Projects

DrAI is an educational platform developed within the Erasmus+ HEALTH-AI Project to make healthcare AI understandable, ethical, and accessible to non-technical users. The platform teaches patient-safety risks, demographic bias, privacy concerns, EU AI Act principles, human oversight, and responsible AI governance.

NeuroMotion is a real-time adaptive EEG brain-computer interface project I developed to detect motion intention from Motor Imagery (MI) and Movement-Related Cortical Potentials (MRCP). The system uses PyTorch-based CNN/RNN models, a TCP/UDP bridge between the Python AI backend and Unity 3D simulation, and an ErrP monitoring module to detect incorrect commands.

Synvia is an Electron and React desktop AI application I built for companies and public institutions that need practical AI workflows without exposing sensitive data. It supports local data processing, local and online model options, and a simple cross-platform interface for non-technical users.

IT-ISQS is an EU-funded software quality project where I worked as co-project leader in a 5-person team. I managed QA workflows, prepared SRS and SDD documentation, created and executed test plans, contributed to the React frontend, and helped present the final product to EU representatives.

GemmaTR is my Turkish LLM fine-tuning project based on Google Gemma, Unsloth, and LoRA. I prepared a dataset of 400,000 Turkish Wikipedia entries and 50,000 law, education, and agriculture-focused QA pairs, trained four model variants on Google Colab, and published the work on Hugging Face.

Financst is a financial tracking platform I built with React, Next.js, MERN components, live market data, and interactive charts. It helps users monitor portfolios, review market movement, and make faster decisions through clearer visualization workflows.

AI Behavior Project is a reinforcement learning experiment where I integrated AI behavior into Minecraft and observed multiple agents in simulation to analyze interaction, adaptation, and decision-making patterns.

Drone Swarm Project is a reinforcement learning simulation focused on dynamic flight behavior for a handcrafted drone and the coordination logic needed for autonomous swarm-style operation.

I built a real-time 2D Unity simulation and trained multiple agents with Python-based reinforcement learning tools. I compared adaptation and learning behavior under changing conditions, with a focus on automation scenarios and defense-oriented simulation use cases.

I designed an AI model that collects financial data with Python and Yfinance, analyzes market movement, and produces strategy-oriented insights for users with limited financial experience.