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

Subject: search.filters.subject.LLMs

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Comparison of GEC Tools for Grammatical Error Correction in English
    (IEEE, 2025-06-02)
    Virtanen, Johanna
    ;
    Using the Building Educational Application (BEA) benchmark11https://codalab.lisn.upsaclay.fr/competitions/4057, this study compares the capabilities of Google Gemini22https://gemini.google.com/, ChatGPT33https://openai.com/chatgpt, DeepSeek44https://www.deepseek.com/en, and the builtin grammar checkers in Google Docs and Microsoft Word for grammatical error correction (GEC). These tools correct a variety of errors, some of which overlap. Based on the BEA benchmark evaluation results, Google Gemini and the Google Docs grammar checker achieve the best F0.5 scores of 60.2 and 65.86, respectively. Google Docs grammar checker is easy to use and, according to this evaluation, performs well, thus proving to be a viable option for GEC. However, standard grammar checkers are not typically designed for rewriting text to the same extent as GenAI tools; hence, it may be advisable especially for non-native speakers to combine traditional and GenAI grammar correction for the best possible results. However, it is necessary to check the grammatical corrections of LLMs, since generative AI tools suffer from hallucinations, which refers to their tendency to generate information that can be factually incorrect [1].
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    A Multimodal Vision: Language Framework for Intelligent Detection and Semantic Interpretation of Urban Waste
    (MDPI AG, 2026-04-03)
    Jonuzi, Verda Misimi
    ;
    Urban waste management remains a significant challenge for achieving environmental sustainability and advancing smart city infrastructures. This study proposes a multimodal vision–language framework that integrates real-time object detection with automated semantic interpretation and structured semantic analysis for intelligent urban waste monitoring. A custom dataset including 2247 manually annotated images was constructed from publicly available sources (TrashNet and TACO), enabling robust multi-class detection across six waste categories. Two state-of-the-art object detection models, YOLOv8m and YOLOv10m, were trained and evaluated using a fixed 70/15/15 train–validation–test split. Under this configuration, YOLOv8m achieved a mAP@50 of 90.5% and a mAP@50–95 of 87.1%, slightly outperforming YOLOv10m (89.5% and 86.0%, respectively). Moreover, YOLOv8m demonstrated superior inference efficiency, reaching 120 FPS compared to 105 FPS for YOLOv10m. To obtain a more reliable estimate of performance stability across data partitions, stratified 5-Fold Cross-Validation was conducted. YOLOv8m achieved an average Precision of 0.9324 and an average mAP@50–95 of 0.9315 ± 0.0575 across folds, suggesting generally stable performance across data partitions, while also revealing variability associated with dataset heterogeneity. Beyond object detection, the framework integrates MiniGPT-4 to generate context-aware textual descriptions of detected waste items, thereby enhancing semantic interpretability and user engagement. Furthermore, GPT-5 Vision is incorporated as a structured auxiliary semantic classification and category-suggestion module that analyzes object crops and multi-class scenes, producing constrained JSON-formatted outputs that include category labels, concise descriptions, and recyclability indicators. Overall, the proposed YOLOv8–MiniGPT-4–GPT-5 Vision pipeline shows that combining accurate real-time detection with multimodal semantic reasoning can improve interpretability and support interactive, semantically enriched waste analysis in smart-city and environmental monitoring scenarios.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    ReAct-ExtrAct: A Tool for Source-Grounded Automated Data Extraction in Systematic Reviews
    (IEEE, 2025-12-15)
    Krawczyk, Sebastian
    ;
    Jemioło, Paweł
    ;
    Karkowski, Jan
    ;
    ;
    Manual information extraction for systematic reviews (SRs) is a major, time-consuming bottleneck that limits the efficiency and reliability of evidence synthesis. We present REACT-ExtrAct, a retrieval-augmented, agent-based framework that combines Small Language Models with heuristicguided reasoning to automate data extraction while ensuring source transparency. Evaluated on two published systematic reviews, our system outperformed Naive RAG and Iter-RetGen baselines in factual accuracy, completeness, and traceability. By enabling lightweight, local deployment, React-ExtrAct offers a trustworthy and sustainable alternative to Large Language Model pipelines for SR automation.