Μεταπτυχιακές διπλωματικές εργασίες - Τεχνητή Νοημοσύνη και Βαθιά Μάθηση: Recent submissions

Now showing items 1-20 of 29

    • Machine learning for animal detection and recognition for European wildlife conservation 

      Παναγιωτόπουλος, Χρήστος (Πανεπιστήμιο Δυτικής Αττικής, 2024-09)
      This Master of Science thesis explores the potential of Computer Vision (CV) for wildlife research and conservation in Europe. I collaborated with Theodoros Kominos, a wildlife researcher who provided me images and video ...

    • Development and evaluation of AI-powered educational assistant 

      Παπάζογλου, Αλέξανδρος (Πανεπιστήμιο Δυτικής Αττικής, 2024-10-09)
      In order to improve student learning in college courses, this thesis investigates the creation and application of J.A.R.V.I.S. (Just An Resourceful Virtual Instructor and Study-aid), an AIpowered instructional assistant. ...

    • Evolutionary image generation with genetic algorithms and deep learning 

      Κωνσταντοπούλου, Δέσποινα (Πανεπιστήμιο Δυτικής Αττικής, 2024-10-11)
      This paper introduces GAGAN, a hybrid model that integrates Generative Adversarial Networks (GANs) with Genetic Algorithms (GA) to improve GAN performance in image generation. Traditional GANs often face challenges such ...

    • Artificial intelligence in medical diagnosis (with emphasis on orthopedics) 

      Σκαλέρης, Σταμάτιος-Μιχαήλ (Πανεπιστήμιο Δυτικής Αττικής, 2024-10-07)
      Early and accurate diagnosis of hip conditions, such as fractures and degenerative diseases, is crucial for ensuring that patients receive appropriate treatment on time. Delayed or incorrect diagnoses can lead to prolonged ...

    • Physics-informed neural networks for data-efficient & accurate learning of physical systems 

      Κουτσιβίτης, Παναγιώτης (Πανεπιστήμιο Δυτικής Αττικής, 2024-10)
      Traditionally, Scientific Computing and Computer Aided Engineering software use numerical solvers for simulating physics-based models. Despite their high accuracy, numerical solvers can become very computationally intensive ...

    • Lightweight model development for arrhythmia detection in wearable devices using deep learning 

      Καραγεωργίου, Στέφανος (Πανεπιστήμιο Δυτικής Αττικής, 2024-10-16)
      Cardiac arrhythmias are a common cause of morbidity and mortality worldwide. The early diagnosis and prompt treatment of cardiac arrhythmias can improve patient outcomes and prevent adverse events such as stroke and sudden ...

    • Autoencoder algorithms for time series anomaly detection 

      Κωνσταντοπούλου, Ευαγγελία (Πανεπιστήμιο Δυτικής Αττικής, 2024-09-02)
      Time series data capture the behavior of variables over time and as such they are of core importance in a broad variety of scientific disciplines and applications including finance, industry, healthcare and networks, among ...

    • Transferable state & action embeddings in deep reinforcement learning 

      Ελευθερίου, Δημήτριος (Πανεπιστήμιο Δυτικής Αττικής, 2024-07)
      This thesis delves into two primary areas: the impact of transfer learning on the performance of RL algorithms and the implementation of a transformers-based architecture for learning representations of both states and ...

    • Artificial intelligence methods for predictive maintenance 

      Κόικας, Δημήτριος (Πανεπιστήμιο Δυτικής Αττικής, 2024-04-26)
      The rapid evolution of Artificial Intelligence over the past few years has revolutionised applications in several fields. Such field is the Predictive Maintenance (PdM) concept. In contrast to reactive or scheduled ...

    • Deep learning and variable autonomy for mobile robot navigation 

      Παππάς, Παντελεήμων (Πανεπιστήμιο Δυτικής Αττικής, 2024-03)
      This paper addresses the problem of safe and efficient navigation of mobile robots in extreme environments such as Search and Rescue (SAR) and Urban Search and Rescue (USAR) missions or other forms of remote robotic tasks. ...

