1. Varstvo podatkov in pravice potrošnikov v digitalnem marketinguMirjana Založnik, 2025, master's thesis Abstract: Magistrska naloga raziskuje varstvo osebnih podatkov in pravice potrošnikov v kontekstu digitalnega trženja, področja, kjer hitra rast spletnih storitev in obdelava osebnih podatkov postavljata zasebnost v ospredje razprav. V teoretičnem delu smo analizirali ključne evropske zakonodajne akte – Splošno uredbo o varstvu podatkov (GDPR), Zakon o digitalnih storitvah (DSA), Zakon o digitalnih trgih (DMA), Zakon o upravljanju podatkov (DGA) in Zakon o podatkih (Data Act), ki skupaj predstavljajo temelje za pregledno, odgovorno in pošteno obravnavo osebnih podatkov v digitalnem okolju.
Empirični del temelji na anketi med 108 potrošniki in se osredotoča na njihovo ozaveščenost o pravicah, izkušnje s kršitvami ter odnos do obdelave osebnih podatkov. Rezultati kažejo, da potrošniki poznajo predvsem osnovne vidike GDPR, medtem ko novejši akti in celoten nabor pravic ostajajo večini neznani. Zakonodajo pogosto zaznavajo kot zapleteno, kar zmanjšuje njihovo pripravljenost na ukrepanje ob kršitvah. Večina se ob zaznanih nepravilnostih ne odloči za formalno pravno varstvo, saj jim primanjkuje jasnih informacij, zaupanja v učinkovitost sistema ali občutijo, da situacija ni dovolj resna.
Kljub temu raziskava potrjuje, da zasebnost ni zgolj formalno zapisana v zakonodaji, temveč jo potrošniki razumejo kot ključen element zaupanja v digitalno okolje. Pogosto se odločijo, da določenih storitev ne bodo uporabljali, kadar menijo, da podjetja preveč posegajo v njihove osebne podatke. To nakazuje, da so potrošniki zasebnost pripravljeni braniti tudi z lastnimi odločitvami, čeprav redko ukrepajo po formalnih pravnih poteh.
Naloga tako pokaže, da je evropski zakonodajni okvir sicer obsežen in napreden, a njegova učinkovitost v praksi ostaja omejena zaradi nizke ravni ozaveščenosti, nepreglednosti pravil in pomanjkanja enostavnih mehanizmov za uveljavljanje pravic. Potrošniki ob tem jasno izražajo pričakovanja po večji preglednosti, strožjem izvrševanju zakonodaje ter širšem ozaveščanju in izobraževanju. Magistrsko delo zato poudarja potrebo po celovitem pristopu, ki združuje pravne, regulatorne in izobraževalne ukrepe ter zagotavlja ravnovesje med razvojem digitalnega marketinga in zaščito temeljnih pravic posameznika.
Keywords: digitalni marketing, pravice, podatki, GDPR, DSA, DMA, DGA, Data Act.
Published in DKUM: 04.11.2025; Views: 0; Downloads: 8
 Full text (1,24 MB) |
2. Automated speech analysis in depressive disorder: enhancing diagnosis and monitoringAljaž Neuberg, 2025, master's thesis Abstract: This paper investigates the automatic recognition of depression by integrating acoustic, linguistic and emotional features extracted from clinical interviews in the DAIC-WOZ dataset. A total of six classical machine learning classifiers such as Decision Tree, Random Forest, SVM, Gradient Boosting, AdaBoost and XGBoost were systematically evaluated under different class balancing methods (such as SMOTE, SMOTETomek and Random Undersampling) and feature selection strategies. The best model, a decision tree classifier with SMOTE-based balancing and a feature selection technique, achieved a weighted F1 score and accuracy of 0.78 with only eight selected features. These features included all three modalities, demonstrating the
added benefit of a multimodal approach. The results suggest that even relatively simple models, when supported by careful preprocessing and dimensionality reduction, can provide accurate and interpretable predictions. This work emphasizes the importance of feature engineering and balancing techniques in clinical machine learning tasks and lays the foundation for future research on scalable and explainable depression detection systems.
