Unified framework for Identity and Imagined Action Recognition from EEG patterns

We present a unified deep learning framework for user identity recognition and imagined action recognition, based on electroencephalography (EEG) signals. Our solution exploits a novel phased subsampling preprocessing step as a form of data augmentation, and a mesh-to-image representation to encode the inherent local spatial relationships of multi-electrode EEG signals. The resulting image-like data is then fed to a convolutional neural network, to process the local spatial dependencies, and eventually analyzed through a Bidirectional LSTM module, to focus on temporal relationships. Our solution is compared against several methods in the state of the art, showing comparable or superior performance on different tasks. Preliminary experiments are also conducted in order to direct future works towards everyday applications relying on a reduced set of EEG electrodes.