Developed an unsupervised deep learning system for large-scale ECG anomaly detection using advanced Variational Autoencoder architectures, achieving strong performance with a Spectral-Temporal VAE (F1-score: 0.90, AUC-ROC: 0.93). The work integrates multi-domain signal modeling with a complete end-to-end pipeline and a functional screening interface.

Developed a machine learning framework to predict entrepreneurial tendencies among university students using academic, demographic, and behavioral data. The study compared multiple classification models and incorporated explainable AI (LIME) to interpret key factors influencing entrepreneurial behavior.

My first research paper, where I developed a custom hand gesture dataset and implemented a YOLOv8-based conceptual webcam-controlled web game for real-time interaction.