Keywords: Depression, Classification, Machine Learning, Data Balancing, Feature Selection
Published in DKUM: 03.11.2025; Views: 0; Downloads: 1
Full text (4,28 MB) |
3. What can artificial intelligence do for soil health in agriculture?Stefan Schweng, Luca Bernardini, Katharina Keiblinger, Peter Kaul, Iztok Fister, Niko Lukač, Javier Del Ser, Andreas Holzinger, 2025, review article Abstract: The integration of artificial intelligence (AI) into soil research presents significant opportunities to advance the understanding, management, and conservation of soil ecosystems. This paper reviews the diverse applications of AI in soil health assessment, predictive modeling of soil properties, and the development of pedotransfer functions within the context of agriculture, emphasizing AI’s advantages over traditional analytical methods. We identify soil organic matter decline, compaction, and biodiversity loss as the most frequently addressed forms of soil degradation. Strong trends include the creation of digital soil maps, particularly for soil organic carbon and chemical properties using remote sensing or easily measurable proxies, as well as the development of decision support systems for crop rotation planning and IoT-based monitoring of soil health and crop performance. While random forest models dominate, support vector machines and neural networks are also widely applied for soil parameter modeling. Our analysis of datasets reveals clear regional biases, with tropical, arid, mild continental, and polar tundra climates remaining underrepresented despite their agricultural relevance. We also highlight gaps in predictor–response combinations for soil property modeling, pointing to promising research avenues such as estimating heavy metal content from soil mineral nitrogen content, microbial biomass, or earthworm abundance. Finally, we provide practical guidelines on data preparation, feature extraction, and model selection. Overall, this study synthesizes recent advances, identifies methodological limitations, and outlines a roadmap for future research, underscoring AI’s transformative potential in soil science.
Keywords: artificial intelligence, machine learning, agriculture, soil health, soil parameter modeling, regional data bias
Published in DKUM: 17.10.2025; Views: 0; Downloads: 3
Full text (4,22 MB) |
4. Using data mining to improve decision-making : case study of a recommendation system developmentHyrmet Mydyti, Arbana Kadriu, Mirjana Pejić Bach, 2023, original scientific article Abstract: Background and purpose: This study aims to provide a practical perspective on how data mining techniques are used in the home appliance after-sales services. Study investigates on how can a recommendation system help a customer service company that plans to use data mining to improve decision making during its digital transformation process. In addition, study provides a detailed outline on the process for developing and analyzing platforms to improve data analytics for such companies. Methodology: Case study approach is used for evaluating the usability of recommendation systems based on data mining approach in the context of home appliance after-sales services. We selected the latest platforms based on their relevance to the recommender system and their applicability to the functionality of the data mining system as trends in the system design. Results: Evaluation of the impact on decision making shows how the application of data mining techniques in organizations can increase efficiency. Evaluation of the time taken to resolve the complaint, as a key attribute of service quality that affects customer satisfaction, and the positive results achieved by the recommendation system are presented. Conclusion: This paper increases the understanding of the benefits of the data mining approach in the context of recommender systems. The benefits of data mining, an important component of advanced analytics, lead to an increase in business productivity through predictive analytics. For future research, other attributes or factors useful for the recommender systems can be considered to improve the quality of the results. Acknowledgement: The author Hyrmet Mydyti’s PhD thesis has been extended in this paper.
Keywords: digital transformation, data mining, decision tree algorithm, decision-making, home appliances after-sales services
Published in DKUM: 08.10.2025; Views: 0; Downloads: 2
Full text (1,95 MB)
This document has many files! More... |
5. Protection of workers in relation to the use of artificial intelligence in the workplaceAsja Lešnik, 2025, original scientific article Abstract: This article examines the impact of artificial intelligence (AI) on all stages of the employment relationship and analyses whether the current legal framework adequately protects workers from the risks posed by the use of AI in the workplace. The focus is on Slovenian labour law, while also considering relevant international and EU legal sources such as the AI Act, the Directive on Improving Working Conditions in Platform Work, the GDPR, and the EU Charter of Fundamental Rights. The author addresses legal challenges including discrimination, data protection, privacy, occupational safety and health, and liability for damages. The article finds that while some protective mechanisms already exist, none of the analysed legal sources comprehensively regulate AI use in employment relationships. To ensure effective worker protection, the author argues for either the amendment of current laws or the adoption of dedicated legislation. Since AI will play an even more significant role in Labour Law in the future, it is crucial for the law to adapt in a timely manner to the new challenges posed by AI.
