Перегляд за Автор "Strashnoy, Leonard"

Зараз показуємо 1 - 3 з 3
  • Ескіз
    ДокументВідкритий доступ
    Cybersecurity in AI-Driven Casual Network Formation
    (Igor Sikorsky Kyiv Polytechnic Institute, 2023) Lande, Dmytro; Feher, Anatolii; Strashnoy, Leonard
    The paper describes a methodology for forming thematic causal networks using artificial intelligence and automating the processes of their visualization. The presented methodology is considered on the example of ChatGPT, as an artificial intelligence for analyzing the space of texts and building concepts of causal relationships, and their further visualization is demonstrated on the example of Gephi and CSV2Graph programs. The effectiveness of the disaggregated method in relation to traditional methods for solving such problems is shown by integrating the means of intelligent text analytics and graphical network analysis on the example of the problem of data leakage in information systems and a selection of news clippings on the selected cybersecurity topic.
  • Ескіз
    ДокументВідкритий доступ
    GPT Semantic Networking: A Dream of the Semantic Web – The Time is Now
    (Engineering Ltd, 2023) Lande, Dmytro; Strashnoy, Leonard
    The book presents research and practical implementations related to natural language processing (NLP) technologies based on the concept of artificial intelligence, generative AI, and the concept of Complex Networks aimed at creating Semantic Networks. The main principles of NLP, training models on large volumes of text data, new universal and multi-purpose language processing systems are presented. It is shown how the combination of NLP and Semantic Networks technologies opens up new horizons for text analysis, context understanding, the formation of domain models, causal networks, etc. This book presents methods for creating Semantic Networks based on prompt engineering. Practices are presented that will help build semantic networks capable of solving complex problems and making revolutionary changes in the analytical activity. The publication is intended for those who are going to use large language models for the construction and analysis of semantic networks in order to solve applied problems, in particular, in the field of decision making.
  • Ескіз
    ДокументВідкритий доступ
    Methodology of a Swarm of Virtual Experts for Evaluating the Weight of Connections in Networks
    (Igor Sikorsky Kyiv Polytechnic Institute, 2024) Lande, Dmytro; Alekseichuk, Lesya; Svoboda, Igor; Strashnoy, Leonard
    This article proposes a new methodology —the Swarm of Virtual Experts (SVE) —for evaluating the weights of connections in complex networks, based on a holistic approach. Traditional methods relying on expert assessments often face issues of subjectivity and limited resources. This paper introduces the methodology of the Swarm of Virtual Experts. The focus is on integrating large language models (LLMs) into the decision-making process, where each model acts as a virtual expert with specific tasks and functions. The core idea is to combine diverse assessments from different LLMs using mathematical tools, including incidence matrices, weighted averages, and aggregation methods. The methodology addresses the issue of fragmented results caused by the probabilistic nature of LLMs and enhances analytical efficiencythrough role assignment to agents, aggregation mechanisms, and quality evaluation of outcomes. The application of this technique is illustrated with examples, particularly in the field of cybersecurity.Special attention is given to holistic analysis, which provides a comprehensive approach to evaluating the weights of connections between nodes in networks.