E-business technologies conference proceedings

Exploring the Potential of Adopting Blockchain in Human Resource Management

Ana Ruljević — 2025-12-04

Human resource management (HRM) faces persistent challenges in ensuring data security, verifying credentials, and improving process efficiency. The subject of this research is the development of a blockchain-based HRM ecosystem to address these issues by leveraging decentralized data management and smart contract automation. The paper analyzes the concepts of blockchain technology with a focus on its application in HRM. The practical part of the work involves a survey of HR stakeholders, guided by the adapted Blockchain Adoption Model, to examine their readiness for blockchain adoption. This approach highlights the potential of blockchain to enhance trust and efficiency in HRM processes.

From Paper to Blockchain: Toward Sustainable Decentralized Identity in E-Government

Milos Jolović — 2025-12-03

In the era of rapid digital innovations and transformations, identity management still remains a largely paper-based and centralized process, which can lead to excessive paperwork, inefficient public administration and serious data privacy and security concerns. This paper aims to present GreenChainID – a digital identity management platform prototype, based on blockchain technology and Self-Sovereign Identity (SSI) principle. The proposed platform prototype is designed to offer citizens several key functionalities such as secure personal data sharing, remote document signing, and anonymous digital petitions voting. Beyond offering citizens to selectively and carefully choose which personal data they are sharing with other stakeholders in both public and private sector, GreenChainID highlights sustainability by cutting resource consumption in public administration, paperwork, and citizen’s need for physical presence.

The Role and Limitations of Counter-Drone Systems in Smart Cities

Slaviša Sovilj — 2025-12-04

In recent years, unmanned aerial vehicles (UAVs) have experienced significant growth in use across both military and civilian sectors due to their low production costs and wide range of applications. With the increase in UAV usage in the civilian sector, concerns arise regarding the safety of citizens in urban environments, where malicious use or unintentional handling errors of UAVs can lead to serious incidents. In response to this threat, counter-drone systems are being developed to protect against potentially dangerous UAVs. Like UAVs themselves, counter-drone systems were primarily developed for military operations, but recently there has been a need for their deployment in the civilian sector, particularly in urban areas. This paper provides a review of the literature, technologies and legal frameworks related to counter-drone systems, analyzes the specificities of their use in smart cities, identifies potential challenges in their implementation in urban environments, and proposes solutions to address these challenges.

Evaluating the Role of Heuristics in LLM-Based Extraction of Entity-Relationship Models

Tatjana Stojanović — 2025-12-04

Translating natural language requirements into precise conceptual models is a challenging and very important step in software development. This paper investigates the effectiveness of combining modelling heuristics with large language models for extracting Extended Entity-Relationship (EER) models from text. Two prompting strategies were compared: zero-shot LLM prompting and heuristic-guided prompting. The evaluation, based on 14 manually annotated models, compares precision, recall, and F1-score for modeling constructs: entities, attributes, and relationships. Results suggest that integrating heuristics can improve the reliability and consistency of LLM-generated models, particularly in entity and attribute extraction. Although the heuristic-guided method requires more processing time, it shows stronger alignment with established modeling practices and offers better resilience to textual ambiguity. These findings indicate that heuristics can provide valuable structure and guidance to LLMs, and highlight the potential for further refinement to address recurring errors and improve performance across diverse domains.

Text as Expressive Content on Instagram: A Case Study of @djokernole and the Role of Captions in Audience Engagement

Nada Mihailović — 2025-12-04

This paper analyzes the expressive role of text on Instagram through a case study of the profile @djokernole, representing global tennis champion Novak Djokovic. It focuses on three key dimensions: caption construction, thematic composition of posts (professional, family, and sponsored), and performance metrics such as engagement rate, follower growth, and comment activity. The study situates these findings within the broader evolution of Instagram from a photo-sharing platform to a global marketing ecosystem. It highlights how Djokovic effectively balances personal authenticity with professional branding, maintaining digital relevance among diverse audiences. Particular emphasis is placed on the role of captions as more than mere annotations — they function as carriers of narrative, emotion, and cultural resonance. Through this profile, the paper illustrates how even high-profile public figures must navigate the delicate interplay of audience expectations, sponsorship obligations, and content cadence to sustain a meaningful digital presence.

