Personal Identification Based on Brain Networks of EEG Signals

Abstract

Personal identification is particularly important in information security. There are numerous advantages of using electroencephalogram (EEG) signals for personal identification, such as uniqueness and anti-deceptiveness. Currently, many researchers focus on single-dataset personal identification, instead of the cross-dataset. In this paper, we propose a method for cross-dataset personal identification based on a brain network of EEG signals. First, brain functional networks are constructed from the phase synchronization values between EEG channels. