Miloš Ilić

International Journal Of Human–Computer Interaction

Exploring Learner Engagement in E-Learning Environments: A Predictive Analytics Perspective

Mikić, Vladimir; Keković, Goran; Mangaroska, Katerina; Ilić, Miloš; Kopanja, Lazar; Vesin, Boban

https://doi.org/10.1080/10447318.2025.2535530

During the last decade, the embracement of learner engagement in developing educational technologies has contributed to the amalgamation of favorable pedagogical practices and advanced learning tools. New opportunities for tailoring data-driven learning designs created optimal conditions for crafting personalized, interactive e-learning environments that foster successful learning outcomes. Although a plethora of metrics exist to capture engagement, there is a need for comprehensive research that incorporates both the learner’s subjective perceptions of their engagement and the objective indicators of their actual engagement. The goal of this research is twofold: first, we aim to investigate the relationships between the interaction data on student behavior in an e-learning environment and their self-reported engagement data, and second, to design a model for predicting students’ level of engagement based on the study findings. Statistical analysis was conducted using data from (n = 45) undergraduate students at the University of South-Eastern Norway who completed a one-semester programming course, to explore relationships between their engagement and behavior in the programming tutoring system. Artificial neural networks were then used to develop a prediction model for classifying students’ engagement levels, leveraging the algorithms’ adaptability to diverse input data structures and classification efficiency. The findings highlight the importance of e-learning features like coding exercises, topic-based assessments, and explanatory hints in fostering student engagement. They also demonstrate the feasibility of predicting engagement using learner activity, interaction time, and learning outcomes. The study provides insights that inform the development of future educational designs for personalized engagement detection and improved learning outcomes.

e-Learning environment, learning engagement, behavior data, questionnaire, ANN

M21

Proceedings of the International Scientific and Professional Conference “ALFATECH” – Smart Cities and Modern Technologies

Project management in smart city development: challenges and best practices

Ilić, Miloš; Mikić, Vladimir

https://doi.org/10.46793/ALFATECHproc25.043I

Successful project management represents the basis of effective smart city development, demanding a systematic approach that integrates technology, infrastructure, and urban requirements. However, the proper management of smart city projects encounters different challenges, such as managing budgets, coordinating employees, defining deadlines, and ensuring stakeholder collaboration. Effective project management is essential for overcoming these difficulties and ensuring successful project completion. That is why this study will focus on project management as a means for effective smart city development, and it will also explore challenges and best practices in that context. The goal is to provide a thorough framework for project managers, offering insights into balancing innovation with practical execution in the context of smart city development.

best practices, challenges, development, project management, smart city

M33

Book of Abstracts of the International Scientific and Professional Conference “ALFATECH” – Smart Cities and Modern Technologies

Synergy of Smart Technologies: IoT as the Foundation for the Evolution of Smart Cities

Ilić, Miloš

/

The evolution of urban environments into smart cities depends on the integration of advanced technologies that aim to improve many aspects. Among these aspects are better quality of life, resource optimization, sustainability, efficient public administration, smart education, etc. The Internet of Things (IoT) plays a crucial role in this transformation by enabling seamless communication between a wide range of devices and systems. IoT can not only automate and optimize many important processes for smart cities, but it can also simplify them. IoT helps manage urban infrastructure more effectively, including energy, transportation, public safety, and many more, by facilitating real-time data collection. As cities face new challenges, IoT has the potential to reshape urban living, making cities more responsive and adaptable, which can be of great importance to residents. Nonetheless, the widespread adoption of IoT raises concerns over data security, privacy, and the necessity of a reliable infrastructure. This paper explores the role of IoT in the evolution of smart cities, examining both its opportunities and challenges and how it is driving innovation in urban development. In spite of many issues and complexities, IoT is still defining the future of cities by creating sustainable environments and making them smarter and more connected.

smart cities, internet of things (IoT), urban sustainability, technology integration, data security

M34

IEEE Transactions on Learning Technologies

Predicting Student Performance in a Programming Tutoring System Using AI and Filtering Techniques

Ilić, Miloš; Keković, Goran; Mikić, Vladimir; Mangaroska, Katerina; Kopanja, Lazar; Vesin, Boban

https://doi.org/10.1109/TLT.2024.3431473

In recent years, there has been an increasing trend of utilizing artificial intelligence (AI) methodologies over traditional statistical methods for predicting student performance in elearning contexts. Notably, a considerable number of researchers have adopted AI techniques without conducting a comprehensive investigation into the most appropriate and accurate approach to employ. Additionally, determining the most suitable input parameters for each AI technique remains a pertinent question in this domain. This study employs machine learning (ML) and artificial neural networks (ANN) to predict student grades within a programming tutoring system. The experiment involved university students whose interaction data with the e-learning system were analyzed and used for predictions. By identifying the structural relationships between the properties of the input data, this research aims to determine the most efficient AI method for accurately predicting student performance in elearning systems. The structure of the input data in these systems is described by variables related to individual student activities, so correlations between variables were a natural starting point for further theoretical considerations. In this manner, by applying a filtering technique based on the mrMR (minimum redundancy - Maximum Relevance) criterion, it was shown that correlations among predictors and between predictors and the target variable play a significant role in defining the appropriate model for predicting student grades. The results showed that ANN (the Levenberg-Marquardt algorithm with Bayesian regularization) outperformed ML methods and predicted outcomes with the highest accuracy. The results obtained from this study can be of great importance for learning technologies engineering and for AI in general.