The Metaverse and Virtual Reality: New Frontiers in Customer Experience and Digital Sales

Nevena Jeremić — 2025-12-03

The emergence of the metaverse and virtual reality
has transformed the way companies connect with customers in
the emerging digital environment. Initially intended solely for
entertainment purposes, these new technologies have quickly
become impressively enabling new forms of engagement,
enabling businesses to build interactive experiences that go far
beyond traditional online platforms. This paper explores the
evolving role of the metaverse and virtual reality as alternative
channels for digital commerce and user experience design. The
study highlights both the promise and limitations of
implementation challenges, including technical integration, data
privacy concerns, and the tension between innovation and user
readiness. Although still in its infancy, the metaverse – powered
by virtual reality (VR) – offers a compelling path for forwardlooking brands seeking not only differentiation but also deeper
forms of digital engagement in an increasingly saturated
market.

Reimagining International Mobility Through Blockchain: A Model for End-to-End Recruitment, Legal Compliance, and Stakeholder Trust

Aleksandar Ivanovic — 2025-12-04

International labor mobility encompasses a complex network of processes and stakeholders, including governmental bodies, employers, recruitment firms, and legal institutions, all functioning within and across varied legal frameworks. This multifaceted landscape frequently results in procedural inefficiencies, lack of transparency, and increased vulnerability to fraud and regulatory breaches. This paper introduces a conceptual framework for a blockchain-based ecosystem intended to streamline international labor mobility. By leveraging decentralized, transparent, and tamper-resistant technologies, the proposed system seeks to address critical inefficiencies and build trust among participants. Central to the framework are smart contracts, secure digital identities, and interoperable legal modules that collectively enable safer recruitment practices, enforce regulatory standards, and automate key procedural interactions. This paper lays the theoretical groundwork for future implementation, offering a vision for more secure, efficient, and equitable cross-border workforce mobility.

SmartAberration: An annotated multimodal smartphone IMU dataset for aberration detection

Sakshi — 2025-12-04

Smartphone IMU sensors are being used more and more to track different aspects of human activity during everyday life. The sensors built into smartphones yield objective quantifications of normal and anomalous behaviors. The dataset, referred to as SmartAberration, consists of motion data collected from five participants, each engaging in 10 activities, for a total of 50 activity recordings. The data set contains both normal activities and ones that are indicative of potentially suspicious actions, including running in off-limits areas, punching, or kicking. These are of specific interest because they have the potential to indicate security threats or interruptions of normal patterns of movement. The SmartAberration dataset records motion signals derived from the smartphone IMU data, such as parameters of acceleration, velocity, and angular velocity. Each sample is labeled in terms of the actual activity being undertaken, allowing behaviors to be classified based on their signal. This publicly accessible dataset provides a wide range of opportunities for researchers to utilize intelligent data analysis methods in order to automatically discover and type human activities. It provides a singular platform for creating systems that can continuously monitor and evaluate normal and abnormal behaviors in real-time, without the need for self-reporting or manual observation. This technology could make security, health monitoring, and behavioral analysis applications more powerful, enabling proactive interventions as well as enhanced comprehension of human activity patterns.

Social Media Survey Dataset: Exploring the Impact of social media on Personal Well-Being

Devesh Attri — 2025-12-04

Social media has become an integral part of life, and step by step occupies a certain position in people’s everyday lives. Concerning its recourse in social life, it has created rising societal concern in areas such as general happiness, mood, concentration, and sleep. The research, therefore, systematically and comprehensively explores these effects with the help of the Social Media Survey Dataset, which consists of cross-sectional ordinal data of various characteristics and potential behavioral outcomes of employing such platforms. This research utilizes data collected from participants of different ages and various jobs. Descriptive questions concerned with specific content, the feelings evoked from content, and likely impact of content consumption on mood, attention span and quality of sleep. Thus, the data was analyzed using such steps of data preprocessing as feature encoding and dimensionality reduction using PCA. For the initial analysis of the project, five models of machine learning were employed which include Logistic Regression, Support Vector Machines, Random Forest, XG Boost, and Artificial Neural Network. The first significant set of performance measures was used to find a reference point for the following studies and to determine to what degree modern models can identify patterns in the explored dataset. Classifiers depicted a moderate baseline accuracy between 25% to 59% suggesting that there could be an improvement. These results shed the light on the dataset for future research on the impact of social media and to enhance the finding of the intervention in the field of digital health and wellness.

A Review on SCADA for Healthcare Systems

Ebenezer Agbozo — 2025-12-04

Healthcare systems continue to experience an increased level of technological innovation due to the desire to provide quality services for patients and improve decision-making of health experts. Technologies such as artificial intelligence, digital twins, big data, and blockchain are some of these novel solutions being introduced. This study explores the state of research of one of such innovations in healthcare which is known as Supervisory Control and Data Acquisition (SCADA) systems. Despite SCADA systems being widely known in the manufacturing and production spheres, they have a gradual level of adoption in healthcare organizational systems. The study adopts a computational literature review method to extract knowledge from literature from prominent sources with publications discussing the implementation of SCADA systems in healthcare. Our study revealed that SCADA systems research with respect to their deployments in healthcare mainly focused on cyber security. The study presents a snapshot of research on SCADA systems in healthcare and provides research trajectories to guide future research.

