective learning programs. With other factors, such as intrinsic and
extrinsic motivation, perceived relevance, and goal orientation, organizations can
develop strategies that promote and sustain employee motivation. This can ultimately
lead to improved engagement, performance, and professional growth among
employees.
Ključne besede: motivation, adult education, adult learning, motivational factors, lifelong
learning
Objavljeno v DKUM: 25.04.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (1,66 MB) |
3. Fostering fairness in image classification through awareness of sensitive dataIvona 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: 1
Celotno besedilo (2,01 MB) |
4. Procedure for the determination of the appropriate protective foil size to reduce step voltage using a FEM model and evolutionary methodsMarko Jesenik, Peter Kitak, Robert Maruša, Janez Ribič, 2025, izvirni znanstveni članek Opis: When a fault occurs in a power transmission system, voltages that are dangerous to people may occur. The aim of this work is to present the following method of protection: the use of protective foil installed at the appropriate depth around the transmission pole. Moreover, a procedure is presented for determining the optimal size of the protective film using a minimum number of finite element method calculations. In addition to the finite element method, evolutionary methods are used to determine the appropriate coefficients. Real earthing system data, earth data, and the fault current are obtained from the Slovenian system operator (ELES, d.o.o.) and used exclusively in the presented analyses. The results of determining the appropriate size of the protective foil for two transmission poles are presented, and the determination of the required breakthrough strength of the materials used is shown. The suitability of the proposed method is confirmed. This method is practical and useful when protection with protective foil is required, ensuring only as much as necessary is applied.
Ključne besede: transmission system, touch voltage, touch voltage, step voltage, grounding system, differential evolution, artificial bee colony, teaching–learning-based optimization
Objavljeno v DKUM: 23.04.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (29,51 MB) |
5. EEG-based finger movement classification with intrinsic time-scale decompositionMurside Degirmenci, Yilmaz Kemal Yuce, Matjaž Perc, Yalcin Isler, 2024, izvirni znanstveni članek Ključne besede: brain-computer interfaces, electroencephalogram, feature reduction, machine learning, finger movements classification, time series analysis
Objavljeno v DKUM: 16.04.2025; Ogledov: 0; Prenosov: 0
Celotno besedilo (1,44 MB)
Gradivo ima več datotek! Več... |
6. The learning curve of laparoscopic liver resection utilising a difficulty scoreArpad Ivanecz, Irena Plahuta, Matej Mencinger, Iztok Peruš, Tomislav Magdalenić, Špela Turk, Stojan Potrč, 2022, izvirni znanstveni članek Opis: Background: This study aimed to quantitatively evaluate the learning curve of laparoscopic liver resection (LLR) of a single surgeon.
Patients and methods: A retrospective review of a prospectively maintained database of liver resections was conducted. 171 patients undergoing pure LLRs between April 2008 and April 2021 were analysed. The Halls difficulty score (HDS) for theoretical predictions of intraoperative complications (IOC) during LLR was applied. IOC was defined as blood loss over 775 mL, unintentional damage to the surrounding structures, and conversion to an open approach. Theoretical association between HDS and the predicted probability of IOC was utilised to objectify the shape of the learning curve.
Results: The obtained learning curve has resulted from thirteen years of surgical effort of a single surgeon. It consists of an absolute and a relative part in the mathematical description of the additive function described by the logarithmic function (absolute complexity) and fifth-degree regression curve (relative complexity). The obtained learning curve determines the functional dependency of the learning outcome versus time and indicates several local extreme values (peaks and valleys) in the learning process until proficiency is achieved.
Conclusions: This learning curve indicates an ongoing learning process for LLR. The proposed mathematical model can be applied for any surgical procedure with an existing difficulty score and a known theoretically predicted association between the difficulty score and given outcome (for example, IOC).
Ključne besede: difficulty score, learning curve, laparoscopy, hepatectomy, intraoperative complications, surgical procedures
Objavljeno v DKUM: 07.04.2025; Ogledov: 0; Prenosov: 2
 Povezava na celotno besedilo
Gradivo ima več datotek! Več... |
7. Advancing sustainable mobility: artificial intelligence approaches for autonomous vehicle trajectories in roundaboutsSalvatore Leonardi, Natalia Distefano, Chiara Gruden, 2025, izvirni znanstveni članek Opis: This study develops and evaluates advanced predictive models for the trajectory planning of autonomous vehicles (AVs) in roundabouts, with the aim of significantly contributing to sustainable urban mobility. Starting from the “MRoundabout” speed model, several Artificial Intelligence (AI) and Machine Learning (ML) techniques, including Linear Regression (LR), Random Forest (RF), Support Vector Regression (SVR), Gradient Boosting Regression (GBR), and Neural Networks (NNs), were applied to accurately emulate human driving behavior and optimize AV trajectories. The results indicate that neural networks achieved the best predictive performance, with R2 values of up to 0.88 for speed prediction, 0.98 for acceleration, and 0.94 for differential distance, significantly outperforming traditional models. GBR and SVR provided moderate improvements over LR but encountered difficulties predicting acceleration and distance variables. AI-driven tools, such as ChatGPT-4, facilitated data pre-processing, model tuning, and interpretation, reducing computational time and enhancing workflow efficiency. A key contribution of this research lies in demonstrating the potential of AI-based trajectory planning to enhance AV navigation, fostering smoother, safer, and more sustainable mobility. The proposed approaches contribute to reduced energy consumption, lower emissions, and decreased traffic congestion, effectively addressing challenges related to urban sustainability. Future research will incorporate real traffic interactions to further refine the adaptability and robustness of the model.
Ključne besede: sustainable mobility, autonomous vehicles, machine learning, roundabouts, artificial intelligence, ChatGPT
Objavljeno v DKUM: 04.04.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (9,00 MB)
Gradivo ima več datotek! Več... |
8. Using a region-based convolutional neural network (R-CNN) for potato segmentation in a sorting processJaka Verk, Jernej Hernavs, Simon Klančnik, 2025, izvirni znanstveni članek Opis: This study focuses on the segmentation part in the development of a potato-sorting system that utilizes camera input for the segmentation and classification of potatoes. The key challenge addressed is the need for efficient segmentation to allow the sorter to handle a higher volume of potatoes simultaneously. To achieve this, the study employs a region-based convolutional neural network (R-CNN) approach for the segmentation task, while trying to achieve more precise segmentation than with classic CNN-based object detectors. Specifically, Mask R-CNN is implemented and evaluated based on its performance with different parameters in order to achieve the best segmentation results. The implementation and methodologies used are thoroughly detailed in this work. The findings reveal that Mask R-CNN models can be utilized in the production process of potato sorting and can improve the process.
Ključne besede: image segmentation, potato sorting, neural network, mask RCNN, object detection, production process, machine learning, AI
Objavljeno v DKUM: 27.03.2025; Ogledov: 0; Prenosov: 10
Celotno besedilo (5,97 MB)
Gradivo ima več datotek! Več... |
9. Cephalometric landmark detection in lateral skull X-ray images by using improved spatialconfiguration-netMartin 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
Celotno besedilo (2,46 MB)
Gradivo ima več datotek! Več... |
10. |
