期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2020
卷号：12
页码：14-22
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：This paper aims to investigate the use of alpha and beta band for brainprint authentication modelling by using Incremental Fuzzy-Rough Nearest Neighbour (IncFRNN) technique. Many electroencephalogram (EEG) research worked well in controlled lab environments with the minimum ambient disturbance. It is because the EEG signals are easily influenced by the ambient noise or other physiological noise. Therefore, in order to enhance the use of brainprint authentication, two rhythms of EEG signals: alpha and beta band were examined in three different level of auditory distraction (i.e. quiet, low and high distraction) to simulate the real-world environment. Only 5 electrodes, which represents the auditory and visual are used for the brainprint authentication modelling. The representative features were extracted from the power spectral density (PSD), coherence and wavelet phase stability (WPS) before perform classification. The experimental results showed that the authentication results of quiet and high distraction conditions are performed significantly better than the low distraction condition in the alpha band. However, the statistical tests do not show significant different for the three conditions in beta band. It might because of the tasks given in this environment do not involved much analysis and decision making. Further investigations will be focused on the combination of alpha and beta band for brainprint authentication modelling..
