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
39 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, EXPLORING COMPUTATIONAL THINKING IN EDUCATION: DEFINITIONS, PEDAGOGIES, AND INTEGRATION APPROACHES(IATED, 2024-11); ; Nowadays, many academics agree that one of the essential 21st-century skills is computational thinking (CT). This study explores the diverse meanings of CT and their evolution throughout the years. It examines the complex connections between digital literacy/competence, programming, and CT, and clarifies their differences. The fundamental ideas and abilities of CT—abstraction, algorithmic reasoning, automation, decomposition, debugging, pattern recognition, and generalization—will be at the center of our discussion. We claim that CT serves as a catalyst for developing students' critical thinking and problem-solving skills, emphasizing its importance in education. Our paper evaluates the necessity of incorporating CT into curricula while discussing how it might promote economic growth. It investigates the best pedagogical approaches to support CT and looks into ways to incorporate it easily into current curriculum. Additionally, it looks into how dependent CT is on technology and how students' access to it affects CT-oriented education. A comprehensive review of relevant studies will be conducted, examining various methods of implementing and using CT in mandatory education worldwide. Finally, three primary approaches to integrating CT skills in compulsory education curricula will be examined: as a cross-curricular topic, as a standalone subject, and by integration within other subjects. Real-world examples of CT integration in compulsory education across various countries are provided, offering insights into successful implementation strategies. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Data-Driven Adaptive Course Framework - Case Study: Impact on Success and Engagement(MDPI, 2025-07-19) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Gender Impact on Performance in Adaptive Learning Settings: Insights from a Four-Year University Study(MDPI, 2025-06-16) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A novel methodological approach for learning cybersecurity topics in primary schools(Springer Science and Business Media LLC, 2024-08-24); Trajkovik, Vladimir - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Generative AI for Customizable Learning Experiences(MDPI, 2024-04) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Using Peer-Learning and Game-Based Instruction for Achieving Long-Lasting Knowledge of Cybersecurity in Primary Schools(Institute of Electrical and Electronics Engineers (IEEE), 2025) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Blood Oxygen Saturation Estimation Using PPG Signals from the MIMIC-III Database(Springer, Cham, 2025-04-23); Madevska Bogdanova, AnaPhotoplethysmogram (PPG) signals are pivotal in cardiovascular monitoring, offering real-time insights into heart rate and oxygen saturation (SpO2). This study explores the creation of deep learning and machine learning models - specifically Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, Recurrent Neural Networks (RNNs), and Random Forest Regressors (RFRs)-to estimate SpO2 levels from single-channel PPG data. Another point is developing algorithms for using the data sourced from the PhysioNet MIMIC-III database. The patients used for training and testing are distinct, ensuring no overlap between the datasets and enabling rigorous model evaluation. A comprehensive analyses reveal that LSTM-based model achieve significant accuracy in SpO2 estimation, with R-squared value reaching up to 0.59. Specifically, the LSTM model demonstrated an MAE of 1.26, MSE of 3.11 and RMSE of 1.76. These results demonstrate the potential of machine learning techniques in advancing clinical monitoring and decision-making processes within critical care environments, thereby enhancing patient care outcomes. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A narrative review of e-health systems' evolution – evidence from a regional study(Emerald Publishing Limited, 2024-05-29); ; ; Chagoroska, ZaklinaPurpose The growing implementation of electronic health (e-health) systems has raised the importance of analyzing how these systems have been implemented in diverse regions. By employing a contextual sensitive approach and social mechanism theory, this study aims to better understand the reasons for the success and failure of e-health initiatives in the ex-Yugoslav region and derive useful insights for policymakers. Design/methodology/approach We employ a narrative review process grounded in the social mechanism theory, extended with field experts’ review, to acquire state-of-the-art information. Findings Findings indicate that different e-health systems coexist and evolve in different contexts in different countries, with varying levels of success. The contextual differences shape the broader environment, affecting the level of preparedness and capability for e-health implementation. Top-down approaches dominate e-health implementation in most countries when it comes to design process features, and more developed countries do not rely on strong social mechanisms for implementing e-health due to the openness of their culture towards e-health innovations. Practical implications Analyzing the milestones, challenges and functionalities of e-health systems in the region of interest can assist policymakers, academics and practitioners in making informed decisions and recommendations to enhance future e-health implementation. Originality/value No known studies evaluated e-health initiatives in the former ex-Yugoslav countries holistically and evolutionarily in the form of a comprehensive regional study. Further, our research endeavor is contextually specific since the health systems of these countries in the past were tied together under the federative umbrella health system and then diverged in terms of e-health development. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Prediction of Oxygen Saturation from Graphene Respiratory Signals with PPG Trained DNN(SCITEPRESS - Science and Technology Publications, 2024); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Parallelizing file-type conversion for financial analysis(IEEE, 2023-11); Data analysis has gained significant traction, particularly in the era of artificial intelligence, offering novel approaches for financial data analysis. However, a data storage challenge arises prior to analysis. Financial data is commonly stored in the XLSX format, whereas for faster analysis and reduced server storage, the preferred format is CSV. This paper investigates the acceleration of XLSX to CSV conversion. The XLSX file’s main content is represented as a tree structure in XML format. Leveraging the independent nature of rows and files, we propose two methods for parallelizing the conversion process: single file parallelization and simultaneous parallel conversion of multiple files. Our results demonstrate the effectiveness of parallelization, resulting in reduced workflow waiting times.