Abstract
Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.
Highlights
Nowadays, different biometric modalities are being explored
Five questions arises: What is the impact of using different tasks from the same run in biometric verification? Despite the parity of reported Equal Error Rate (EER), the model trained with task Task 2 (T2) presented a small and similar EER with both nine channels and 64, outperforming the models trained with tasks Task 3 (T3)–Task 4 (T4)
We believe SE-block based network is a promising approach as a feature extractor for EEG signals. It was evaluated the use of deep descriptors to extract features from the EEG signal for biometric purposes
Summary
Different biometric modalities are being explored. They have been gradually replacing the logging/password systems, once it represents the future path in terms of digital security. In a preliminary work (Schons et al, 2017), a data augmentation technique was proposed to increase the training data, improving the network performance, and enabling the deep learning model to converge for the Physionet—EEG Motor Movement/Imagery Dataset. It has been shown in previous works evidence that EEG has biometric potential under the performance of different tasks (Vinothkumar et al, 2018, DelPozo-Banos et al, 2018; Kong et al, 2018; Kumar et al, 2019; Fraschini et al, 2019).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
