Projects

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 developed to help companies and public institutions integrate AI into daily workflows. It focuses on privacy-aware local data processing, support for both local and online AI models, and a simple cross-platform interface for non-technical users.

IT-ISQS is an EU-funded software project where I served as co-project leader in a 5-person team. I managed quality assurance processes, prepared SRS and SDD documents, created and executed test plans and test cases, contributed to the React frontend, and presented the project and website to EU representatives.

GemmaTR addresses the lack of Turkish chatbot resources by fine-tuning Google's Gemma model with Unsloth and LoRA on Google Colab. I created a dataset with 400,000 Turkish Wikipedia entries and 50,000 law, education, and agriculture-focused question-answer pairs, developed four model variants, and shared them on Hugging Face for public access.

A high-performance financial tracking platform I developed with the MERN stack, React, Next.js, live market data, and dynamic interactive charts. Users can monitor portfolios in real time, analyze complex market data, and make faster investment decisions through optimized visualization workflows.

A reinforcement learning project where I developed and integrated AI behavior inside Minecraft, then observed multiple AI agents in a simulation environment to analyze interaction, adaptation, and decision-making patterns.

A reinforcement learning drone swarm project where I developed dynamic AI behavior for a handcrafted drone that completed a flight in simulation, with the broader goal of enabling multiple drones to operate independently while coordinating as a group.

I created a real-time 2D simulation environment with Unity and developed a game in C#. In this environment, I trained multiple agents using Python-based RL libraries and comparatively analyzed their learning processes and adaptation abilities by testing each agent under different, dynamic environmental conditions. In the project, I demonstrated the potential of Reinforcement Learning algorithms in critical application areas like the defense industry by measuring the agents' performance in automation scenarios.

I designed an artificial intelligence model using Python and Yfinance that automatically collects and processes financial data, analyzes market movements, and provides strategic insights to the user. Thanks to the model I developed, even users with limited financial knowledge can make informed investment decisions by receiving personalized recommendations on products like stocks and mutual funds.