Theodorakopoulos Ilias

RANK:	Assistant Professor
SECTOR:	Electronics and Information Technology Systems
LABORATORY:	Electrical Circuits, Signal and Image Processing Laboratory
EXPERTISE:	Machine Learning for Signal Processing

CONTACT DETAILS

ADDRESS:	University Campus Kimmeria, Building B, Office 1.16
E-MAIL:
TELEPHONE:	+30 25410 79571, Fax: +30 25410 79569
PERSONAL WEBSITE:	https://utopia.duth.gr/~iltheodo/
CV:

SCIENTIFIC INTERESTS

Deep Learning

Machine Learning methods for Limited Data

Computer Vision

Biomedical Signal Processing

Image Analysis

Biometrics

UNDERGRADUATE COURSES

Pattern Recognition

Electric Measurements

Electric Circuits I

Digital Image Processing

POSTGRADUATE COURSES

SHORT CV

Dr. Ilias Theodorakopoulos received his Bachelor’s degree in Physics from the University of Patras, Greece in 2007, followed by a Master’s degree in Electronics & Computers in 2009. In 2014, he earned his PhD from the University of Patras, working on Pattern Recognition methods for Images and Multimedia. He has over a decade of experience in the private sector, specializing in the development of Computer Vision and Data Analysis systems for industrial and consumer applications, and contributing to numerous European and national R&D projects. Dr. Theodorakopoulos has worked as a post-doctoral researcher at the Electronics Laboratory of the Department of Physics at the University of Patras, also collaborating with the Pediatric Pulmonology Group at the University Hospital of Patras. He has taught as an Academic Scholar in the Department of Biomedical Engineering at the University of West Attica from 2020 to 2022. In 2023, Dr. Theodorakopoulos joined the faculty of the Department of Electrical and Computer Engineering at the Democritus University of Thrace (DUTH) as an Assistant Professor. His current research interests focus on Deep Learning and Machine Learning methods for Signal Processing, Computer Vision, and Image Analysis applications.

RESEARCH PROJECTS

SAFE-AORTA (safe-aorta.gr) - Clinical Decision Support System for Abdominal Aortic Aneurysm Disease Based on Artificial Intelligence Models (TAEDR-0535983) – Research Collaborator

SELECTED PUBLICATIONS

Tsourounis, I. Theodorakopoulos, E. N. Zois and G. Economou, "From Text to Signatures: Knowledge Transfer for Efficient Deep Feature Learning in Offline Signature Verification," Expert Systems with Applications 189, 2022.

Fouzas, A-C Kentgens, O. Lagiou, B. S. Frauchiger, F. Wyler, I. Theodorakopoulos, S. Yammine, P. Latzin “Novel volumetric capnography indices measure ventilation inhomogeneity in cystic fibrosis,” ERJ Open Research Jan 2022, 8 (1) 00440-2021

Theodorakopoulos, F. Fotopoulou, G. Economou, “Geometric Regularization of Local Activations for Knowledge Transfer in Convolutional Neural Networks,” Information 2021, 12, 333.

Pothos, E. Vassalos, I. Theodorakopoulos and N. Fragoulis, “Deep Learning Inference with Dynamic Graphs on Heterogeneous Platforms,” International Journal of Parallel Programming, 49, pages158–176, 2021.

N. Zois, D. Tsourounis, I. Theodorakopoulos, A. L. Kesidis and G. Economou, "A Comprehensive Study of Sparse Representation Techniques for Offline Signature Verification," in IEEE Transactions on Biometrics, Behavior, and Identity Science. 2019

Fouzas, I. Theodorakopoulos, E. Delgado-Eckert et al., "Breath-to-breath variability of exhaled CO2 as a marker of lung dysmaturity in infancy," Journal of Applied Physiology, vol. 123, no. 6. pp.1563-1570, Nov. 2017.

Theodorakopoulos, G. Economou, S. Fotopoulos and C. Theoharatos, “Local manifold distance based on neighborhood graph reordering,” Pattern Recognition, Volume 53, pp. 195-211, May 2016.

Kastaniotis, I. Theodorakopoulos, C. Theoharatos, G. Economou and S. Fotopoulos, "A framework for gait-based recognition using Kinect," Pattern Recognition Letters, Volume 68, pp. 327-335, December 2015.