Keywords: artificial intelligence, algorithmic management, automation of work processes, discrimination, data protection, privacy protection, occupational safety and health, liability, worker protection, legal framework
Published in DKUM: 02.10.2025; Views: 0; Downloads: 5
Full text (1,02 MB)
This document has many files! More...
This document is also a collection of 1 document! |
6. The role of intelligent data analysis in selected endurance sports : a systematic literature reviewAlen Rajšp, Patrik Rek, Peter Kokol, Iztok Fister, 2025, review article Abstract: In endurance sports, athletes and coaches shift increasingly from intuition-based decisionmaking to data-driven approaches powered by modern technology and analytics. Since 2018, the field has experienced significant advances, influencing endurance sports disciplines. This systematic literature review identified 75 peer-reviewed studies on intelligent data analysis in endurance sports training. Each study was categorized by its intelligent method (e.g., machine learning, deep learning, computational intelligence), the types of sensors and wearables used, and the specific training application and approach. Our synthesis reveals that machine learning and deep learning are among the most used approaches, with running and cycling identified as the most extensively studied sports. Physiological and environmental data, such as heart rate, biomechanical signals, and GPS, are often used to aid in generating personalized training plans, predicting injuries, and increasing athletes’ long-term performance. Despite these advancements, challenges remain, related to data quality and the small participant sample sizes.
Keywords: smart sports training, endurance sports, intelligent data analysis, machine learning, artificial intelligence, computational intelligence, systematic literature review
Published in DKUM: 02.10.2025; Views: 0; Downloads: 6
Full text (655,98 KB) |
7. A novel framework for unification of association rule miningRahul Sharma, Minakshi Kaushik, Sijo Arakkal Peious, Alexandre Bazin, Syed Attique Shah, Iztok Fister, Sadok Ben Yahia, Dirk Draheim, 2022, original scientific article Abstract: Statistical reasoning was one of the earliest methods to draw insights from data. However, over the last three decades, association rule mining and online analytical processing have gained massive ground in practice and theory. Logically, both association rule mining and online analytical processing have some common objectives, but they have been introduced with their own set of mathematical formalizations and have developed their specific terminologies. Therefore, it is difficult to reuse results from one domain in another. Furthermore, it is not easy to unlock the potential of statistical results in their application scenarios. The target of this paper is to bridge the artificial gaps between association rule mining, online analytical processing and statistical reasoning. We first provide an elaboration of the semantic correspondences between their foundations, i.e., itemset apparatus, relational algebra and probability theory. Subsequently, we propose a novel framework for the unification of association rule mining, online analytical processing and statistical reasoning. Additionally, an instance of the proposed framework is developed by implementing a sample decision support tool. The tool is compared with a state-of-the-art decision support tool and evaluated by a series of experiments using two real data sets and one synthetic data set. The results of the tool validate the framework for the unified usage of association rule mining, online analytical processing, and statistical reasoning. The tool clarifies in how far the operations of association rule mining and online analytical processing can complement each other in understanding data, data visualization and decision making.
