EPAM School of Digital Technologies (capstones)

Permanent URI for this collection

https://er.auk.edu.ua/handle/234907866/4

Browse

Browsing EPAM School of Digital Technologies (capstones) by Subject "Artificial Intelligence"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    AUTOMATED QUIZ CREATION USING CHATGPT WITH INTEGRATION INTO THE CANVAS LMS
    (Manuscript, 2025-06-09) Lazebnyi, Vitalii
    This study explores the automation of quiz generation using Large Language Models (LLMs) like GPT-4, and their integration into Learning Management Systems (LMS) Canvas. It discusses the potential of LLMs to transform assessment creation by generating diverse question types aligned with learning objectives. The research also addresses ethical considerations, including data privacy and algorithmic bias, and highlights the importance of prompt engineering for effective AI-human interaction. The findings suggest that LLMs can significantly streamline quiz creation, saving educators time and enhancing student learning experiences while emphasizing the need for ongoing refinement and ethical oversight.
  • Thumbnail Image
    Item
    TACTICAL COMBAT CASUALTY CARE (TCCC) AI DECISION SUPPORT SYSTEM
    (Manuscript, 2026) Piltiai, Roman
    Tactical Combat Casualty Care (TCCC) serves as the definitive standard for battlefield trauma management, yet the application of these protocols under high-stress combat conditions remains a significant challenge. Cognitive overload and lack of immediate expert guidance can lead to critical errors in pre-hospital care. This capstone project addresses this gap by engineering an Intelligent TCCC Tutor and Decision Support System tailored for dynamic environments. The proposed solution leverages a cloud-native, serverless architecture on Amazon Web Services (AWS) to ensure high availability, scalability, and low-latency performance. By integrating Generative AI and Large Language Models (LLMs), the system interprets complex user inputs and provides real-time, context-aware guidance aligned with the MARCH algorithm. The application was designed using modern software engineering principles, prioritizing modularity and enterprise-scale security standards. The resulting system demonstrates how advanced cloud computing and artificial intelligence can be effectively operationalized to enhance medical training and decision-making. This project not only delivers a functional prototype for tactical education but also establishes a reference architecture for future AI-driven systems in high-stakes domains.