Publication detail

Machine Learning-Based Semantic Analysis of Scientific Publications for Knowledge Extraction in Safety-Critical Domains

NOSOV, P. MELNYK, O. MALAKSIANO, M. MAMENKO, P. ONYSHKO, D. FOMIN, O. PÍŠTĚK, V. KUČERA, P.

English title

Machine Learning-Based Semantic Analysis of Scientific Publications for Knowledge Extraction in Safety-Critical Domains

Type

WoS Article

Language

en

Original abstract

This article presents the development of a modular software suite for automated analysis of scientific publications in PDF format. The system integrates vectorization, clustering, topic modelling, dimensionality reduction, and fuzzy logic to combine both formal (vector-based) and semantic (topic-based) approaches. Interactive 3D visualization supports intuitive exploration of thematic clusters, allowing users to highlight relevant documents and adjust analytical parameters. Validation on a maritime safety case study confirmed the system’s ability to process large publication collections, identify relevant sources, and reveal underlying knowledge structures. Compared to established frameworks such as PRISMA or Scopus/WoS Analytics, the proposed tool operates directly on full-text content, provides deeper thematic classification, and does not require subscription-based databases. The study also addresses the limitations arising from data bias and reproducibility issues in the semantic interpretability of safety-critical decision-making systems. The approach offers practical value for organizations in safety-critical domains—including transportation, energy, cybersecurity, and human–machine interaction—where rapid access to thematically related research is essential.

Keywords in English

intelligent data analysis; artificial intelligence (AI); AI-support; clustering; topic modelling; fuzzy logic; interactive visualization; human factor; decision-support systems; safety-critical systems; transport automation; cybersecurity; human–machine interaction; maritime sector; shipping safety; analytics; semantic classification

Released

2025-11-24

Volume

7

Number

4

Pages from–to

1–21

Pages count

21

BIBTEX


@article{BUT199706,
  author="{} and Oleksiy {Melnyk} and  {} and  {} and  {} and Oleksij {Fomin} and Václav {Píštěk} and Pavel {Kučera}",
  title="Machine Learning-Based Semantic Analysis of Scientific Publications for Knowledge Extraction in Safety-Critical Domains",
  journal="Machine Learning and Knowledge Extraction",
  year="2025",
  volume="7",
  number="4",
  pages="1--21",
  doi="10.3390/make7040150",
  url="https://www.mdpi.com/2504-4990/7/4/150"
}