e-learning, programming tutoring systems, artificial intelligence, artificial neural networks, machine learning

M21

Proceedings of the International Scientific and Professional Conference “ALFATECH” – Smart Cities and Modern Technologies

The use of business intelligence in the development and management of smart cities

Ilić, Miloš; Mikić, Vladimir

https://conference.alfatech.rs/wp-content/uploads/2025/05/THE-USE-OF-BUSINESS-INTELLIGENCE-IN-THE-DEVELOPMENT-AND-MANAGEMENT-OF-SMART-CITIES.pdf

In recent years, smart cities, as well as their development and management, have become a popular study topic among researchers. Smart cities, through the use of different technologies, produce vast amounts of data. Business intelligence (BI) is a set of techniques and procedures used for collecting and analyzing data and turning it into useful insights that can assist in decision-making. For these purposes, BI employs various tools to process data and display analytical findings with some kind of visualization, such as reports, charts, or different gauges. This paper aims to show how essential BI can be for the development and management of smart cities. The integration of smart cities and BI technology can bring great benefits for residents and city officials since it may provide them with valuable information that can address complex issues.

business intelligence, smart cities, databases, BI tools, data mining

M33

Artificial Intelligence Review

Intelligent techniques in e-learning: a literature review

Ilić, Miloš; Mikić, Vladimir; Kopanja, Lazar; Vesin, Boban

https://doi.org/10.1007/s10462-023-10508-1

Online learning has become increasingly important, having in mind the latest events, imposed isolation measures and closed schools and campuses. Consequently, teachers and students need to embrace digital tools and platforms, bridge the newly established physical gap between them, and consume education in various new ways. Although literature indicates that the development of intelligent techniques must be incorporated in e-learning systems to make them more effective, the need exists for research on how these techniques impact the whole process of online learning, and how they affect learners’ performance. This paper aims to provide comprehensive research on innovations in e-learning, and present a literature review of used intelligent techniques and explore their potential benefits. This research presents a categorization of intelligent techniques, and explores their roles in e-learning environments. By summarizing the state of the art in the area, the authors outline past research, highlight its gaps, and indicate important implications for practice. The goal is to understand better available intelligent techniques, their implementation and application in e-learning context, and their impact on improving learning in online education. Finally, the review concludes that AI-supported solutions not only can support learner and teacher, by recommending resources and grading submissions, but they can offer fully personalized learning experience.

artificial intelligence, e-learning, intelligent techniques, intelligent tutoring systems, personalization

M21a+

Proceedings of the 9th Conference with International Participation on Knowledge Management and Informatics

Performance analysis of C# programming language in Visual Studio 2017, 2019, and 2022

Ilić, Miloš; Mikić, Vladimir; Gligorijević, Milan; Zlatković, Dragan

https://www.researchgate.net/publication/368874837_PERFORMANCE_ANALYSIS_OF_C_PROGRAMMING_LANGUAGE_IN_VISUAL_STUDIO_2017_2019_AND_2022

In recent literature, researchers have often compared the performance of different programming languages, all in favour of finding optimal solutions to various problems. Dynamic programming is one of the most popular programming paradigms when it comes to the implementation of optimization algorithms. It focuses on fragmenting the main problem into sub-problems, and relies on the fact that the optimal solution for the main problem correlates with the optimal solutions of its sub-problems. This paper provides an analysis on how various C# programming language environment versions perform regarding three of the most common optimization problems: the Fibonacci sequence, the longest increasing subsequence, and the knapsack problem. The results obtained from this research identify the most efficient and reliable Visual Studio version.

C#, Visual Studio, dynamic programming, algorithms, performance analysis

M63

Computer Applications in Engineering Education

Personalisation methods in e-learning - A literature review

Mikić, Vladimir; Ilić, Miloš; Kopanja, Lazar; Vesin, Boban

https://doi.org/10.1002/cae.22566

Over the years, personalisation in e‐learning has evolved as a promising paradigm for matching learners' specific requirements. Although many literature reviews on personalised e‐learning have been conducted, there are still voids and limitations in the comprehensive literature survey regarding how personalisation might occur in e‐learning environments and benefit the teaching and learning process. In addition, no design guidelines, frameworks, or tools to guide its implementation exist, so practice can vary widely. The principal purpose of this literature review is to examine the subject, provide insights into the use of personalised techniques and systems in e‐learning, and investigate its impact on the engagement and success of the students. This study applies methods of precise selection criteria to determine which of the selected publications have the strongest interconnection and relevance with the topic of e‐learning personalisation. It also categorises the personalisation techniques employed by each identified system and highlights new perspectives and advances in the area.

