A deep descriptor for cross-tasking EEG-based recognition

• Published in: PeerJ. Computer science Vol. 7; p. e549
• Main Authors: Mota, Mariana R.F., Silva, Pedro H.L., Luz, Eduardo J.S., Moreira, Gladston J.P., Schons, Thiago, Moraes, Lauro A.G., Menotti, David
• Format: Journal Article
• Language: English
• Published: San Diego PeerJ. Ltd 19.05.2021; PeerJ, Inc; PeerJ Inc
• Subjects: Artificial Intelligence; Bioinformatics; Biometric; Biometrics; Biometry; Cable television broadcasting industry; Channels; CNN; Data augmentation; Data Mining and Machine Learning; Datasets; Deep learning; Electrodes; Electroencephalogram; Electroencephalography; Excitation; Expert systems; Multi-task; Pattern recognition; Performance evaluation; United States
• ISSN: 2376-5992; 2376-5992
• DOI: 10.7717/peerj-cs.549

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.