Wavelet Transform and Machine Learning-Based Biometric Authentication Using EEG Evoked by Invisible Visual Stimuli

In this study, we propose the authentication of individuals using electroencephalograms (EEGs) evoked by the application of invisible visual stimuli. In our previous study, we introduced a wavelet transform, which is a time-frequency analysis method, and applied it to extract features, including time information, to enable more accurate discrimination between individuals. An equal error rate (EER) of 9.4 % was achieved using Euclidean distance matching. In this paper, we introduce a machine learning-based approach in order to further improve the verification performance. An EER of 8.1 % is achieved by the proposed method after training the constituent neural networks using ensemble learning with 30 networks.