Research & Applied Projects

An overview of formal research endeavors, architectural implementations, and practical methodologies developed to handle data and reasoning constraints.

Transformer-Based Automated Subjective Answer Evaluation

Current

Developed an evaluation pipeline utilizing BERT and SBERT alongside OCR to semantically score free-form subjective answers. The system normalizes language structure and establishes metric baselines against reviewer ground-truth.

Python TensorFlow Hugging Face Computer Vision

Hybrid RNN-Transformer Efficiency Optimization

Current

Architectural research investigating permutations of recurrent contexts with localized attention mechanisms to achieve standard language modeling capabilities under reduced computational budgets.

NLP Efficiency Research

Mental Health Detection using Baseline NLP

May 2025

A multi-label categorization architecture engineered to predict clinical mental health indications from unstructured text corpora utilizing attention-pooled BERT representations.

Attention Mechanisms Text Classification

Autonomous Vehicle Driving Safety System

Sep 2024

Orchestrated a vision pipeline with YOLOv8 for continuous inference of obstacle velocity, lane deviation, and collision probabilities in real time to support automated alerting functionality.

YOLOv8 Safety Analytics Object Tracking

AI Tool for Data & Web Insights

Dec 2024

LLM-integrated extraction architecture facilitating unstructured data ingestion, RAG-assisted contextual search, and formal structured output formatting.

LLMs Structured Extraction

Face Recognition Pipeline

Apr 2023

Implemented localized CNN verification networks relying on FaceNet embeddings to achieve identity resolution against arbitrary topological variations.

CNN OpenCV FaceNet