Selected work in ML, LLM systems, and distributed AI.
Privacy-first industrial AI assistant analyzing PLC fault logs with hybrid RAG retrieval, local LLM reasoning (Ollama + Mistral 7B), deterministic statistics, and strict hallucination guarding. Runs 100% locally with multi-tenant vector search via Qdrant.
Real-time system recognizing depression by extracting features from facial expressions, EEG signals, and speech modules using multimodal deep learning. Supported by peer-reviewed research publications.
YOLOv3 trained on the COCO dataset for real-time object detection and localization on road scenes. Related to autonomous vehicle patents and deployed in a braking system prototype.
ARIMA model built with MATLAB's Econometrics Toolbox to forecast GDP and Stock Indexes of 10 countries. Includes Python-based validation, residual diagnostics, and confidence intervals for economic trend analysis.
Data analysis and ML pipeline to find optimal business locations using Wikipedia data and Foursquare API for Toronto neighborhoods. Features Folium mapping, K-Means clustering, and geospatial visualization.
Full-stack audit trail system for doctors providing a unified overview of patient medical history, prescriptions, and lab reports. Features real-time search, role-based access control, and relational DB optimization.