Predictors of intention to use IPS QR codes in payment transactions in the Republic of Serbia

Miloš Mijić — 2025-12-04

Mobile applications for personal finance were created for the common man with the aim of improving mobile banking services through significant facilitation in the field of monetary transactions. The National Bank of Serbia has enabled consumers to complete a transaction at the point of sale using the IPS QR code application. The goal of the work was to determine the predictors of intention to use mobile applications in Serbia according to the extended UTAUT2 model. The Habit construct has the most significant influence on the intention to use the IPS QR code mobile application. The Price Value and Facilitating Conditions constructs have a strong influence. The construct Hedonic motivation shows a significant and positive influence. Social impact, Expected effort and Expected performance have a slightly weaker impact, but still significant. The obtained results indicate that Habit is the most important factor in the acceptance of IPS QR technology. The tested model is applicable for domestic users, especially in the context of the introduction of national digital services, IPS QR code. In further research, attention can be paid to differences between generations, geographical distribution and digital literacy.

The architecture design of the health monitoring system

Anja Radulović — 2025-12-04

Smart health devices enable users to create health habits, and maintain or improve their overall well-being. This growing trend increases the demand for systems capable of processing and visualizing collected data in real-time. The focus of this paper is to present the architecture design of a health monitoring system, developed as a full-stack web application using modular MVC-based architecture. The designed system is user-friendly and scalable, offering different types of interactive reports based on the type of the collected health data. The system allows users to register, synchronize their health data with the application, and view personalized reports that help them follow their daily, weekly, and monthly health trends. The result of the implementation provides a functional and adaptable platform for managing personal health data, which can support future integration with real-world wearable devices.

Multi-talent Discovery, Development and Drive in Digital Dynamics: The Case of Smart Kids Connect

Teklehaimanot Embaye — 2025-12-04

This paper explores a holistic approach to identifying and nurturing multiple talents in children (ages 7–17) within today’s digital environment. We define eight talent categories adapted from Gardner’s multiple intelligences (e.g. Thinking & Problem-Solving, Language & Expression, etc.) and introduce a novel framework for Discovery, Development, and Drive for kids in Digital Dynamics alongside a mapping method of Classes, Challenges, Coaching, and Competitions to operationalize talent development in a program called Smart Kids Connect. We analyze an initial pilot study (N=32, immigrants in Rwanda and Angola) with a custom developed questionnaire and Exploration Readiness Index to gauge curiosity and growth mindset. Key findings on talent profiles, clustering, and drive inform the design of a comprehensive digital talent discovery and development platform. Building on a Digital Project-Based Learning model and prior work on African youth and diaspora, we discuss implications for scaling to 500+ kids and early youth globally, fostering a connected multi-talent ecosystem for future research and innovation.

Predicting heart disease among males based on performance analysis using machine learning technology: an unsupervised feature selection approach

Farhad Lotfi — 2025-12-04

Abstract—Machine learning algorithms play a vital role in the early intervention of heart disease by enabling accurate, data-driven insights. This study focuses on predicting heart disease among males using an unsupervised learning approach applied to the PTB-XL ECG dataset. After thorough preprocessing—including MinMaxScaler normalisation, Variance Thresholding, and PCA—K-Means Clustering was employed to detect hidden patterns in patient data. The optimal model with k=8 achieved a silhouette score of 0.82 and inertia of 5.09, outperforming Agglomerative and DBSCAN in both cohesion and interpretability. These results confirm the effectiveness of unsupervised learning in extracting clinically relevant patterns and highlight the importance of gender-specific modelling in heart disease prediction. The proposed framework offers a scalable and robust solution for early risk assessment and supports future development of intelligent, sex-aware diagnostic systems.

Student evaluation of teachers' work in project-based teaching in higher vocational education

Miloš Mijić — 2025-12-04

Teachers in higher vocational education should often critically review their teaching work. In addition to self-examination, it would be desirable to include students in their critical analysis. Feedback from students can greatly help the teacher to critically examine aspects of their work and then make an effort to improve them. The paper has designed and tested a method of collecting feedback for the teacher from students for one segment of the implemented project teaching. Through a survey, information about the teacher's work was collected, such as ratings that show students' satisfaction with the teacher's organizational skills and his willingness to help in critical situations. The students' opinion of the teacher represents important feedback that they will use to analyze their own work. After critically reviewing the analyzed information, the teacher can correct his work in order to build his own approach to teaching practice, creating his own professional identity and his own system of teaching values with significant credibility among his students.

