Convolutional Neural Network for Closed-Set Identification from Resting State Electroencephalography

In line with current developments, biometrics is becoming an important technology that enables safer identification of individuals and more secure access to sensitive information assets. Researchers have recently started exploring electroencephalography (EEG) as a biometric modality thanks the uniqueness EEG signals. A new architecture for convolutional neural network (CNN) uses signals suggested in this paper identification. CNN does not need complex signal pre-processing, feature extraction, selection stages. The datasets utilized research are resting state eyes open (REO) closed (REC) EEG. Extensive experiments were performed design deep architecture. These showed eleven layers (eight layers, one average pooling layer, two fully connected layers) Adam optimizer resulted highest accuracy. proposed here was compared existing models using same dataset. results show method outperforms other task-free paradigm models, accuracy 98.54%.