Towards Robust Subject Identification From EEG Segments With Data Augmentation Techniques

Electroencephalography (EEG) has a wide gamut of information, from subject identity to their emotional states encoded in it. Given a segment of the EEG signal, our study aims to identify the subject in a robust way using the EEGChannel-Net architecture. To achieve this goal, we add gaussian noise to...

Full description

Saved in:
Bibliographic Details
Published inProceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 1 - 2
Main Authors Nani, Meka, Banerjea, Supriyo, R, Raghavan
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.04.2025
Subjects
Accuracy
Brain modeling
Cross Entropy Loss
Data Augmentation
EEGChannelNet
Electroencephalography
Entropy
Gaussian noise
Linear programming
Noise measurement
Robustness
Signal to noise ratio
SNR
Speech processing
Online AccessGet full text

Cover

More Information
Summary:Electroencephalography (EEG) has a wide gamut of information, from subject identity to their emotional states encoded in it. Given a segment of the EEG signal, our study aims to identify the subject in a robust way using the EEGChannel-Net architecture. To achieve this goal, we add gaussian noise to the given 32-channel EEG signal, and minimize the ℓ 2 distance between embeddings of the original signal and that of the noisy signal in addition to the categorical cross entropy loss for classification of the 26 subjects in the dataset. Addition of noise to each channel at a fixed signal-to-noise ratio (SNR) of 15 dB gave the best balanced accuracy of 98.27% in the validation set. Our study concludes by justifying the optimality of the 15 dB SNR and highlights the superiority of our proposed objective function.
ISSN:2379-190X
DOI:10.1109/ICASSP49660.2025.10887643