1. Development of family of artificial neural networks for the prediction of cutting tool conditionObrad Spaić, Zdravko Krivokapić, Davorin Kramar, 2020, izvirni znanstveni članek Opis: Recently, besides regression analysis, artificial neural networks (ANNs) are increasingly used to predict the state of tools. Nevertheless, simulations trained by cutting modes, material type and the method of sharpening twist drills (TD) and the drilling length from sharp to blunt as input parameters and axial drilling force and torque as output ANN parameters did not achieve the expected results. Therefore, in this paper a family of artificial neural networks (FANN) was developed to predict the axial force and drilling torque as a function of a number of influencing factors. The formation of the FANN took place in three phases, in each phase the neural networks formed were trained by drilling lengths until the drill bit was worn out and by a variable parameter, while the combinations of the other influencing parameters were taken as constant values. The results of the prediction obtained by applying the FANN were compared with the results obtained by regression analysis at the points of experimental results. The comparison confirmed that the FANN can be used as a very reliable method for predicting tool condition.
Ključne besede: drilling, cutting tool, twist drill bits, axial force, tool wear, prediction, artificial neural networks, back propagation
Objavljeno v DKUM: 15.01.2026; Ogledov: 0; Prenosov: 1
 Celotno besedilo (1,26 MB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo! |
2. Neuro-mechanistic model for cutting force prediction in helical end milling of metal materials layered in multiple directionsUroš Župerl, Franc Čuš, Anna Zawada-Tomkiewicz, Krzysztof Stępień, 2020, izvirni znanstveni članek Ključne besede: helical end milling, multidirectional layered metal material, cutting forces, specific cutting forces, neuro-mechanistic model, modelling, prediction, artificial neural networks
Objavljeno v DKUM: 13.01.2026; Ogledov: 0; Prenosov: 1
Celotno besedilo (764,53 KB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo! |
3. A multi-task deep learning approach for landslide displacement prediction with applications in early warning systemsDamjan Strnad, Domen Mongus, Štefan Horvat, Ela Šegina, 2025, izvirni znanstveni članek Opis: Accurate landslide displacement prediction is important for the construction of reliable landslide early warning systems (LEWS). Recently, deep neural networks have become the dominant approach for landslide displacement modeling. However, we show that focusing solely on low prediction residuals is not perfectly aligned with the goals of LEWS, where the emphasis is on precise forecasts near the warning threshold. This can result in poor efficiency of threshold-based warning prediction. We propose a multi-task approach to model training, where auxiliary targets are used to optimize the model towards the performance relevant for LEWS. The methodology is validated using the data from the deep-seated Urbas landslide in north-western Slovenia, which has been monitored by GNSS since 2019. Developing a displacement prediction model for Urbas is a step towards extending the existing wire-based mechanical alarm system. We employ a convolutional neural network for day-ahead displacement prediction using recent landslide activity, hydrometeorological measurements and seismological data. The proposed multi-task model retains a competitive score for warning prediction while achieving a significantly lower mean absolute error compared to the reference models. The proposed methodology is generally applicable and has the potential to improve the efficiency of landslide modeling in the context of LEWS.
Ključne besede: landslide displacement prediction, neural network, multitask learning, landslide early warning system, remote sensing, GNSS
Objavljeno v DKUM: 12.12.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (2,63 MB) |
4. A machine vision approach to assessing steel properties through spark imagingGoran Munđar, Miha Kovačič, Uroš Župerl, 2025, izvirni znanstveni članek Opis: Accurate and efficient evaluation of steel properties is crucial for modern manufacturing. This study presents a novel approach that combines spark imaging and deep learning to predict carbon content in steel. By capturing and analyzing sparks generated during grinding, the method offers a fast and cost-effective alternative to conventional testing. Using convolutional neural networks (CNNs), the proposed models demonstrate high reliability and adaptability across different steel types. Among the tested architectures, MobileNet-v2 achieved the best performance, balancing accuracy and computational efficiency. The findings highlight the potential of machine vision and artificial intelligence in non-destructive steel analysis, providing rapid and precise insights for industrial applications.
