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

Settings

Search Results

Now showing 1 - 10 of 2096
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Benchmarking Sentence Encoders in Associating Indicators With Sustainable Development Goals and Targets
    (Institute of Electrical and Electronics Engineers (IEEE), 2025)
    Gjorgjevikj, Ana
    ;
    ;
    ;
    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...
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Evaluating Trustworthiness in AI: Risks, Metrics, and Applications Across Industries
    (MDPI AG, 2025-07-04)
    Nastoska, Aleksandra
    ;
    Jancheska, Bojana
    ;
    Rizinski, Maryan
    ;
    Ensuring the trustworthiness of artificial intelligence (AI) systems is critical as they become increasingly integrated into domains like healthcare, finance, and public administration. This paper explores frameworks and metrics for evaluating AI trustworthiness, focusing on key principles such as fairness, transparency, privacy, and security. This study is guided by two central questions: how can trust in AI systems be systematically measured across the AI lifecycle, and what are the trade-offs involved when optimizing for different trustworthiness dimensions? By examining frameworks such as the NIST AI Risk Management Framework (AI RMF), the AI Trust Framework and Maturity Model (AI-TMM), and ISO/IEC standards, this study bridges theoretical insights with practical applications. We identify major risks across the AI lifecycle stages and outline various metrics to address challenges in system reliability, bias mitigation, and model explainability. This study includes a comparative analysis of existing standards and their application across industries to illustrate their effectiveness. Real-world case studies, including applications in healthcare, financial services, and autonomous systems, demonstrate approaches to applying trust metrics. The findings reveal that achieving trustworthiness involves navigating trade-offs between competing metrics, such as fairness versus efficiency or privacy versus transparency, and emphasizes the importance of interdisciplinary collaboration for robust AI governance. Emerging trends suggest the need for adaptive frameworks for AI trustworthiness that evolve alongside advancements in AI technologies. This paper contributes to the field by proposing a comprehensive review of existing frameworks with guidelines for building resilient, ethical, and transparent AI systems, ensuring their alignment with regulatory requirements and societal expectations.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Multiword Discourse Markers Across Languages: A Linguistic and Computational Perspective
    (Wiley, 2025-04-22)
    Apostol, Elena‐Simona
    ;
    Truică, Ciprian‐Octavian
    ;
    Damova, Mariana
    ;
    Silvano, Purificação
    ;
    Oleškeviciene, Giedre Valunaite
    Discourse markers (DMs) are linguistic expressions that convey different semantic and pragmatic values, managing and organizing the structure of spoken and written discourses. They can be either single-word or multiword expressions (MWE), made up of conjunctions, adverbs, and prepositional phrases. Although DMs are the focus of many studies, some questions regarding the interoperability of taxonomies and automatic identification and classification require further research. We aim to tackle these issues by offering a critical analysis and discussing the constitution of a multilingual corpus in 10 languages, i.e., English, Lithuanian, Bulgarian, German, Macedonian, Romanian, Hebrew, Polish, European Portuguese, and Italian. The novel two-level annotation approach is based on (i) signaling the existence or non-existence of DMs in a given text, and (ii) applying the ISO-24617 standard to annotate the DMs’ discourse relation and communicative function in the corpora. Additionally, we introduce prediction models for detecting the presence of DMs within a text.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Pressure Related Ocular Parameters in Caucasian Patients with Primary Open-Angle Glaucoma
    (Savvy Science Publisher, 2021-06-02)
    Galina, Dimitrova
    ;
    Antonela, Ljubic
    ;
    ;
    Keti, Tagasovska
    ;
    Urosh, Tomasevic
    Objectives: To investigate pressure related ocular parameters (intraocular pressure (IOP), estimated trans-lamina cribrosa pressure difference (TLPD) and ocular perfusion pressure (OPP) in Caucasian patients with primary open angle glaucoma (POAG) and control subjects. Methods: This is an observational cross-section study that included 57 subjects (27 patients with open-angle glaucoma and 30 healthy control subjects). All subjects underwent ophthalmic and systemic measurements in order to evaluate pressure related ocular parameters – IOP (mmHg), OPP (mmHg), and TLPD (mmHg) based on established formulas. The differences in the IOP, OPP and TLPD values between patients with POAG and control subjects were evaluated. Results: Intraocular pressure and TLPD were significantly higher in patients with glaucoma (mean IOP= 18.93 ± 4.53 mmHg; TLPD= 9.47 ± 5.02 mmHg), than in control subjects (IOP= 16.47 ± 2.60 mmHg; TLPD= 6.82 ± 3.60 mmHg) (p=0.017 and p=0.025 respectively). In univariate logistic progression, IOP and TLPD were significant predictors for POAG. Conclusion: Our results suggest that in addition to IOP, TLPD is also significantly higher in Caucasian patients with POAG than in control subjects and both parameters are significant predictors of POAG. This suggests that TLPD may have a role in the pathogenesis of POAG.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Corrigendum on “On a general decay stability of stochastic Cohen-Grossberg neural networks with time-varying delays” [Applied Mathematics and Computation 219 (2012) 2289–2302]
    (Elsevier BV, 2013-01)
    ;
    Janković, Svetlana
    In Lemma 2, as well as in Theorems 1 and 3 which proofs are based on Lemma 2, it is necessary to suppose for δ< 1 that functions a and b from C ([t 0,∞); R n) are increasing and decreasing, respectively, and that γ∗= γ (t 0). The proof of Lemma 2 in the paper holds only for δ⩾ 1 and must be similarly completed for δ< 1: since y (t)< kz (t) on [t 0, t 1) and y (t 1)= kz (t 1), k= const> 1, it follows straightforwardly that‖ y (t 1)‖< kz (t 1) δ γ∗ and D+(y (t 1)− kz (t 1))< 0, which completes the proof.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    On some stability problems of impulsive stochastic Cohen–Grossberg neural networks with mixed time delays
