nim Composition Space Optimization is a high-performance tool leveraging metaprogramming to implement several methods for selecting components (data dimensions) in compositional datasets, as to optimize the data availability and density for applications such as machine learning.

A Python tool to identify and remove similar-looking images from a dataset. Utilizes image preprocessing and hashing techniques for efficient comparison.

Morphia is a powerful library designed for transforming complex JSON structures into compact, index-based arrays and back. Ideal for efficient data serialization and deserialization, Morphia simplifies the handling of nested and dynamic data by flattening JSON objects into arrays and reconstructing them with precision.

Highlighting expertise in data migration, data normalization and standardization, this project demonstrates successful data transfer from Snowflake to Databricks. It emphasizes optimized data flow and enhanced accessibility through standardization, showcasing a commitment to ethical data practices.

⚡💾 Vectro — Compress LLM embeddings 🧠🚀 Save memory, speed up retrieval, and keep semantic accuracy 🎯✨ Lightning-fast quantization for Python + Mojo, vector DB friendly 🗄️, and perfect for RAG pipelines, AI research, and devs who want smaller, faster embeddings 📊💡

interface to ADAO (Data Assimilation and Optimization features in Python ) in SALOME

UI website for the ESAT Team 5A2 Smart Grid Data Project

An award-winning solution proposal for optimizing vertiport site selection in Urban Air Mobility (UAM) using multi-source data analysis and platform logic design. Recognized at the 9th Hyundai Motors University Case Competition.

Lobster data analysis and modelling using Python

This explores data optimization using PySpark, covering big data concepts, pipelines, machine learning, and data transformation techniques. The goal is to enhance data processing efficiency and model performance.

Official Tensorflow implementation for ActiveTCR: Active Learning Framwork for Cost-Effective TCR-Epitope Binding Affinity Prediction

Contains my project that analyzes air quality sensor data to determine if the NO (Nitric Oxide) sensor in N. Mai, Los Angeles, CA can be removed without affecting data accuracy.

This project analyzes historical weather data to identify patterns and predict future weather conditions, focusing on extreme events and temperature trends across Europe.

An efficiency enhancement tool for binary classifier pipelines. Aims to optimize feature selection within datasets for faster training and improved binary classification performance.