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

Search Results

Now showing 1 - 10 of 146

Some of the metrics are blocked by your
consent settings
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...
Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
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.
Some of the metrics are blocked by your
consent settings
Methodology for food prices forecasting
(IEEE, 2023-12-15)
Peshevski, Dimitar
;
Todorovska, Ana
;
Trajkovikj, Filip
;
Hristov, Nikola
;
Trajanoska, Milena
Fluctuations in food prices play a pivotal role in maintaining economic equilibrium and influencing the very fabric of our everyday lives. This paper presents a comprehensive framework for modeling and analyzing food price trends in 12 select European countries, spanning from January 2013 to January 2023, utilizing advanced state-of-the-art Machine Learning techniques. To achieve this objective, historical price data and technical indicators are incorporated into the proposed XGBoost model alongside a baseline model. The model results are assessed using various measures, and a benchmark is established. Notably, the average achieved R2 for predicting food prices within the time frame from January 2020 to January 2022 is 0.85 and 0.64 from January 2021 to January 2023. The findings reveal the efficacy of the proposed model, providing valuable insights into food price forecasting model interpretability and laying the groundwork for further research, including exploration into areas such as food fraud, food sustainability, and other pertinent topics in food economics.
Some of the metrics are blocked by your
consent settings
Assessing the Environmental Impact of Plant-Based Diets: A Comprehensive Analysis
(IEEE, 2023-12-15)
Golubova, Blagica
;
Fetaji, Fjola
;
Dobreva, Jovana
;
Trajanoska, Milena
;
Todorovska, Ana
This study examines a pressing issue related to the loss of natural resources and biodiversity driven by the high reliance of food production on ecosystem management services. The well-being of all living species is impacted by this depletion, which represents a huge obstacle in our collaborative effort to improve environmental quality. Our research aims to explain the environmental effects of food production and raise awareness of pollution levels at various phases of this process. This research combines statistical analysis and visualization to show considerable differences in CO2eq emissions among 43 different food products. In particular, it highlights how animal-based diets have much higher emissions than their plant-based equivalents. Subsequently, the products were divided into three distinct groups: plant-based, animal-based, and refined oils and sugars. This demonstrated how well an unsupervised clustering technique separates food products according to their CO2eq emissions. Where, these findings highlight how excellent plant-based products are for the environment. The main goal of this study goes beyond simple observation since it aims to provide an example of how a comprehensive, health-conscious eating habit may live with a stable ecosystem and clean surroundings. Particularly, reductions in cane sugar production yield substantial reductions in CO2 emissions, whereas even marginal decreases in meat production result in a significant reduction in emissions. These results highlight the potential for sustainable eating habits to aid in environmental conservation and deepen our understanding of the complex interactions between dietary decisions and environmental effects.
Some of the metrics are blocked by your
consent settings
Learning Robust Food Ontology Alignment
(IEEE, 2022-12-17)
Mijalcheva, Viktorija
;
Davcheva, Ana
;
;
;
In today’s knowledge society, large number of information systems use many different individual schemes to represent data. Ontologies are a promising approach for formal knowledge representation and their number is growing rapidly. The semantic linking of these ontologies is a necessary prerequisite for establishing interoperability between the large number of services that structure the data with these ontologies. Consequently, the alignment of ontologies becomes a central issue when building a worldwide Semantic Web. There is a need to develop automatic or at least semi-automatic techniques to reduce the burden of manually creating and maintaining alignments. Ontologies are seen as a solution to data heterogeneity on the Web. However, the available ontologies are themselves a source of heterogeneity. On the Web, there are multiple ontologies that refer to the same domain, and with that comes the challenge of a given graph-based system using multiple ontologies whose taxonomy is different, but the semantics are the same. This can be overcome by aligning the ontologies or by finding the correspondence between their components.In this paper, we propose a method for indexing ontologies as a support to a solution for ontology alignment based on a neural network. In this process, for each semantic resource we combine the graph based representations from the RDF2vec model, together with the text representation from the BERT model in order to capture the semantic and structural features. This methodology is evaluated using the FoodOn and OntoFood ontologies, based on the Food Onto Map alignment dataset, which contains 155 unique and validly aligned resources. Using these limited resources, we managed to obtain accuracy of 74% and F1 score of 75% on the test set, which is a promising result that can be further improved in future. Furthermore, the methodology presented in this paper is both robust and ontology-agnostic. It can be applied to any ontology, regardless of the d...