    (Elsevier BV, 2014-07)
    ;
    Janković, Svetlana
    This paper covers the topic of both the pth moment ( ) and almost sure stability of impulsive stochastic Cohen–Grossberg neural networks with mixed time delays. We partially use a known result on exponential stability of impulsive stochastic functional differential systems, based on the Razumikhin type technique, and extend it to the case of stochastic neural networks using the Lyapunov function method and a Gronwall type inequality. Additionally, we consider the stability with respect to a general decay function which includes exponential, but also more general lower rate decay functions as the polynomial and the logarithmic ones. This fact gives us the opportunity to study general decay almost sure stability, even when the exponential one cannot be discussed. Suitable examples which support the theory are also presented.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent 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)
    Rizinski, Maryan
    ;
    Artificial intelligence (AI) is reshaping financial systems and services, as intelligent AI agents increasingly form the foundation of autonomous, goal-driven systems capable of reasoning, learning, and action. This review synthesizes recent research and developments in the application of AI agents across core financial domains. Specifically, it covers the deployment of agent-based AI in algorithmic trading, fraud detection, credit risk assessment, roboadvisory, and regulatory compliance (RegTech).The review focuses on advanced agent-based methodologies, including reinforcement learning, multi-agent systems, and autonomous decision-making frameworks, particularly those leveraging large language models (LLMs), contrasting these with traditional AI or purely statistical models. Our primary goals are to consolidate current knowledge, identify significant trends and architectural approaches, review the practical efficiency and impact of current applications, and delineate key challenges and promising future research directions. The increasing sophistication of AI agents offers unprecedented opportunities for innovation in finance, yet presents complex technical, ethical, and regulatory challenges that demand careful consideration and proactive strategies. This review aims to provide a comprehensive understanding of this rapidly evolving landscape, highlighting the role of agent-based AI in the ongoing transformation of the financial industry, and is intended to serve financial institutions, regulators, investors, analysts, researchers, and other key stakeholders in the financial ecosystem.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Election candidates fuzzy multi-agent recommender system
    (SAGE Publications, 2013-01)
    ;
    Dukovska, Snezana Cerepnalkovska
    In this paper we propose fuzzy multi-agent recommender system for candidates in state elections that is intended to serve to voters as a filter for excess of information on Internet and other media on their election candidates. The recommender system we propose should guide voters to the candidates that suit their preferences, and help them make a choice of a representative by accessing relevant information. For this system we have enrolled computing with words (CW) methodology which main concepts are graduation (linguistic variables) and granulation (a fuzzy set of points drawn together by similarity). Our proposed recommender system is appropriate for application in developing countries, because of its simplicity and its low cost. It can also serve as foundation for future development and sophistication, taking into consideration both technical and political aspects.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Automatic Recognition of Emotions from Speech
    (Digital Information Research Foundation, 2019-12-01)
    Gjoreski, Martin
    ;
    ;
    This paper presents an approach to recognition of human emotions from speech. Seven emotions are recognized: anger, fear, sadness, happiness, boredom, disgust and neutral. The approach is applied on a speech database, which consists of simulated and annotated utterances. First, numerical features are extracted from the sound database by using audio feature extractor. Next, the extracted features are standardized. Then, feature selection methods are used to select the most relevant features. Finally, a classification model is trained to recognize the emotions. Three classification algorithms are tested, with SVM yielding the highest accuracy of 89% and 82% using the 10 fold cross-validation and Leave-OneSpeaker-Out techniques, respectively. “Sadness” is the emotion which is recognized with highest accuracy.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Online marketing — The case of Macedonia
    (IEEE, 2016-10)
    Varnalieva, Jasminka
    ;
    Online marketing is identified as one of the key drivers of European digital economy. Recent studies have shown that advertising is not adding direct value for the advertisers only, but it creates significant additional indirect value and jobs while boosting innovation and creativity. In Europe online advertising has grown dramatically. It is expected that online advertising revenues will surpass television advertising in 2016. Online marketing in Macedonia is still in its nascent stage. It significantly lags behind countries in the region and far behind the developed countries in the European Union at all possible parameters. Online marketing ad spend in Macedonia is still very low. It is estimated to be 3% to 4% of total ad spending. The reasons why Macedonia's online marketing use is still very low, in spite of the relatively high level of Internet penetration and solid infrastructure, are numerous and multifaceted: distorted market forces, lack of official independent company that measures internet traffic, lack of knowledge on online marketing of Macedonian companies, legal framework etc. Policy makers in Macedonia could address the most important obstacles to increased use of online marketing by designing and implementing specific policy instruments and carrying out existing strategies in this area.