Hands-on work spanning machine learning, NLP, computer vision, and data engineering.
End-to-end financial data pipeline: querying financial data stored in MongoDB, exploratory data analysis, and visualization with Seaborn and Matplotlib.
Real-time system recognizing depression by extracting features from facial expressions, EEG signals, and speech modules using multimodal deep learning.
ARIMA model built with MATLAB's Econometrics Toolbox to forecast GDP and Stock Indexes of 10 countries with Python-based validation.
Data analysis and visualization to find suitable business locations using Wikipedia data for Toronto, leveraging Folium mapping and web scraping.
Implemented YOLOv3 trained on the COCO dataset for real-time object detection and localization on road scenes.
Modern audit trail system for doctors providing an overview of medical history, prescriptions, and lab reports using MySQL and JavaScript.
Full-stack web application with user-friendly interface for seamless booking and exploration of camping destinations.