EEG-Based User Authentication System
Author Information
Author(s): Khalil Adnan Elahi Khan, Perez-Diaz Jesus Arturo, Cantoral-Ceballos Jose Antonio, Antelis Javier M.
Primary Institution: School of Engineering and Sciences, Tecnologico de Monterrey, Monterrey, Nuevo Leon, Mexico
Hypothesis
Can brain signals be used for reliable user authentication?
Conclusion
The proposed EEG-based user authentication scheme achieved 97% accuracy in identifying and authenticating users.
Supporting Evidence
- The EEG-based user authentication system can accommodate new users without retraining.
- The method focuses on power spectral density for feature extraction.
- The system achieved a high accuracy of 97% in user authentication.
- Privacy is preserved by storing only extracted features, not raw EEG data.
Takeaway
This study shows that we can use brain signals to tell who someone is, making it a super secure way to log in without passwords.
Methodology
The study used a multi-layer perceptron feedforward neural network to analyze EEG signals for user identification and authentication.
Potential Biases
Potential biases may arise from the limited diversity of the participant pool.
Limitations
The study's small sample size may limit the generalizability of the findings.
Participant Demographics
The study involved eight participants.
Statistical Information
P-Value
0.0001 to 0.0007
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website