Biometric Identification Based on EEG Signal with Photo Stimuli using Hjorth Descriptor

Abstract

Biometric techniques are methods for recognizing a person based on physiological or behavioral characteristics. The advantage of biometric techniques is difficult to modify. Many recent studies have started to develop bio signal-based biometrics such as the biometric electroencephalogram (EEG). This study proposes a biometric identification system based on EEG signals with photo stimuli. The EEG data is collected from five participants with five recording sections by using the Muse Headband EEG Monitor. The EEG characterization of each individual is calculated using the Hjorth Descriptor method. Validation of the proposed system is done by using K-fold crossvalidation and Backpropagation neural network. A total of 25 validated data, consisting of 10 test data and 15 training data. The system achieves 100% accuracy.