Knowledgable in Java, C, Python, and other frameworks
Troubleshooting software and hardware systems
Communicate and work effectively across teams
HTML
CSS
React
Java
C
Python
SQL
Azure
Linux
Aug, 2023 - Present
A web-based facial recognition system featuring real-time face detection and recognition using OpenCV, and machine learning models. The system includes a user-friendly interface, robust database integration, and live video streaming for real-time processing.
Engineered a multi-file C program that implements the SHA256 hashing algorithm, converting file input into secure hashed strings using advanced bitwise operations and pointer arithmetic. The program processes data in 64-byte blocks, applying padding and executing the SHA256 function to produce precise hexadecimal hash outputs. Designed with a robust state structure to handle block parsing efficiently.
Source link cannot be provided
Led the design of a comprehensive social media management tool that maps and analyzes connections across multiple platforms. Developed an algorithm to efficiently track relationships by user and platform, complemented by a detailed UML diagram. Evaluated and implemented various data structures and sorting algorithms to optimize abstract data type behavior, significantly improving performance and scalability.
Source link cannot be provided
A full-stack web app for booking, scheduling, and payment processing for a car detailing service. It features user authentication, admin management of bookings, real-time updates, and a user-friendly interface. Includes calendar views and an admin dashboard for efficient operations, with a focus on performance, scalability, and a clean UI.
Developed a multi-label deep learning model using DenseNet121 to train, validate, and test a collection of over 30,000 images to classify chest X-ray images across 14 thoracic diseases, achieving an overall accuracy of 93.84%. Evaluated model performance with AUC-ROC scores ranging from 0.69 to 0.87 for individual classes. Enhanced model interpretability through Grad-CAM visualizations, providing clear insights into regions influencing predictions. The project emphasizes performance, scalability, and reliability for potential deployment in medical diagnostic support systems.