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.

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

lightweight and interpretable approach for binary image blur detection using handcrafted spatial and frequency domain features processed by a fully connected multilayer perceptron neural network this method provides efficient realtime classification without relying on deep convolutional architectures