학술논문

Performance Improvement in User Verification Using Evoked Electroencephalogram by Imperceptible Vibration Stimuli
Document Type
Conference
Source
2021 20th International Symposium on Communications and Information Technologies (ISCIT) Communications and Information Technologies (ISCIT), 2021 20th International Symposium on. :109-113 Oct, 2021
Subject
Communication, Networking and Broadcast Technologies
Signal Processing and Analysis
Vibrations
Support vector machines
Electrodes
Degradation
Biometrics (access control)
Error analysis
Frequency-domain analysis
biometrics
EEG
imperceptible vibration stimuli
EER
SVM
Language
ISSN
2643-6175
Abstract
In this study, we examine electroencephalogram (EEG) biometric information that can be detected continuously with high confidentiality to realize personal verification using the evoked EEG when presented with an imperceptible vibration stimulus. Considering the survey of conventional studies on brain-waves evoked by perceptible vibration stimulation, we determined that to use the evoked EEG, including the immediately response after the stimulus is effective in verification. Therefore, we introduce a method for repeating the stimulus presentation over a short time. In addition, to improve the verification performance, we introduce support vector machine (SVM). Furthermore, we evaluated the verification performance and obtained an equal error rate of 11%.