How Advancing AI is Shaping the Future of eCommerce. A Detailed Literature Review

Daniyal Mukhtar — 2025-12-04

One of the most applied and also most exciting areas of computer science now days is AI or AI. In its basics, AI is about making Smart systems designed to carry out functions typically dependent on human intelligence. Now a days AI is known too almost everyone. In fact, it has been integrated into our daily lives — from online learning to e-commerce platforms to household EMR systems and other technology — to streamline efficiency. There are few if any industries that the AI will not touch. From grocery store self-checkouts to streamlined airport kiosks with high-tech safety systems, we are surrounded by AI in one way or another. It is also entering schools, offices and just about every other domain, weaving itself more and more into the fabric of our daily lives every day. In our rapidly moving world, profit-driven planet, businesses are required to operate efficiently across different time zones and customer demands. AI helps by enabling real-time data analysis, improving productivity, and enhancing safety and security measures.

A prime illustration of AI in action is in action is the web-based commerce industry. Organizations use AI to grow their client base, analyze shopping behaviors, solve problems in real time, and streamline operations. You’ll find AI working behind the scenes in chatbots, Technologies like CRM platforms, ERP applications, and PCM systems that streamline business operations and data handling.

Digital Transformation in Export-Import Banking: A Literature Review

Mahamane Ali Bossoma — 2025-12-04

This literature review integrates recent scholarly findings on the incorporation of digital tools into export-import banking. The studies discussed indicate the transformative role these tools can play in enhancing transparency, security, efficiency, and trust in trade operations. Core applications include smart contracts, decentralized data management, and paperless documentation, all of which streamline processes, prevent fraud, and reduce transaction costs. The literature also covers challenges like regulatory uncertainty, scalability, and integration with the current financial infrastructures. By mapping thematic contributions from more than 70 scholarly sources, this review skims a structured overview of the impact of blockchain on digital trade finance, identifies current limitations, and provides outlines of future directions for research.

Algorithm for Vertical Handover based on GRA and User preference

Siddhartha Goutam — 2025-12-03

As of today, multiple heterogeneous wireless networks have been deployed across geography. This has become possible due to developments & growth in the areas of Information & Communication Technologies. Considering the simultaneous existence of multiple Radio Access Technologies (RATs), the problem pertaining to the selecting the best n/w, all the time & place, has become crucial. The smart mobile phone user, based on his requirements and priorities, should get latched to the best network among the available set of various candidate n/w. The issue of network selection can be resolved by effective Vertical Handover (VHO). The choice of the best network can be made by applying the multi attribute decision making technique called as Grey Relational Coefficient (GRC). This research paper presents an algorithm for network selection based on GRC. The scores of the networks are calculated basis GRC and then the handover is happens to the best network. The main criteria considered for network selection are RSS, bandwidth, cost & user velocity.

The Ethics of AI-Driven Marketing: Challenges and Opportunities

Raj Saha — 2025-12-04

This study explores the ethical challenges involved in using artificial intelligence (AI) in marketing, with a focus on issues like privacy, transparency, and algorithmic bias. It aims to identify responsible practices that support innovation while maintaining consumer trust and aligning with societal values. Using a structured survey, data was collected from 215 respondents and analyzed through statistical models to examine the relationships among Transparency, Privacy, Ethics, Adaptability, Cooperation, and Consumer Trust. The findings show that Transparency and Privacy significantly influence consumer trust in AI-driven marketing. However, Adaptability, Cooperation, and Ethical AI practices did not show statistically significant effects, indicating a gap between ethical efforts and consumer awareness. These results emphasize the need for better communication and education about ethical AI. While limited by its sample and reliance on self-reported data, the study offers valuable insights and practical recommendations for marketers to adopt more transparent and privacy-focused AI strategies.

