Key Projects

Member of Hermes Team
Hermes Team is a project led by University of Thessaly students, aimed at creating a robotic ex-
oskeleton for individuals suffering from spinal cord injury. The team was accepted as a participant at
Cybathlon 2024, a non-profit contest by ETH Zurich. Configured the controllers to interface seamlessly with the system’s kinematic model, ensuring
precise alignment with the exoskeleton’s movement requirements. I designed and implemented a multithreaded synchronization system to coordinate actuator
movements in real-time, ensuring precise and smooth motion across all joints.
Visit Team site

GSL Letter Recognition Using MediaPipe and PyTorch
Developed a sign language recognition system with 369 individual classes using MediaPipe Hands and Python, capturing
camera input to detect hand landmarks for real-time inference.
• Trained a machine learning model using a pre-existing dataset of labeled Greek sign language hand poses,
applying preprocessing techniques to normalize landmark data and improve classification accuracy.

Notable Courses

Machine Learning for Data analysis

Machine learning techniques, categorization and regression, artificial neural networks, SVMs, data mining techniques, applications in large amounts of unstructured data for business analytics and sentiment analysis and opinion mining.
Python - Pandas, Keras, PyTorch, Tensorflow

Operating systems

Structure and organization of OSs, mechanisms and policies. Processes and Threads, Context Switch. Memory Segmentation, Memory paging. File system organization, RAID storage organization.

High Performance Computing Systems

Programming techniques for parallel systems and more specifically multicores and manycores. It spans programming of conventional and non-conventional, homegeneous and heterogeneous architectures. The students are introduced to performance measurement and estimation techniques, application profiling, experimental performance evaluation, experimental evaluation of software / hardware interaction and optimization techniques.
CUDA, OpenMP

Computer Vision

Basic image processing operations, namely linear filtering, additional neighborhood operations, Fourier transform, and Gaussian / Laplacian pyramidal image representation.
Feature detection, matching, and alignment, including the Harris detector and SIFT descriptors, the Canny edge detector, the Hough transform, as well as efficient and robust feature matching algorithms and the RANSAC approach.
Python - OpenCV

Teaching Assistant
"Computer Organization & Architecture" course Fall 2024
Webmaster
local IEEE student Branch April 2025 -
Wikimedia
User Group Greece Member October 2024

Volunteering