Ključne besede: carbon content prediction, convolutional neural networks, deep learning, machine vision, spark imaging, steel analysis
Objavljeno v DKUM: 03.11.2025; Ogledov: 0; Prenosov: 6
Celotno besedilo (1,84 MB)
Gradivo ima več datotek! Več... |
5. Can corporate social responsibility contribute to bankruptcy prediction? : evidence from CroatiaAdriana Galant, Robert Zenzerović, 2023, izvirni znanstveni članek Opis: Background/Purpose: Companies are becoming aware of the fact that corporate social responsibility (CSR) is becoming the imperative of their sustainable business model despite the potential costs it could generate. Researchers are mostly focused on estimating the relationship between CSR and financial performance where most of the findings indicate their positive relationship. This paper expands existing research and focuses on the relationship between CSR and the risk of bankruptcy using the data from 102 midsize and large companies from non-financial sectors using the data for four years. Research expands existing studies on the EU level according to the fact that most of the existing studies are performed among US companies. Method: Descriptive statistics and SEM-PLS methodology was used to compare and analyze financial data with data collected from 7 groups of stakeholders. Results: Research results indicate that the relation between CSR and the risk of bankruptcy is negative. Conclusion: Becoming a socially responsible company is in the best interest of all stakeholders because CSR activities contribute to financial stability and maintenance of going concern assumption.
Ključne besede: corporate social responsibility, bankruptcy prediction, Altman Z’ score, SEM-PLS methodology
Objavljeno v DKUM: 26.09.2025; Ogledov: 0; Prenosov: 3
Celotno besedilo (713,38 KB)
Gradivo ima več datotek! Več... |
6. Micro-location temperature prediction leveraging deep learning approachesAmadej Krepek, Iztok Fister, Iztok Fister, 2025, izvirni znanstveni članek Opis: Nowadays, technological progress has promoted the integration of artificial intelligence into modern human lives rapidly. On the other hand, extreme weather events in recent years have started to influence human well-being. As a result, these events have been addressed by artificial intelligence methods more and more frequently. In line with this, the paper focuses on searching for predicting the air temperature in a particular Slovenian micro-location by using a weather prediction model Maximus based on a longshort term memory neural network learned by the long-term, lower-resolution dataset CERRA. During this huge experimental study, the Maximus prediction model was tested with the ICON-D2 general-purpose weather prediction model and validated with real data from the mobile weather station positioned at a specific micro-location. The weather station employs Internet of Things sensors for measuring temperature, humidity, wind speed and direction, and rain, while it is powered by solar cells. The results of comparing the Maximus proposed prediction model for predicting the air temperature in micro-locations with the general-purpose weather prediction model ICON-D2 has encouraged the authors to continue searching for an air temperature prediction model at the micro-location in the future.
Ključne besede: long short-term memory neural networks, air temperature, micro-location, prediction, weather, Internet of Things
Objavljeno v DKUM: 25.09.2025; Ogledov: 0; Prenosov: 10
Celotno besedilo (8,81 MB) |
7. Hardened workpiece shape prediction using acoustic responses and deep neural networkJernej Hernavs, Tadej Peršak, Miran Brezočnik, Simon Klančnik, 2025, izvirni znanstveni članek Opis: This study proposes a novel approach to predict the shape of hardened metal workpieces using acoustic responses processed by a deep convolutional neural network (CNN), aiming to advance automated straightening in manufacturing. Tool steel 1.2379 workpieces of varying widths (24 mm, 90 mm, 200 mm) were struck using a custom-built device, with acoustic responses captured and transformed into scalograms via Continuous Wavelet Transform (CWT). A 40-layer CNN predicted 5×9 shape matrices, validated by 3D scans. The dataset (219 shape states, 3396 recordings) was evaluated using leaveone-workpiece-out cross-validation, comparing the CNN against baseline models (linear regression, random forest, shallow CNN, XGBoost). CNN achieved competitive accuracy, demonstrating the feasibility of acoustic-based shape prediction. As a non-invasive, cost-efective complement to 3D scanning, this method ofers innovative potential for multi-modal quality control systems in manufacturing.