Study of new generation cloud based digital ERP system

Siddhartha Goutam — 2025-12-03

The global digital transformation has led to
paradigm shift in Enterprise Resource Planning systems. This
major shift occurs while transition is performed from
traditional on premises models to cloud based ERP model.
This research paper explores the strategic factors which act as
catalysts to this major transformation. The research paper
investigates the benefits, challenges, adoption drivers and the
business impact of cloud ERP systems. The research paper
focuses for presenting strategic recommendations for
successful and smother transitions and increased digital
maturity

Evolution of E-Business Research: A Bibliometric Study on Innovation and Digital Transformation

Reynald Yunansyah — 2025-12-04

This bibliometric study explores the global evolution of e-business research within the context of innovation and digital transformation over the past decade, analyzing 7,981 documents from the Scopus database (2014–2024) using the Biblioshiny tool. The findings reveal a consistent increase in publications, underscoring the strategic role of e-business in driving digital transformation across industries. Key research themes include e-business models, processes, and technologies, along with their effects on organizational performance, customer behavior, and sustainability. Emerging topics like artificial intelligence, big data analytics, and the influence of the COVID-19 pandemic on e-business practices further highlight the field's dynamism. This study provides a comprehensive understanding of e-business research, offering valuable insights for businesses, entrepreneurs, and policymakers to advance digital innovation and foster a robust digital economy.

Trust as a determinant of Electronic Business success: Analysis of key factors

Anton Ećimović — 2025-12-03

U savremenom digitalnom dobu elektronsko
poslovanje predstavlja dominantan oblik komercijalne
aktivnosti, koji menja način na koji akteri posluju i
medjusobno komuniciraju. Medjutim, specifičnosti onlajn
okruženja, kao što su fizička distanca, anonimnost, ograničen
nivo kontrole i potencijalni oportunizam, stvaraju izazove koji
mogu narušiti poverenje izmedju učesnika. Upravo u tom
kontekstu poverenje se nameće kao ključna determinanta
uspešnosti elektronskog poslovanja.

Blockchain-Enabled Trust Framework for Vehicle-to-Everything (V2X) Systems

Ana Kovacevic — 2025-12-03

This paper, prepared as part of a doctoral colloquium, presents preliminary research toward establishing a decentralized trust model for Vehicle-to-Everything (V2X) systems using blockchain technology. As an alternative to traditional PKI-based architectures, it proposes a security framework based on Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). The paper outlines a two-layer architecture that combines identity management with distributed logging of security-relevant events. The approach focuses on representative V2X use cases that do not require ultra-low latency, such as over-the-air (OTA) software updates, electric vehicle (EV) charging authentication, vehicle-to-grid (V2G) interactions, and cross-border vehicle identity verification.

A Novel Framework for Usability Evaluation of Mass-based Software

Harshita Sharma — 2025-12-04

Mass-based software platforms such as instant messaging apps, video conferencing platforms, and generative AI interfaces play a pivotal role in modern e-businesses. Many businesses use these software as an outreach for new customers. Their usability, hence significantly affects digital engagement, customer satisfaction, and customer retention. In view of the limitations of the existing literature, tools and techniques for mass-based software, this research work proposes a four phase methodology with the intent to develop and design tools, techniques and a framework for the empirical evaluation of various performance and human-factor related parameters like effectiveness, efficiency, satisfaction, cognitive load, etc. widely used in the domain of usability evlauation. In addition, this research work also aims to propose and automate usability heuristics adapted especially to the use of mass-based software for the context of e-businesses. For e-business platforms, the framework provides actionable insights into UX design, supports detection of usability issues, and facilitates informed design decisions for improved customer retention in today's customer-centric digital transformation.

AI In Telecommunications – Impact On Regulation

Tijana Milovanović — 2025-12-04

To address all the challenges and make the most of the opportunities that artificial intelligence offers, the European AI2 Strategy was published in April 2018 [1]. The Strategy puts people at the center of the development of artificial intelligence. Although most AI systems in the telecommunications sector are still in a development phase, artificial intelligence is expected to play an important role in this sector in the next period. Regulators and decision-makers must, therefore, develop robust and, most of all, forward-looking policies.

Context of Business Transformation: From Traditional to Generative AI Agents

Zoran Pavlović — 2025-12-03

In business processes, the activities of people are
less and less represented. Realization of the needs of users as
well as employees in companies can be realized through the
application of computer systems. This paper presents the
dimensions of context and situational parameters in
communication processes. Business modalities include the
traditional ways that are still applied, the application of
autonomous intelligent agents and the application of generative
artificial intelligence agents that are currently occupying the
academic community and increasingly business societies and
organizations. The main goal of the work includes the
presentation of the advantages of applying innovative digital
technologies and the transformation that is inevitable. In this
paper, the semantic dimensions of the context with the factors
of communication dynamics and models of communication
dynamics are presented, where the advantages of the
application from traditional to generative artificial intelligence
agents are clearly seen.

