Alex Trbovic

PhD Student • Quantum Game Theory Researcher • Industrial Engineer

Featured Projects

Quantum Chess

Quantum Computing Game Development

Quantum Chess is a Python-based chess engine and GUI that integrates quantum mechanics principles into traditional chess. The game allows players to perform quantum moves such as superposition and entanglement, making for a unique and educational chess experience.

Key Features:

  • Classical chess gameplay with all standard rules
  • Quantum moves: superposition, entanglement, and measurement
  • PyQt5-based graphical user interface
  • Asynchronous quantum simulation using Qiskit
  • Move validation and basic game loop

Technologies: Python 3.9+, PyQt5, Qiskit

Quantum Nash Equilibrium Solver (WIP)

Research Quantum Computing

A quantum computing simulation environment for exploring strategic optimization in nonlocal games. This research project investigates how quantum entanglement and superposition can provide strategic advantages in competitive scenarios, particularly focusing on CHSH games.

Research Applications:

  • Simulation of quantum strategies in Bell games and CHSH scenarios
  • Analysis of quantum vs. classical strategic advantages
  • Optimization of quantum circuit parameters for maximum strategic benefit
  • Investigation of noise effects on quantum strategic performance

Technologies: Qiskit, Python, NumPy, Matplotlib, Jupyter Notebooks

Dynamic Tackler Identification System

Machine Learning Sports Analytics

An advanced machine learning system designed to predict the most likely tackler in NFL plays using real-time player positioning data. The system employs convolutional neural networks to process complex spatial-temporal relationships and provide tactical insights for coaching staff and analysts.

Key Features:

  • Real-time processing of multi-dimensional player tracking data
  • CNN architecture optimized for spatial pattern recognition
  • Integration with NFL play-by-play data for comprehensive analysis
  • Interactive visualization of prediction confidence and contributing factors

Technologies: TensorFlow, Python, Selenium, Pandas, NumPy, Matplotlib

Spectroscopy Data Analysis Suite

Data Science Materials Science

A comprehensive Python-based analysis platform for materials characterization using photoluminescence, absorption, and Raman spectroscopy data. The suite includes automated data processing, statistical analysis, and interactive visualization tools.

Features:

  • Automated peak detection and fitting algorithms
  • Statistical analysis and uncertainty quantification
  • Interactive dashboards for real-time data exploration
  • Integration with LabVIEW acquisition systems
  • Batch processing capabilities for large datasets

Impact: 80% improvement in data collection and analysis efficiency, enabling higher throughput materials research.

Technologies: Python, LabVIEW, Pandas, SciPy, Plotly, Dash

Poster: View project poster