Some of the metrics are blocked by your
consent settings
Large language models in food and nutrition science: Opportunities, challenges, and the case of FoodyLLM
(Elsevier BV, 2026)
Gjorgjevikj, Ana
;
Martinc, Matej
;
Cenikj, Gjorgjina
;
;
Drole, Jan
Background Reliable nutrient profiling and semantic interoperability are essential for scalable dietary assessment, food labeling (e.g., traffic-light schemes), and FAIR integration of food composition and consumption data. However, general-purpose large language models (LLMs) are not systematically exposed to structured recipe–nutrition mappings and food ontologies, limiting their accuracy and trustworthiness in food and nutrition tasks. Scope and approach We review recent LLM advances in life sciences and healthcare and analyze the gap in food and nutrition applications. To address this gap, we introduce FoodyLLM, a domain-specialized LLM fine-tuned on 225k task-aligned QA pairs for (i) recipe nutrient estimation, (ii) traffic-light classification, and (iii) ontology-based entity linking to support FAIR food data interoperability. We benchmark FoodyLLM against strong general-purpose baselines (e.g., Llama 3 8B, Gemini 2.0) under zero-/few-shot prompting across five evaluation folds. Key findings Across all tasks, FoodyLLM substantially outperforms general-purpose LLMs for nutrient estimation across all macronutrients (fat, protein, salt, saturates, sugar), accuracy increases from 0.43 to 0.63 to 0.91–0.97; for traffic-light classification across all nutrients and color categories, macro F1 improves from 0.46 to 0.80 to 0.86–0.97; and for ontology-based food entity linking across FoodOn, SNOMED-CT, and Hansard, macro F1 increases from 0.33 to 0.44 (best general-purpose baseline) to 0.93–0.98 on artificial NEL data, and from 0.24 to 0.51 to 0.67–0.84 on real corpora (CafeteriaSA and CafeteriaFCD). Overall, our results demonstrate the practical value of domain-specialized LLMs in food and nutrition research. They enable automated dietary assessment, large-scale nutritional monitoring, and FAIR data integration, while opening new pathways toward sustainable and personalized nutrition.
Some of the metrics are blocked by your
consent settings
Preserving Macedonian Culinary Heritage: Fine-Tuning a Large Language Model for Recipe Generation in a Low-Resource Language
(IEEE, 2025-12-08)
Peshevski, Dimitar
;
Sasanski, Darko
;
;
We introduce the first fine-tuned large language model for recipe instruction generation in Macedonian. Building on VezilkaLLM-Instruct, a 4-billion parameter model, we fine-tune it using a curated dataset of 36,000 recipes with detailed cooking instructions. Our key contributions include: (1) the development of a domain-adapted language model for a low-resource language; (2) the demonstration that relatively small LLMs can be effectively adapted to specialized culinary tasks; and (3) the proposal of a dual evaluation framework that combines semantic similarity and verb overlap analyses to assess both content generalization and procedural accuracy. Fine-tuning results in a mean cosine similarity of 0.90 and significantly increases the overlap of domain-specific cooking verbs, indicating improved generation quality. These results highlight the potential of targeted fine-tuning approaches for domain-specific applications in underrepresented languages and provide a foundation for further research in computational culinary heritage.
Some of the metrics are blocked by your
consent settings
A comprehensive study of food prices and food fraud in the European Union
(IEEE, 2023-12-15)
Trajkovikj, Filip
;
Todorovska, Ana
;
Peshevski, Dimitar
;
Nakova, Lina
;
Trajanoska, Milena
This research delves into the intricate dynamics of food pricing and fraud within European Union member countries. We analyze the complex interplay between food categories and countries, unraveling unique pricing trends and potential anomalies. By computing inflation-adjusted expected prices and sourcing real prices, we gain a deep understanding of inflation’s impact on actual food costs. Our multi-level analyses, network-based approaches, and cluster maps provide a global perspective, revealing international correlations in food pricing and fraud. The significance of our findings lies in setting the groundwork for understanding food fraud, informing strategies for fraud prevention, consumer protection, and, ultimately, food sustainability. Our work serves as a crucial resource for policymakers, economists, and consumers, emphasizing the importance of data-driven decision-making and transparency in the ever-evolving landscape of the European food market.

Faculty of Computer Science and Engineering

Browse

Filters

Settings

Sort By

Results per page

Search Results