Social Media as a Tool for Promoting the Šarganska Osmica Museum-Tourist Complex

Danijela Stojanović — 2025-12-04

This paper explores the role of social media in the promotion of the Šarganska Osmica museum-tourist complex, located in Mokra Gora, Serbia. Through a quantitative analysis of data from Facebook, Instagram, and TikTok, combined with a qualitative assessment of content and user interaction, the study examines the significance of digital communication in enhancing the visibility and business performance of the complex. Special emphasis is placed on evaluating promotional practices and their contribution to brand development and the destination’s tourism image. The results indicate that social media represents a key and cost-effective tool for improving marketing and attracting visitors. Based on the findings, a strategic framework for digital marketing is proposed to strengthen the complex’s online presence further.

Bias in AI-Driven Candidate Selection Processes

Aleksandar Ćosić — 2025-12-04

This paper examines the nature, causes, and implications of bias in artificial intelligence (AI)-driven candidate selection processes, with a focus on the need for ethical development and application of AI systems. The primary objective is to identify and explain the key causes of bias in AI-driven candidate selection through a review and analysis of existing literature, contemporary studies, and case examples. The contribution of this work lies in proposing directions for future research aimed at mitigating bias and promoting fairness in the candidate selection process.

STARTUPS AND INNOVATIONS BASED ON 5G TECHNOLOGY IN WESTERN BALKAN COUNTRIES - OPPORTUNITIES AND LIMITATIONS

Tijana Milovanovic — 2025-12-04

5G technology, as the fifth generation of high-speed mobile networks, represents a new phase in the development of mobile communications and the opportunities it offers are enormous. Startups that creatively use this technology will not only transform their businesses but will also contribute to the evolution of entire industries. The aim of this article is to show that there is still a lot of space for the development of startups in the countries of the region, especially with the introduction and development of 5G technologies.

Commercialization of Generative Artificial Intelligence in E-Business

Dejana Kresović — 2025-12-04

This paper examines the key aspects of the commercialization of generative artificial intelligence (Gen AI) in the e-business domain. The focus is on distinguishing between three primary commercial models: Business-to-Consumer (B2C), Business-to-Business (B2B), and Business-to-Government (B2G), which differ from one another in terms of target audience, application, technical requirements, and monetization strategies. While B2C solutions are focused on mass accessibility, personalization, and user experience, B2B systems require deep integration with business processes, along with a high level of scalability and security. The B2G model addresses the improvement of public services, but it also raises specific ethical and regulatory questions. The paper also highlights that the development and application of Gen AI are outpacing the response of the scientific community and regulators, creating a need for more intensive collaboration between industry, science, and policymakers to ensure the responsible and sustainable application of this transformative technology.

Roles, Responsibilities, and Value Flows: A Stakeholder Map of Micro-Credential Processes in Higher Education Ecosystem

Tamara Naumović — 2025-12-08

bstract – Micro-credentials are transforming how learning
achievements are recognized across formal and non-formal
education. This paper maps the stakeholder landscape of
micro-credential processes, clarifying roles, responsibilities,
and value flows among participants. Drawing on stakeholder
theory and ecosystem mapping, five core roles are identified:
earner, course provider, issuer, verifier/viewer, and policy maker;
and analyzed across four process groups: learning and earning,
issuance, verification and recognition, and maintenance. The
paper contributes by systematizing stakeholders and their
interrelations, offering a structured view of value exchanges
that supports the design of interoperable, transparent, and
trustworthy micro-credential ecosystems in higher education.

IMI MathCode Duel: A Competition-Based Learning Platform for Students

Aleksandar Milenković — 2025-12-04

This paper presents the web platform IMI MathCode Duel, designed as an interactive environment for primary and secondary school students that encourages learning mathematics and programming through real-time online peer duels. The platform integrates a high-quality task base inspired by the international Mathematical Kangaroo competition and national informatics competitions, enabling customized challenges based on age and knowledge level. The paper outlines the platform’s main features: opponent selection, task generation, automatic grading, support for multiple programming languages, as well as an administrative interface for task management and results analysis. It also examines the platform’s educational potential in fostering active learning, self-assessment, and the development of analytical and algorithmic thinking. Additionally, the possibilities for system expansion through new functionalities and its application in both curricular and extracurricular contexts are discussed.

