How Much EEG Data Do We Need for Accurate Biometrics?

Published on May 10, 2022

Imagine you have a treasure map that leads you to a game-changing discovery. But here’s the catch – you don’t know how much of the map you need to find the treasure. Well, scientists face a similar challenge when it comes to developing robust biometric models using Electroencephalogram (EEG) data. In this study, researchers set out to determine the minimum amount of EEG data required to train accurate models for task-dependent biometric applications. By analyzing over 11,000 combinations of training sizes and employing advanced learning techniques, they found that just 1 second of data per subject is enough to achieve a testing accuracy of over 95%. And if you want an even higher accuracy of 99%, just 3 seconds will do the trick! These findings open up exciting opportunities for using EEG in real-world biometric applications and provide valuable insights into how much data is truly needed. Ready to dive deeper into this fascinating research? Follow the link below!

Biometrics is the process of measuring and analyzing human characteristics to verify a given person’s identity. Most real-world applications rely on unique human traits such as fingerprints or iris. However, among these unique human characteristics for biometrics, the use of Electroencephalogram (EEG) stands out given its high inter-subject variability. Recent advances in Deep Learning and a deeper understanding of EEG processing methods have led to the development of models that accurately discriminate unique individuals. However, it is still uncertain how much EEG data is required to train such models. This work aims at determining the minimal amount of training data required to develop a robust EEG-based biometric model (+95% and +99% testing accuracies) from a subject for a task-dependent task. This goal is achieved by performing and analyzing 11,780 combinations of training sizes, by employing various neural network-based learning techniques of increasing complexity, and feature extraction methods on the affective EEG-based DEAP dataset. Findings suggest that if Power Spectral Density or Wavelet Energy features are extracted from the artifact-free EEG signal, 1 and 3 s of data per subject is enough to achieve +95% and +99% accuracy, respectively. These findings contributes to the body of knowledge by paving a way for the application of EEG to real-world ecological biometric applications and by demonstrating methods to learn the minimal amount of data required for such applications.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>