Projects
> Showcasing some of my selected projects image (16 x 9)
Brain MRI Detection using Deep Learning
brain-tumor-detection is a compact, reproducible repository for detecting and classifying brain tumors from MRI images using transfer learning (MobileNetV2). The repository includes data organization, augmentation, training (frozen base + fine-tuning), checkpointing, evaluation and a minimal Streamlit dashboard.
Learn more
Sentic-Quant-High-Fidelity-sentiment-Predictor
A multi-modal signal engine fusing FinBERT sentiment with a Time-Series Transformer architecture. It decodes non-linear market regimes by applying self-attention to unified qualitative and quantitative data. Features a robust walk-forward back testing suite with institutional risk-adjusted metrics.
Learn more
Vector-Loom Domain Specific Q/A RAG Assistant
VectorLoom is a decoupled FastAPI/Streamlit architecture utilizing local embedding models and language generation to weave retrieved document chunks into highly accurate, domain-adaptable answers.
Learn more
Multimodal Instructional Assistant
A Multimodal AI Pipeline for Educational Content Understanding and Contextual Question Generation.
Learn more
Energy-Demand-Forecasting
This project focuses on time series forecasting of hourly energy consumption (AEP_MW) using a Long Short-Term Memory (LSTM) neural network
Learn more
VoiceForge
A voice-controlled local AI agent that transcribes audio, classifies intent, and executes actions on your machine — powered by Whisper, Ollama, and Streamlit.
Learn more
Social-to-Lead Agentic Workflow
A social-to-lead agentic workflow built with LangGraph and Groq (Llama 3.3 70B). The agent classifies user intent, answers product/pricing questions via a RAG knowledge base, and automatically collects lead information (name, email, platform) through natural conversation — saving qualified leads to a CRM. Features a Gradio web UI
Learn more