Theo Lab

Emotion Detection using Machine Learning

This project demonstrates the use of a multi-modal approach for emotion detection, leveraging both visual and audio cues to predict emotions. The system combines computer vision and audio processing techniques to analyze facial expressions and voice patterns, offering a more robust solution compared to unimodal emotion detection systems.

Quantum Maze Solver

This project investigates the application of quantum computing in solving mazes more efficiently than traditional methods. By utilizing quantum algorithms, this solver takes advantage of quantum superposition and parallelism to explore multiple paths simultaneously, providing a new approach to maze-solving problems.

Machine Learning Enhanced Turbulence Modeling

Developed a turbulence modeling framework integrating Support Vector Machines (SVM) with Reynolds-Averaged Navier-Stokes (RANS) simulations. Aimed to enhance predictive accuracy by leveraging machine learning for improved turbulence closure modeling.

Attendance system Using Java

This project implements an efficient and scalable attendance management system using Java, Object-Oriented Programming (OOPS) principles, and Data Structures & Algorithms (DSA). The system allows instructors to record, track, and manage student attendance while leveraging key concepts of OOPS and DSA

File Manager Using C

Developed a command-line file manager in C for efficient file handling operations. Implemented functionalities like creating, deleting, renaming, copying, and moving files and directories. Utilized system calls and standard I/O operations for seamless interaction with the filesystem