A CNN-LSTM Based Model for EEG-Based Biometric Authentication

Biometric authentication using Electroencephalogram (EEG) signals is a promising method for secure and unique user identification due to the inherent complexity of brain signals and their variability among individuals. This study introduces a deep learning approach for EEG-based biometric authentication. The proposed method attains elevated classification accuracy by employing Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models on time-series EEG data. We analyze the performance using publicly available datasets such as the PhysioNet EEG Motor Movement/Imagery Dataset and DEAP. The results demonstrate superior accuracy and robustness in comparison to traditional machine learning models. We also did a thorough analysis of 20 related studies to put our work in the context of the present.