    • Study of simulation and modelling tools for autonomous vehicle driving based on stereoscopy 

      Αποστόλου, Νικόλαος (Πανεπιστήμιο Δυτικής Αττικής, 2024-03-08)
      The subject of this thesis is the analysis and study of the tools available today that assist engineers in the modeling and development of autonomous vehicles with automatic navigation. A comprehensive explanation of the ...

    • Applying graph neural networks for stance detection over online social networks 

      Μοναχέλης, Παναγιώτης (Πανεπιστήμιο Δυτικής Αττικής, 2024-03)
      Fake news has flooded social networks and has been studied from different perspectives. Different methodologies have been proposed to approach this issue. In recent years, researchers have been conducting analyses based ...

    • A comparative evaluation of machine learning and deep learning for sports predictions in table tennis 

      Κυρώσης, Μηνάς-Νικόλαος (Πανεπιστήμιο Δυτικής Αττικής, 2024-03-07)
      The surge in sports data availability has opened avenues for exploring the application of machine learning (ML) and deep learning (DL) techniques in predicting match outcomes as classification tasks across various sports. ...

    • Designing a scalable and reproducible machine learning workflow 

      Πολυχρόνου, Ιωάννα (Πανεπιστήμιο Δυτικής Αττικής, 2024-03-06)
      The advancement of machine learning (ML) applications necessitates the construction of end-to-end experimentation pipelines characterized by scalability, robustness, and reproducibility. This thesis aims to empower Data ...

    • Augmentation of large language model capabilities with knowledge graphs 

      Τσακαλάκης, Βίκτωρ (Πανεπιστήμιο Δυτικής Αττικής, 2024-03-06)
      This postgraduate thesis explores the possibility for augmentation of the abilities of Large Language Models (LLMs) in the task of Question Answering by incorporating the technique of Retrieval-Augmented Generation (RAG) ...

    • Solving multiple sequence alignment using deep reinforcement learning 

      Κοτζιά, Ειρήνη (Πανεπιστήμιο Δυτικής Αττικής, 2024-02-20)
      Multiple Sequence Alignment (MSA) is a fundamental task in Bioinformatics, essential for understanding evolutionary relationships, genetic adaptations, drug design, and other applications. In general, MSA is a Nondeterministic ...

    • Applying reinforcement learning algorithms for profitable strategies in a stock market simulator 

      Σταυροθανάσης, Θεόδωρος (Πανεπιστήμιο Δυτικής Αττικής, 2023-10-13)
      Financial time series present unique characteristics that an investor, analyst or algorithmic trader has to take always into account. One of the defining features is their inherent volatility and non-linearity. Unlike many ...

    • Use of artificial intelligence and deep learning in the food and agriculture domain 

      Αθανασόπουλος, Ιάσων (Πανεπιστήμιο Δυτικής Αττικής, 2023-02)
      The current thesis is an overview of the materials and the technics that are used in the Smart Farming sector. It focuses on the particularities of Smart Farming compared to other Artificial Intelligence applications, hence ...

    • Sign language detection 

      Σταμούλης, Στέφανος-Ιωάννης (Πανεπιστήμιο Δυτικής Αττικής, 2023-02)
      Communication is defined as the exchange of information, ideas and feelings.In order for two people to communicate with each other they must understand the same language.When a person is deaf they cannot hear and when they ...

    • Σχεδιασμός και υλοποίηση έξυπνης σύμβασης σε ένα δίκτυο Blockchain για την αξιολόγηση των χαρακτηριστικών σε ομάδες δεδομένων 

      Λιακόπουλος, Αλέξανδρος Δημήτριος (Πανεπιστήμιο Δυτικής Αττικής, 2023-02-23)
      Τα μοντέλα τεχνητής νοημοσύνης (AI) με επίκεντρο τα δεδομένα βασίζονται, σε μεγάλο βαθμό, σε σύνολα δεδομένων υψηλής ποιότητας για την εκτέλεση των καθηκόντων τους. Έχουν σχεδιαστεί για να αναλύουν και να μαθαίνουν από ...