Faculty of Computer Science and Engineering
Permanent URI for this communityhttps://repository.ukim.mk/handle/20.500.12188/5
The Faculty of Computer Science and Engineering (FCSE) within UKIM is the largest and most prestigious faculty in the field of computer science and technologies in Macedonia, and among the largest
faculties in that field in the region.
The FCSE teaching staff consists of 50 professors and 30 associates. These include many “best in field” personnel, such as the most referenced scientists in Macedonia and the most influential professors in the ICT industry in the Republic of Macedonia.
Browse
959 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Benchmarking Sentence Encoders in Associating Indicators With Sustainable Development Goals and Targets(Institute of Electrical and Electronics Engineers (IEEE), 2025); ; The United Nations’ 2030 Agenda for Sustainable Development balances the economic, environmental, and social dimension of sustainable development in 17 Sustainable Development Goals (SDGs), monitored through a well-defined set of targets and global indicators. Although essential for humanity’s future well-being, this monitoring is still challenging due to the variable quality of the statistical data of global indicators compiled at the national level and the diversity of indicators used to monitor sustainable development at the subnational level. Associating indicators other than the global ones with the SDGs/targets may help not only to expand the statistical data, but to better align the efforts toward sustainable development taken at (sub)national level. This article presents a model-agnostic framework for associating such indicators with the SDGs and targets by comparing their textual descriptions in a common representation space. While removing the dependence on the quantity and quality of the statistical data of the indicators, it provides human experts with data-driven suggestions on the complex and not always obvious associations between the indicators and the SDGs/targets. A comprehensive domain-specific benchmarking of a diverse sentence encoder portfolio was performed first, followed by fine-tuning of the best ones on a newly created dataset. Five sets of indicators used at the (sub)national level of governance (around 800 indicators in total) were used for the evaluation. Finally, the influence of 40 factors on the results was analyzed using explainable artificial intelligence (xAI) methods. The results show that 1) certain sentence encoders are better suited to solving the task than others (potentially due to their diverse pre-training datasets), 2) the fine-tuning not only improves the predictive performance over the baselines but also reduces the sensitivity to changes in indicator description length (performance drops even by up to 17% for baseline m... - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Evaluating Trustworthiness in AI: Risks, Metrics, and Applications Across Industries(MDPI AG, 2025-07-04) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Multiword Discourse Markers Across Languages: A Linguistic and Computational Perspective(Wiley, 2025-04-22) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Pressure Related Ocular Parameters in Caucasian Patients with Primary Open-Angle Glaucoma(Savvy Science Publisher, 2021-06-02); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, AI Agents in Finance and Fintech: A Scientific Review of Agent-Based Systems, Applications, and Future Horizons(Tech Science Press, 2026) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Detection and Recognition of UAVs by Using Deep Learning Techniques(IEEE, 2025-11-25); The use of drones (UAVs) is multi-dimensional in positive aspects, but it is worrying that they are also used by malicious people in negative aspects. Drones can be misused for smuggling, illegal surveillance, or security violations. The development of an anti-drone system is very necessary in order to prevent the aforementioned problems. This paper discusses the construction of an intelligent system that will detect and recognize drones using data provided by optical technology (camera). Based on the obtained results, they show that the use of techniques for dataset preparation and model training is very promising. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, THE ART OF DESIGNING AN INFORMATICS COURSE: HOW TO CREATE THE PERFECT LEARNING SPACE FOR STUDENTS?(IATED, 2023-03); Jancheska, SofijaDesigning an informatics course has become a great challenge. The rapid technological developments coupled with today’s abundance of online learning materials have made it tricky for educators to design effective class curriculums. Our paper will provide educators with the winning formula for students’ perfect learning experience. We aim to inspire educators to leverage modern tools to create engaging and fruitful classes. Our work is a general toolbox which will enable educators to tailor their classes to different areas within the field of informatics. We thus aim to answer the following questions: “How to prepare well for an informatics class?”, “How to conduct an informatics class successfully?” and “How to evaluate a properly conducted informatics lesson?”