Search the repository

A+ | A- | | SLO | ENG

Abstract: Organizations are increasingly confronted with regulatory requirements that encompass both personal data protection and cybersecurity. While the GDPR establishes a clear framework for processing personal data, the NIS 2 Directive introduces additional obligations aimed at strengthening cybersecurity resilience. Addressing these combined demands represents a complex legal, organizational, and technical challenge. One way forward is the development of integrated audit frameworks that support systematic compliance assessment across both domains. Building on prior work in which the original privacy by design (PbD) model was developed and empirically tested, this paper proposes an extended model that incorporates NIS 2 requirements. The extended framework aspires to provide a robust and comprehensive instrument for identifying compliance gaps and supporting organizations in adapting more effectively to an increasingly demanding regulatory landscape.
Keywords: privacy by design, conceptual model, cybersecurity, NIS 2
Published in ReVIS: 22.01.2026; Views: 254; Downloads: 2
Full text (12,52 MB)

Abstract: This paper presents the design and implementation of a digital feedback loop for optimizing material consumption in a manufacturing environment. The study focuses on small and medium-sized enterprises (SMEs) that often lack access to costly Manufacturing Execution Systems (MES). We demonstrate how commonly available tools such as Microsoft Excel, Power Query, and open-source solutions can be combined. We created a functional feedback mechanism linking ERP data, CNC machine outputs, and production logs. The proposed solution was developed and tested in a woodworking company producing custom furniture components. By integrating heterogeneous data sources, we established a real-time overview of material usage and waste, reducing manual work and increasing process transparency. The study highlights the role of simple Extract Transform Load (ETL) tools in supporting smart manufacturing, data-driven decision-making, and continuous process improvement.
Keywords: digital feedback loop, smart manufacturing, power query, ERP integration, data transformation, material optimization, ETL process
Published in ReVIS: 22.01.2026; Views: 314; Downloads: 11
Full text (12,52 MB)

Abstract: Customer retention is a major problem in the telecommunications industry. This study develops and evaluates models to identify possible churners. Machine learning techniques (“Decision Trees”, “Random Forests”, “Logistic Regression” and “Neural Networks (multilayer perceptron MLP)”) were applied through Python and R to analyze the “Telco Customer Churn” Kaggle dataset, based on customer assests and service usage. The data pre-processing compiled missing data and then standardized it. Evaluation used nested 10-fold cross-validation with an inner loop for hyperparameter tuning and mutual-information top-K feature pruning, with pre-processing confined to training folds. In Python, RF and LR achieve F1(~0.629), with Logistic Regression accuracy ~0.75. In R, Logistic Regression performed best (F1 ≈ 0.60 ± 0.03, Accuracy ≈ 0.80 ± 0.01). Metrics derived from pooled confusion matrices averaged over folds equal outer-fold means, confirming generalization across folds and between Python and R. Research offers empirical evidence for transferring and testing churn prediction models across Python and R in telecommunications analytics, with fully reproducible evaluation and results.
Keywords: customer churn, telecommunications, churn prediction, logistic regression, neural networks (MLP), Python, R, nested cross-validation
Published in ReVIS: 22.01.2026; Views: 321; Downloads: 2
Full text (12,52 MB)

Abstract: This study constitutes the second part of our investigation presented at ITIS 2023, which explores the search for objective physiological biomarkers for major depressive disorder (MDD). Moving beyond the established role of Heart Rate Variability (HRV), this preliminary research focuses on Pulse-Respiratory Coupling (PRC) – the coordination between cardiac and respiratory rhythms. We hypothesize that depression, characterized by autonomic nervous system (ANS) dysregulation, disrupts this coupling. A group of 73 subjects (healthy controls, untreated depressed patients, and patients treated with tricyclic antidepressants) were submitted to simultaneous electrocardiogram (EKG) and respiratory recording. Analysis revealed a distinct degradation of PRC in the depressed group, manifesting as a loss of synchronous patterns observed in healthy subjects. Machine learning models were trained on features derived from PRC timing. The k-Nearest Neighbors algorithm achieved a promising classification accuracy of 97.3% in distinguishing depressed from healthy individuals, outperforming other classifiers like Random Forest (95.9%) and Support Vector Machine (95.9%). While these results are preliminary and require validation in larger cohorts, they strongly suggest that PRC is a sensitive, non-invasive marker of ANS dysfunction in depression. This work underscores the potential of integrating multi-system physiological analysis with artificial intelligence to create objective aids for psychiatric diagnosis.
Keywords: major depressive disorder, physiological biomarkers, pulse-respiratory coupling, heart rate variability, autonomic nervous system, machine learning
Published in ReVIS: 22.01.2026; Views: 315; Downloads: 4
Full text (12,52 MB)

Abstract: Teoretična izhodišča: Strokovno znanje prvih posredovalcev je zelo pomembno pri reševanju nujnih stanj, zaradi katerih posamezniki pokličejo nujno medicinsko pomoč. Metodologija: Poleg osnovne deskriptivne statistike je bila uporabljena kvantitativna metoda raziskovanja z uporabo lastnega anketnega vprašalnika. Vzorec je vključeval 34 prvih posredovalcev v Občini Rogašovci. Za interpretacijo rezultatov smo uporabili tabelarični številčni in odstotkovni prikaz s pomočjo Microsoft Excela. Rezultati: Največ anketiranih (N = 34, f = 100 %) pozna ukrepe za sprostitev dihalne poti in pomen slišanega smrčanja in hropenja. Vedo, s kakšno frekvenco se izvaja stiske prsnega koša. Pozna pravilno razmerje med stiski prsnega koša in dajanjem vpihov pri odrasli osebi. Najmanj anketiranih je izbralo pravilne odgovore pri vprašanju ukrepanja ob osebi, pri kateri je prisotna popolna zapora dihalne poti s tujkom (N = 8, f = 24 %) ter ukrepu ob amputaciji uda, ki močno krvavi (N = 10, f = 29 %). Slabo je bilo tudi poznavanje ukrepanja za zaustavitev krvavitve (N = 11, f = 32 %) in znakov šoka (N = 11, f = 32 %). Odstotek splošnega poznavanja nudenja ukrepov prve pomoči v povprečju znaša 71 %. Prvi posredovalci so ocenili, da imajo v 74 % (N = 26) dovolj znanja za nudenje prve pomoči, ter da so za naloge prvega posredovalca dobro usposobljeni (N = 28, f = 82 %). Razprava: Prvi posredovalci potrebujejo za nudenje prve pomoči dodatno znanje, na podlagi katerega bodo lahko kakovostneje in za pacienta učinkoviteje opravljali svoje delo na terenu.
Keywords: reševalec, prvi posredovalec, prva pomoč, posredovalec, pacient
Published in ReVIS: 21.01.2026; Views: 385; Downloads: 18
Full text (2,21 MB)
This document has many files! More...