Now showing items 1-20 of 20

  • Applications of machine learning and object recognition in virtual worlds.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Tzermia, Chrysoula
    Thesis advisor: Malamos, Athanasios
    Publication Date: 2022-05-11
    In this work, the application of machine learning in the division of objects (models) in the virtual space was studied in order to extract their characteristics and finally their classification and recognition. For this ...
  • Design and development of a web-based data visualization software for political tendency identification of Twitter’s users using Python Dash Framework.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Britzolakis, Alexandros
    Thesis advisor: Papadakis, Nikolaos
    Publication Date: 2020-06-11
    The rapid evolution of computers as well as the emerge of the internet brought a new era on the field of communication systems. Many individuals can instantly communicate with each other (through instant messaging or ...
  • Exploiting compressed sensing in distributed machine learning.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Stamatakis, Emmanouil
    Thesis advisor: Panagiotakis, Spyridon
    Publication Date: 2023-07-11
    A range of contemporary applications, such as remote monitoring of crucial measurements, mechanical fault recognition, remote detection of structural strain in constructions, and many others, have become possible today ...
  • Gene expression and gene regulatory network analysis with statistical methods and machine learning algorithms.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Droumalia, Foteini
    Thesis advisor: Tsiknakis, Emmanouil
    Publication Date: 2023-04-10
    Determining the best approach and data type for Pathway Analysis is a significant difficulty for the field of diagnostic medicine. The findings of recent studies indicate their preference for Machine Learning algorithms ...
  • Integration of gene expressions with polymorphism data in systems biology: comparison with imaging techniques in gliomas.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Iosifidis, Petros-Konstantinos
    Thesis advisor: Tsiknakis, Emmanouil; Koumakis, Eleftherios
    Publication Date: 2022-11-01
    The present work outlines core aspects of machine learning in the fields of radiomics, genomics, transcriptomics and radiogenomics. More specifically, it’s attempting through the usage of multi-type data (including medical ...
  • Machine learning-based active operating system fingerprinting dataset.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Nikas, Evangelos-Polynikis
    Thesis advisor: Markakis, Evangelos
    Publication Date: 2022-10-21
    Cyber-attacks have expanded significantly and progressed in effectiveness over the past few years. As a result, vulnerabilities of targeted computer and network systems can be exploited remotely. Before the initialization ...
  • Machine learning-based near real time intrusion detection and prevention system using eBPF.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Kostopoulos, Stamatios
    Thesis advisor: Markakis, Evangelos
    Publication Date: 2024-02-12
    As technology evolves rapidly, more and more critical infrastructures are going online. Malicious individuals are trying to exploit such infrastructures, thus cyber-attacks have become a major issue for users and businesses. ...
  • Opinion mining from data of social media by probabilistic logic reasoning.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Zervoudakis, Stefanos
    Thesis advisor: Marakakis, Emmanouil
    Publication Date: 2020-09-23
    This thesis studies opinion mining from social media with probabilistic logic reasoning. Twitter is one of the most active social networks, with millions of tweets sent daily, where multiple users express their opinion ...
  • Semantic segmentation of diabetic retinopathy lesions, using a UNET with pretrained encoder.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Theodoropoulos, Dimitrios
    Thesis advisor: Marias, Konstantinos
    Publication Date: 2022-01-19
    With the emergence of Deep Learning nowadays, a lot of novel architectures have been devised to perform tasks such as classification, detection, segmentation etc. In Medical Imaging and especially in Ophthalmology, the ...
  • Type 1 diabetes hypoglycemia prediction based on continuous glucose monitoring and heart rate.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Tsichlaki, Styliani
    Thesis advisor: Tsiknakis, Emmanouil
    Publication Date: 2022-01-14
    Hypoglycemia is a condition that arises when blood glucose levels decrease below 60 mg/dL. This incident can occur due to a variety of causes, such as taking additional doses of insulin, skipping meals, or over-exercising. ...
  • WiFi-based indoor positioning.