Marketing Transformation: Generative AI for Content and Strategies

Dejana Kresović — 2025-12-04

Generative Artificial Intelligence (GAI) represents a fundamental shift in marketing, transitioning from passive data analysis to the creation of original content, encompassing texts, images, videos, and audio materials. This characteristic enables high automation and hyper-personalization of marketing processes, enhances user interaction, and optimizes operational procedures. The widespread application of GAI tools across various industries, coupled with predictions of significant market growth and survey data indicating that most marketing professionals actively use AI, suggests that GAI is transitioning from an experimental phase to becoming a key element of contemporary strategies. This paper examines the application of GAI in marketing communication, public relations, the marketing mix, strategy development, and e-marketing, highlighting its strategic implications, challenges, and future directions.

Application of chatbot technology for enhancing knowledge management and ISO standards compliance

Marina Jovanović-Milenković — 2025-12-04

Knowledge management is a key success factor for modern organizations, especially in environments that require a high degree of compliance with internal and external standards. This paper explores the use of chatbot technology as a tool for improving the availability and distribution of organizational knowledge, aiming to enhance process efficiency and compliance. The focus is on digital assistants that provide access to internal procedures, policies, and regulations, thereby facilitating the consistent application of standardized processes in daily operations. A case study in a real-world organization analyzes the effects, benefits, challenges, and recommendations for further development. Special attention is given to chatbot integration in environments governed by ISO standards.

Decentralized Platform for Issuing and Verifying Student Achievements

Dušan Kostić — 2025-12-03

The aim of this paper is to present a prototype platform for issuing and verifying of student achievements across different forms of academic engagement, using blockchain technology. The proposed solution leverages smart contracts and NFT standards to represent and store verifiable proofs of student participation and performance. By utilizing decentralized storage and wallet-based identity, the platform enables secure, transparent, and tamper-proof management of student achievements. This paper outlines the conceptual framework, presents a technical prototype built on Ethereum-compatible blockchain, and discusses the potential implications of applying tokenization in higher education for incentivizing engagement, ensuring verifiability, and fostering innovation in e-learning ecosystems.

Formal Approach to Internet of Things in the Context of the Web 7.0 Project

Radomir A Mihajlović — 2025-12-04

Abstract— Since the introduction of the Internet of Things (IoT) by the International Telecommunication Union (ITU), relevant technology has been a subject of intensive Research and Development (R&D). Various definitions of IoT have been introduced by different R&D groups and authors, as well as by the involved standardization organizations. Upon the review of the vast body of IoT-related literature we have witnessed on numerous occasions arbitrary IoT relevant terminology. Our conclusion was that a more rigorous approach to this fascinating area of R&D is necessary. This paper is primarily focused on IoT semantics consolidation, IoT security, and new horizons of the application of the Zero Trust Architecture (ZTA) to secure and private IoT systems design. The attribute of privacy, being frequently mixed up with security, has been addressed in the context of the Web 7.0 project. In this paper we consider IoT as an extension of the Internet, i.e., as Internet 2.0, and IoT privacy as an extension of the ZTA set of design goals or principles.

Comparison of feature selection approaches in youth depression determination based on handwriting kinematics

Vladimir Džepina — 2025-12-04

Depressive disorder (DD) in youth is a significant, yet underrecognized mental health issue, often accompanied by psychomotor retardation. Handwriting analysis provides a non-invasive and measurable method for detecting such symptoms. This study explores feature selection approaches to improve machine learning-based classification of DD using kinematic features from a task—repetitively writing the lowercase cursive letter “l”. From 177 extracted features, 40 were retained through statistical filtering and further refined using five selection approaches. Logistic regression models were trained and evaluated using subject-wise leave-one-out cross-validation. In this paper, a comparison of different feature selection approaches (Recursive Feature Elimination, Sequential Forward Selection, SHapley Additive exPlanations, Minimum Redundancy Maximum Relevance, and Feature Importance) is presented, considering the occurrence of optimal feature sets as well as the binary classification accuracy of subjects into the DD and control groups.

Physiological Simulation of Arabidopsis thaliana for Plant Digital Twin

Aleksandar Joksimović — 2025-12-03

The simulation of physiological plant growth is a foundation toward the development of a digital twin of plants in smart agriculture. The aim of this study is the development and validation of a physiological model capable of accurately simulating the biochemical dynamics of Arabidopsis thaliana under varying photoperiods. The model incorporates a wide range of internal and external parameters, including starch and sucrose dynamics, nitrogen and phosphorus levels, as well as biomass accumulation and assimilation costs. The simulation results were compared with experimental data from the literature and demonstrated a high degree of agreement in the dynamics of key processes during day/night cycles. These findings confirm the model’s potential as a foundation for a plant digital twin, designed to integrate with real-time data.