Keywords: association rule mining, data mining, online analytical processing, statistical reasoning
Published in DKUM: 02.10.2025; Views: 0; Downloads: 2
Full text (5,23 MB) |
8. The protection of sensitive personal data and privacy in the US and EU with a focus on health data circulating through health appsEma Turnšek, Suzana Kraljić, 2024, original scientific article Abstract: In today’s modern world, we have more than one global actor leading the economy and rapid technological development. The article focuses specifically on the right to sensitive data protection, or more broadly the right to privacy, in American and in EU legal system. This paper shows distinctions between the two and systematically demonstrates the protection of personal data in EU through years. Exploring these distinctions and different interpretations of the right to data protection is significant, because of the potential impacts on the consumer in particular, possibly resulting in being granted different rights when acquiring services in the EU or America. We will also analyse the fundamental legal acts, which are the cornerstones of data privacy. As its main focus, the article will also examine the provisions concerning sensitive personal data, in particular health data. Furthermore, the article will study some specific concerns in connection to the American smart phone, smartwatch and computer health apps that are not fully compliant with basic EU legal principles, human rights or the General Data Protection Regulation. While the technology is so advanced and users may access these apps from anywhere across the world, such apps, and their privacy policies or other typical contracts, should comply with the relevant legislation, valid in the state of user’s nationality or remaining. The paper examines and substantiates the latter through two recent cases. In one, data breaches were punished by imposing a relatively high fine, and in the other case example, no punitive action was yet taken. That being said, the article argues the insufficient data protection framework that does not necessarily provide a consumer with appropriate safeguards, which is especially relevant in cases of transmission of personal health data.
Keywords: data protection, privacy, sensitive Data, EU vs. US Legal Systems, health Data
Published in DKUM: 29.08.2025; Views: 0; Downloads: 9
Full text (486,05 KB)
This document has many files! More... |
9. The “objective test” and the downstream market presence requirement in Big Data access cases under the essential facilities doctrine - a critical assessmentRok Dacar, 2024, original scientific article Abstract: One possible way to gain access to competitively relevant sets of Big Data is toapply the essential facilities doctrine. However, the European Commission and theEuropean Court of Justice have established several different criteria for applying thedoctrine. Since neither institution has yet applied the doctrine in Big Data accesscases, it is not clear which of the criteria applies in such positions. This paper attemptsto analyze the impact of the “objective test” and the requirement that the controllingcompany be active in the downstream market (which are included in all assessmentcriteria) in Big Data access cases, with the goal of answering the research question,“Do the application of the “objective test” and the requirement that the controllingcompany be active in the downstream market impede the effectiveness of the doctrinein Big Data access cases under EU competition law, and if so, how should they bechanged?” The conclusion is that in Big Data access cases, the “objective test” shouldbe mitigated and replaced by the “subjective test” or the “average company test” andthe requirement that the controlling company be active in the downstream marketshould be discarded altogether in order for the doctrine to be an effective tool foraccessing competitively relevant sets of Big Data.
Keywords: essential facilities, doctrine, big data, mandated data access, Bronner ruling
Published in DKUM: 29.08.2025; Views: 0; Downloads: 10
Full text (209,48 KB)
This document has many files! More... |
10. Cessante ratione legis, cessat ipsa lex? : data and privacy protection in the digitized energy sector amidst green and digital transformation processesZoran Dimović, 2024, original scientific article Abstract: The ex ante regulation of green and digital transformation processes is set to significantly impact personal data and privacy protection in the digitalized energy sector. Although the drive for digitization aligns with EU values, goals, and objectives, it does not inherently ensure compliance with fundamental human rights. While general rules for personal data and privacy protection are sufficiently flexible to allow for appropriate interpretation, implementing sector-specific human rights regulations would enhance legal certainty. This is particularly crucial given the heightened sensitivity of the electricity sector compared to natural gas or heat. The observed lack of standardization in the digitalization of the energy sector is likely to become even more pronounced with the continued development of digital technologies. This increasing complexity underscores the need for comprehensive regulatory frameworks that address both the opportunities and challenges presented by the green and digital transformation. These considerations have significant implications for policymakers, academics, and legal practitioners. Understanding and addressing these issues is essential for ensuring that the transformation processes in the energy sector are conducted in a manner that respects personal data and privacy protection while advancing sustainable and digital innovation. The development of robust and specific regulations will be key to balancing these objectives and ensuring the protection of fundamental human rights in an increasingly digitalized energy landscape.
Keywords: data protection, digitized energy sector, energy law, EU core values, green and digital transformation, privacy protection, public law
Published in DKUM: 29.08.2025; Views: 0; Downloads: 6
Full text (2,27 MB) |