    H.M.U., School of Engineering (ScENG) MSc in Informatics & Multimedia
    Authors: Savvas, Charilaos
    Thesis advisor: Panagiotakis, Spyridon
    Publication Date: 2024-01-23
    In this dissertation, the primary focus is the development of an indoor positioning system predicated on WiFi technology, harnessing both Round Trip Time (RTT) and Received Signal Strength Indication (RSSI) methodologies. ...
  • Gene expression analysis using deep learning.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Panagiotakis, Georgios
    Thesis advisor: Marias, Konstantinos
    Publication Date: 2021-05-11
    The present work outlines the basic aspects of artificial intelligence in the field of bioinformatics and in particular the use of neural networks for the analysis of gene expressions. In the first stage, introductory ...
  • Music database development with the use of the European Digital Library (Europeana Music).

    Η.Μ.U, School of Music and Optoacoustic Technologies (SMOT), Music Technology and Acoustics Dept.
    Authors: Tsoura, Rais
    Thesis advisor: Zervas, Panagiotis
    Publication Date: 2020-10-21
    In this paper, reference is made to digital libraries, and more specifically to the European Digital Library (europeana), their necessity, advantages and disadvantages but also the challenges they face in the modern picture, ...
  • Automatic artist recognition by using machine learning methods.

    Η.Μ.U, School of Music and Optoacoustic Technologies (SMOT), Music Technology and Acoustics Dept.
    Authors: Vavagiakis, Eftychios
    Thesis advisor: Zervas, Panagiotis
    Publication Date: 2020-09-10
    The dissemination of digital musical information brought upon the creation of huge music databases which are used for both personal and professional reasons. Thus, the need was created for fast and reliable information ...
  • Consumer's attitude towards the introduction of robots in accomodation and hotel industry.

    Η.Μ.U, School of Management and Economic Sciences (SMES), Business Administration and Tourism Dept.
    Authors: Vardoulaki, Aikaterini; Roditi, Olga
    Thesis advisor: Dimou, Eirini
    Publication Date: 2020-04-29
    It is widely accepted that we are going through a period of time in which almost all human needs and everyday life are directly linked to technology. New technologies have 'invaded' the modern households and businesses, ...
  • Inverse physical parameter estimation of vibrating membranes from sound using deep neural networks.

    H.M.U., School of Music and Optoacoustic Technologies (SMOT), MSc in Sound and Music Technologies
    Authors: Starakis, Michail
    Thesis advisor: Alexandraki, Chrysoula; Zervas, Panagiotis
    Publication Date: 2022-06-02
    Inverse problems in the field of acoustics can be valuable tools for retrieving information through the produced sound. At the same time, the rapid development of deep machine learning techniques and the remarkable ...
  • The use of chatbots in business.

    Η.Μ.U, School of Management and Economic Sciences (SMES), Management Science and Technology Dept.
    Authors: Chasanai, Egklantina
    Thesis advisor: Vasileiadis, Giorgos
    Publication Date: 2022-05-26
    The economic environment in the modern world is changing thanks to the penetration of Artificial Intelligence technologies in the daily lives of many companies. A big part of artificial intelligence are the chatbots whose ...
  • Using chatbots for customer service and support.

    Η.Μ.U, School of Management and Economic Sciences (SMES), Management Science and Technology Dept.
    Authors: Binikou Ketsiriporn, Anastasia; Mythi, Despoina
    Thesis advisor: Vasileiadis, Giorgos
    Publication Date: 2023-09-25
    The evolution of Internet and the increased popularity of digital services have changed the way businesses interact with their customers. Chatbots is a technology that has emerged as a viable and efficient solution for ...
  • Multi-omic analysis of genomic data for the classification of glioblastoma samples.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Oikonomou, Nikolaos
    Thesis advisor: Tsiknakis, Emmanouil
    Publication Date: 2023-05-10
    Clustering of individual omic datasets has proven invaluable for biological and medical research. Decreasing costs and the development of next-generation sequencing (NGS) methods now have the measurement of multi-omic data. ...
  • Signal quantification from florescent histopathological images and machine learning applications for their categorization.

    Η.Μ.U, School of Engineering (ScENG), Electrical and Computer Engineering Dept
    Authors: Papagiannakis, Stylianos
    Thesis advisor: Marias, Konstantinos
    Publication Date: 2024-01-16
    The quantification and categorization of fluorescence images constitutes a challenging goal nowadays due to the lack of a specific software. Clinicians are required to manually select and delineate regions of interest in ...