Neural control framework for drones using motor imagery EEG classification. Achieves 73% cross-subject accuracy with PyTorch and enables hands-free drone control through imagined hand/feet movements.

VisionAI: A high-performance Image Quality Classifier built with Python and Flask. Utilizing an MLP (Multi-Layer Perceptron) model to instantly detect and distinguish between blurred and sharp images with high precision

this projects contains set of codes that will process the raw audio data for dataset creation and build MLP and CCN models forreal-time voice recognition with 4 classes. at last we implemented this model on a simple game

A Full-Stack web application that classifies the 27 letters of the Mexican Sign Language (LSM) alphabet plus 2 additional signs, processing frames in real-time directly through your webcam.

An interactive, browser-based Real-Time Image Classifier using TensorFlow.js. Train a custom neural network entirely client-side using your webcam, complete with live predictions, model exporting.

Using a LLM and ~800 images per class, this model is able to distinguish between cardboard, glass, plastic, organic, paper, batteries and inorganic waste.