Ključne besede: metal workpiece, hardened, deep neural network, acoustic respons, shape prediction
Objavljeno v DKUM: 14.08.2025; Ogledov: 0; Prenosov: 9
Celotno besedilo (1,10 MB)
Gradivo ima več datotek! Več... |
8. Application of the Altman model for the prediction of financial distress in the case of Slovenian companiesTatjana Dolinšek, Tatjana Kovač, 2024, izvirni znanstveni članek Opis: Background/Purpose: The aim of this paper is to verify the applicability and accuracy of the Altman model in the case of Slovenian companies. The use of the Altman model is hugely popular and widespread among financiers, analysts and other stakeholders who want to determine the creditworthiness of a company’s operations and the likelihood of it running into financial difficulties in the coming years. Methods: The study was conducted on a sample of 66 Slovenian companies, which were divided into two equal groups: bankruptcy and non-bankruptcy companies. Based on accounting data for the last five years, the authors of this paper calculated the Z-Score, which is based on the Multiple Discriminant Analysis (MDA). By calculating the statistical error of the estimate (type I and II), the authors verified the extent (in percentage terms) to which the companies had been correctly classified by the model. The Mann-Whitney U test was used to check whether there was a difference in the average Z-Score between the two groups of companies. Results: The authors determined that the reliability of the Altman model was 71.21% when tested at the upper bound (the threshold value of the Z-Score was 2.6) and 80.30% when tested at the lower bound (the threshold value of the Z-Score was 1.1). This is similar to other countries, where the reliability was found to be over 70% in most cases. Despite the lower reliability of the model, the Z-Score proved to be an important factor in differentiating between the two groups of companies, as bankruptcy companies had a lower value of this indicator than non-bankruptcy companies. Conclusion: Based on the results of this study, as well as those of other studies, it can be summarized that the Altman model is a fairly good way for companies to determine the success of their business in a relatively simple and quick way and also to predict the potential risk of their operations in the future. However, since the reliability of the model is not 100%, it is important to be careful when making business predictions and carry out additional in-depth analyses or use other methods.
Ključne besede: Altman model, business success, bankruptcy prediction, Slovenian companies
Objavljeno v DKUM: 12.08.2025; Ogledov: 0; Prenosov: 1
Celotno besedilo (812,92 KB)
Gradivo ima več datotek! Več... |
9. Metacognitive skills of pupils in primary mathematics educationEva Nováková, 2024, izvirni znanstveni članek Opis: In educational theory and research, metacognition is increasingly seen as an important predictor of successful learning – it is the key to learning and academic achievement. The study investigates "off-line" metacognition (i.e. the level of prediction and the level of self-evaluation) in relation to the solving of mathematical problems by primary school pupils. The research was carried out on a group of 311 pupils of 16 classes of primary schools. We used the test consisting of five tasks, which also included questions aimed at finding out the level of pupils' prediction and their level of self-evaluation. We processed the obtained data with the intentions of a quantitative methodological approach. It follows from the research findings that students who were successful in solving the tasks achieved a higher level of prediction and self-assessment than students who were not successful.
Ključne besede: metacognition, prediction, self-evaluation, solving of problems
Objavljeno v DKUM: 29.07.2025; Ogledov: 0; Prenosov: 5
Celotno besedilo (491,50 KB)
Gradivo ima več datotek! Več... |
10. Coastal flood risk assessment : an approach to accurately map flooding through national registry-reported eventsErik Kralj, Peter Kumer, Cécil J. W. Meulenberg, 2023, izvirni znanstveni članek Opis: The escalating frequency and severity of climate-related hazards in the Mediterranean, particularly in the historic town of Piran, Slovenia, underscore the critical need for enhanced coastal flood prediction and efficient early warning systems. This study delves into the impediments of available coastal flood hazard maps and the existing early warning system, which rely on distant sensors, neglecting the town’s unique microclimate. The current study leverages the public registry maintained by the Administration of the Republic of Slovenia for Civil Protection and Disaster Relief (URSZR), an underutilized resource for generating comprehensive and accurate flooding maps for Piran. Here, we show that in the historic town of Piran, floodings reported through the national registry can be used to map coastal flooding by means of verification and validation of the georeferenced reports therein, with subsequent correlation analysis (hotspot, cluster, and elevation polygons) that show temporal and spatial patterns. The innovative approach adopted in this study aims to bolster the accuracy and reliability of flooding data, offering a more nuanced understanding of flood patterns (in Piran, but generally applicable where national or regional registries are available). The findings of this research illuminate the pressing need for localized field-report and sensor systems to enhance the precision of flood predictions. The study underscores the pivotal role of accurate, localized data in fortifying coastal towns against the escalating impacts of climate change, safeguarding both the inhabitants and the invaluable architectural heritage of historic areas.
Ključne besede: sea flood prediction, flooding maps, climate change resilience, natural disaster registry, coastal inundation, flood-prone areas
Objavljeno v DKUM: 07.04.2025; Ogledov: 0; Prenosov: 12
Celotno besedilo (7,60 MB)
Gradivo ima več datotek! Več... |