adaptive systems, e‐learning, intelligent tutoring systems, personalisation, technology-enhanced learning

M22

Proceedings of the 9th International Scientific Conference Technics and Informatics in Education – TIE 2022

Providing dynamic adaptivity in Moodle LMS according to Felder-Silverman model of learning styles

Zlatković, Dragan; Denić, Nebojša; Ilić, Miloš; Zakić, Aleksandar

https://doi.org/10.46793/TIE22.271Z

E-learning as a difficult structure contains distance learning, teaching resources in many forms and shapes, group and individual learning procedures, as well as interactive and tuition work. In order to increase the use and efficiency of e-learning systems, it is necessary to consider the individualities of students and their learning styles. Based on data collected in various ways, research methods Felder-Silverman Index of Learning Style Questionary (ILS), using the Moodle LMS, based on the subjective valuation of teachers, as well as based on data from the corporate information system, the affinities of students are determined. Then, based on this information, an adaptation is made, a process that adjusts the work of the LMS based on the learning styles of the students. The major goals that can be achieved by dynamic adaptation the e-learning system are to improve the appearance and effectiveness of the course, support in finding information about the subject, more efficient search and placement of search results in terms of student’s interest, and rise students faithfulness to the educational institution.

e-learning, ILS questionary, learning style, moodle LMS, dynamic adaptation

M33

Proceedings of the 12th International Conference on Applied Information and Internet Technologies - AIIT 2022

The use of scaffolding approach in technology-enhanced learning: A literature review

Mikić, Vladimir; Ilić, Miloš; Kopanja, Lazar; Vesin, Boban

https://aiit-conference.org/archive/Proceedings_AIIT2022.pdf

Scaffolding in the context of learning represents an instructional approach that gradually guides learners to a greater level of independence and comprehension during the learning process. This literature survey has the aim of shedding some light on the literature evidence regarding the implementation of the scaffolding approach in technology-enhanced learning (TEL) environments, as well as clarifying the fields’ current focus concerning research methods and scaffolding designs. The research mainly portrays cross-study evidence and categorizes the results obtained through content analysis into the defined coding dimensions. The results describe the current trend in the field, point to the lack of quantitative research, and suggest further research directions regarding the application of scaffolding in TEL.

scaffolding, technology-enhanced learning, e-learning

M33

Proceedings of the 12th International Conference on Applied Information and Internet Technologies - AIIT 2022

Gamification effectiveness in e-learning systems

Ilić, Miloš; Mikić, Vladimir; Kopanja, Lazar; Vesin, Boban

https://aiit-conference.org/archive/Proceedings_AIIT2022.pdf

E-learning systems are software applications used to deliver online learning. They are proven tools that can enhance the entire learning process and improve student performance, but they face some issues, such as low learner engagement, a lack of motivation, and early course dropout. Gamification, which finds application in many areas, has also been recognized as the solution to these e-learning problems. Gamification utilizes games' potential to create effective e-learning environments more attractive to learners than standard e-learning systems. This paper provides an analysis of gamification and its effectiveness in e-learning for solving difficulties that traditional e-learning systems are unable to address, as well as the usage of game elements for this purpose.

gamification, e-learning, game elements

M33

Ecologica

Smernice i tehnička rešenja za recikliranje električnog i elektronskog otpada u svrhu očuvanja životne sredine u Republici Srbiji

Ilić, Miloš; Gligorić, Nenad; Mikić, Vladimir

https://doi.org/10.18485/ecologica.2022.29.105.8

Proizvodnja električnih i elektronskih uređaja raste svakog dana. Kada se ti uređaji pokvare ili budu odbačeni zbog zastarelosti oni postaju e-otpad. Danas se retko ko odlučuje za popravku uređaja i umesto toga oni se jednostavno zamene novim. Kako u svetu, tako i u Srbiji gomilanje ovog otpada predstavlja sve veći problem. E-otpad sadrži mnoge štetne materije koje mogu negativno uticati na životnu sredinu i zdravlje ljudi. Zato je veoma bitno pravilno rukovanje ovim otpadom i njegova reciklaža kako bi se na efikasan i društveno odgovoran način uklonio. U ovom radu, pored definisanja e-otpada, procesa reciklaže i isticanja njenih prednosti, prikazano je trenutno stanje upravljanja e-otpadom u Republici Srbiji. Takođe dat je i pregled najvažnijih firmi koje se bave reciklažom u ovoj zemlji, dok su na kraju rada iznete i određene preporuke i tehnička rešenja za poboljšanje upravljanja e-otpadom u Republici Srbiji.

e-otpad, upravljanje e-otpadom, reciklaža, životna sredina, tehnička rešenja, prednosti, elektronski uređaji, Republika Srbija

M51