. Our paper will familiarize educators with the whole cycle of designing a successful informatics course. We will specifically target the microlevels of a course, a lesson. We will discuss different aspects of every lesson: suitable methods for organization and planning of a lesson, structural elements of a lesson, types of lessons, didactic goals, appropriate selection of teaching material, active methods for teaching and learning, manners for fostering interaction between students and teachers and among students themselves, approaches to fully engage students, lesson delivery models, individualized techniques to target the learning goals of each student, assessment and evaluation of students. We will also take into consideration teachers’ preparedness including their expertise of the material, and their didactical, technical and psychological readiness. The quality of an informatics course lies in the relationship between educators and their students. It is a complex dynamic between teachers’ goals, plans, means, methods and organization, and students’ expectations, abilities, and motivation. Our paper reaches an equilibrium point between all the building blocks of the teaching process of the educator and learning experience of the students. Our focus is put on the teacher and their teaching methods and tactics. We perceive the teachers as pilots leading a full airplane, a class of students. They have a palette of gadgets available, and they need to make a specific choice for the plane to conformably fly and to finally land on the exact coordinates of the intended location. In our case, the fancy gadgets are all traditional and modern learning tools available to the teacher and the intended location is the goal of the teacher for the class. How can educators use the tools to meet their didactic goals? When should they use them at what times? What specific tools should they select for special educational tasks? What does this choice depend on? Our paper will take a holistic view of all components of the process of teaching and learning informatics. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, UNVEILING THE NEXT WAVE OF LEARNING: NAVIGATING CHATGPT'S IMPACTFUL APPLICATION IN EDUCATION(IATED, 2024-03) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, UNLOCKING THE FUTURE OF EDUCATION: A COMPREHENSIVE ANALYSIS OF KEY DOCUMENTS SHAPING ARTIFICIAL INTELLIGENCE IN EDUCATION(IATED, 2024-03); Jancheska, SofijaWith the boom of Artificial Intelligence (AI) in the past few years, there has been a notable upswing in the generation of resources dedicated to this field. Prominent international and supranational entities and initiatives, including UNESCO, European Commission, European Parliament, OECD, EdTech, AI4K12 and International Society for Technology in Education, have produced a significant number of documents in the field. This paper provides a comprehensive analysis of carefully selected documents within the field of AI, specifically focusing on its applications in education. The goal is to provide a nuanced exploration encompassing professional expertise, comprehensive guidelines, and practical recommendations to enhance our understanding of AI. Through this detailed study of documents, our objective is to offer valuable insights for the future potential of AI in education. Our paper emphasizes ethical considerations, best practices, and guidelines, useful to educators, policymakers, and stakeholders who seek to integrate AI technologies responsibly and effectively into educational settings. Our paper also aims to promote responsible and beneficial integration of AI in education, with the ultimate goal of enriching learning experiences for students. With our carefully selected documents, we address various aspects, including the promotion of gender equality and human rights, conducting privacy impact assessments, ensuring responsible use of AI in accordance with privacy regulations, and identifying the essential knowledge and skills that students should acquire in the realm of AI. We explore how to equip students with a foundational understanding of AI concepts, ethical considerations, and practical skills, positioning them as informed and responsible users of AI technologies in the future. The document selection spans topics related to integrating AI in education, encompassing challenges, opportunities, standards, data privacy and security considerations, as well as addressing biases and ethical concerns. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Identification of HIV Inhibitors Using Graph Neural Networks(IEEE, 2024-05-20); Graph neural networks (GNN), primed to extract knowledge and discover patterns in graph-structured data, have received particularly increased attention in biomedical research. By integrating information from a variety of biomedical knowledge repositories they offer a fast and efficient computational alternative approach to the costly and time-consuming process of drug development and research. The core contributions of this paper include the design and empirical evaluation of several GNN-based models for the identification of potential HIV (Human Immunodeficiency Virus) inhibitors. In particular, the predictive power of model variants based on Graph Attention Network (GAT), Graph Isomorphism Network (GIN), and Continuous Kernel-Based Graph Convolutional Network, specifically developed to handle molecular data, have been investigated. To assess the effectiveness of the proposed models, the Stanford open graph benchmark dataset for molecular data ogbg-molhiv was used. Furthermore, two types of molecular fingerprints have been proposed to augment the molecular representation in the proposed graph neural models, leading to better performance standing compared to the original models. The paper provides a detailed description of the proposed models for identifying HIV inhibitors, followed by a comparative analysis of the experimental results focusing on a discussion of the challenges we face and future research directions that could be investigated.