Design and development of smart beehive solution

Petar Lukovac — 2025-12-03

This paper focuses on the problem of efficiency in
agriculture and its’ environmental impact. The agricultural
areas are increasing to follow the growing human demand and
ensure food security. These actions have negative impact on
natural habitats and biodiversity. Introduction of smart
solutions in beekeeping can reduce this negative impact by
improving efficiency of this agricultural field, while supporting
the growth of pollinators population and preserving natural
habitats. The paper presents architecture and a prototype of a
smart beehive solution. The paper offers clear segmentation of
layers in smart beehive architecture. This allows for clear
understanding of the role of each part of the solution and quick
error detection and handling. The paper showcases
development of an edge device with all hardware components as
well as key segments of implemented software. The smart
beehive offers additional sensory data to beekeepers supporting
data-based decisions and thus improving efficiency in
beekeeping.

A Novel Biometric Fingerprint IT System in Determining Newborn Baby Identity

Komlen Lalović — 2025-12-04

This work presents totally new IT security system and novel method for biometric verification for new born babies in birthplaces based on fingerprint minutiae. Information system realized combines nowadays program languages such as: Java, Python considering object-oriented languages, C programing language for device programming as structural (line) and SQL as relationship database management system to store encrypted data. RSA as asynchronous algorithm and key store value for encrypted fingerprint minutiae. Information system implementing device for biometric identification of maternity as dual fingerprint scanner that provides data of mother and baby fingerprints on very moment of birth and in further process guarantee maternity over new born baby with 100% accuracy, generating unique ID reference and encrypting those data with cancelable biometrics we developed totally novel method in determining identity based on baby fingerprint minutiae.

Machine Learning and Judicial Rulings Traffic Violations

Dušan Kuzmanović — 2025-12-04

This paper presents a project focused on applying machine learning techniques to develop an assistive tool aimed at facilitating the process of issuing judgments for traffic offenses. Although the project has not yet achieved full implementation through a system-wide rollout for the automatic case management in misdemeanor courts (SIPRES), it has demonstrated significant potential for improving the efficiency and effectiveness of judicial proceedings. The presentation of the project will focus on practical factors and ethics rather than theoretical principles, law, and philosophy. Instead, it will highlight ethical considerations encountered by the authors directly within the model, data, and the proposals of individual decisions.

The application of artificial intelligence methods for the interpretation of dissolved gas analysis results in transformer oil

Nikola Miladinović — 2025-12-04

The growing complexity of power grids driven by the integration of renewable energy sources, electric vehicles, and climate change has increased the importance of reliable maintenance of power transformers (PT). Transformer failures can severely impact electricity generation, transmission, and distribution. Accurate condition assessment, especially through Dissolved Gas Analysis (DGA) of transformer oil, is crucial for early fault detection. This paper presents an overview of recent developments in the application of artificial intelligence (AI) methods for interpreting DGA results to improve diagnostic accuracy. Various supervised, unsupervised, and hybrid approaches are analyzed, with a focus on their capabilities, advantages, and limitations. The paper also discusses two representative case studies from the literature to illustrate the practical implementation and effectiveness of AI-based diagnostics. AI significantly enhances the reliability and automation of transformer condition monitoring, particularly in borderline or uncertain cases, thereby promoting the adoption of web-based and e-commerce preventive maintenance solutions.

The Application of Artifical Inteligence in Breast Cancer Prevention and Early Detection

Andjela Ivković — 2025-12-04

This paper discusses the technological aspects of Artificial Intelligence, Machine Learning, and Deep Learning, and the potential of their application in the early detection and prevention of breast cancer. To gain a complete overview of the potential utilization, the paper highlights the critical challenges in oncology care today through various stages of the patient journey – screening, diagnosis, staging, treatment planning, and therapy outcome prediction. The goal is to identify the bridge between the pain points of preventing and diagnosing breast cancer and the core functionalities of AI systems, such as detection, classification, characterization, and risk stratification. The research indicates that the impact of integrating AI in oncology care is significant and highlights the benefits of collaborative work between healthcare professionals and AI to achieve more precise diagnosis, evaluate the future risk with more certainty, screen more potential breast cancer patients in the same timeframe, and address healthcare communication problems.

The Potential of AI in the Judiciary of Serbia

Dušan Kuzmanović — 2025-12-04

This paper analyzes the potential integration of AI-based tools into the functioning of the judiciary in Serbia. It focuses on existing AI projects within the legal system, experiences from other countries judicial systems. The paper examines the challenges and limitations associated with implementing AI technologies, as well as the potential benefits for increasing efficiency, transparency, and access to justice. The aim is to provide a general overview of currently available solutions and to suggest guidelines for the future development and application of AI in the Serbian judiciary.