Performance Enhancement of EEG Signatures for Person Authentication Using CNN BiLSTM Method

Despite their vulnerability to competent forgers, signatures are one of the most widely used user verification methods. Recent research has revealed that EEG signals are harder to reproduce and give superior biometric information. This study aims to improve the effectiveness of person authentication by using deep learning techniques on electroencephalogram (EEG) signals. The broad implementation of EEG-based authentication systems has been hindered by problems such as noise, variability, and inter-subject variances despite the potential distinctiveness of EEG signals. We propose a multiscale convolutional neural network (CNN) and a Bidirectional LSTM (BiLSTM) model called CNN-BiLSTM to extract features and classify raw EEG data. This methodology involves acquiring raw EEG data, preprocessing for noise reduction, standardization, normalization, and employing deep learning techniques for feature extraction and classification. Experimental results exhibit a notable improvement in accuracy and reliability compared to existing EEG authentication methods such as LOF, CNN, FCN, EfficientNet-B0, and BiLSTM. The results showcase the performance of the proposed deep learning model utilizing established metrics such as precision, sensitivity, specificity, and accuracy. The proposed methodology outperforms existing methods and achieves a training and validation accuracy of 98.9% and 92.2%, respectively. The findings of the research demonstrate that the proposed approach has been successful in achieving highly effective results by using EEG signals for the purpose of resolving issues related to person identification.