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
1992 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Smart home environment aimed for people with physical disabilities(IEEE, 2016-09); ; ; In this paper we analyze the possibilities and methods for using assistive technologies with focus on the people that cannot regularly control different aspects of their home environments. This paper presents a smart home environment platform for assisting people with physical disabilities. Four modules are included in the platform that enable end users of the system to complete everyday activities without additional assistance. 3D cameras are used to capture facial landmarks and expressions in order to map the user intent into a specific action in the smart home environment. Actuators are triggered to complete actions based on the detected and mapped facial expressions. The system is targeted at users that suffer from motor disabilities and are unable to use their hands and feet to control the surrounding environment. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Animation Visualization of a Mobile Radiation Measurement System for Nuclear Waste Containers Using Autodesk Maya(Walter de Gruyter GmbH, 2025-03-01); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Methodology for food prices forecasting(IEEE, 2023-12-15) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Assessing the Environmental Impact of Plant-Based Diets: A Comprehensive Analysis(IEEE, 2023-12-15) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Learning Robust Food Ontology Alignment(IEEE, 2022-12-17); ; 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 yourconsent settings
Item type:Publication, Large language models in food and nutrition science: Opportunities, challenges, and the case of FoodyLLM(Elsevier BV, 2026); Drole, JanBackground 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 yourconsent settings
Item type:Publication, Preserving Macedonian Culinary Heritage: Fine-Tuning a Large Language Model for Recipe Generation in a Low-Resource Language(IEEE, 2025-12-08); 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 yourconsent settings
Item type:Publication, Fusing Semantic, Lexical, and Domain Perspectives for Recipe Similarity Estimation(arXiv, 2026) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Using P-TOSCA to prevent vendor lock-in for cloud-based laboratories(IEEE, 2015-11); - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Software design patterns to develop an interoperable cloud environment(IEEE, 2015-11); ; Software development has provided methods and tools to facilitate the development process, resulting in scalable, efficient, testable, readable and bug-free code. This endeavor has resulted in a multitude of products, many of them nowadays known as good practices, specialized environments, improved compilers, as well as software design patterns. Software design patterns are a tested methodology, and are most often language neutral. In this paper, we identify the problem of the heterogeneous cloud market, as well as the various APIs per a single cloud. By using a set of software design patterns, we developed a pilot software component that unifies the APIs of heterogeneous clouds. It offers an interface that would greatly simplify the development process of cloud based applications. The pilot adapter is developed for two open source clouds - Eucalyptus and OpenStack, but the usage of software design patterns allows an easy enhancement for all other clouds that have APIs for cloud management, either open source or commercial.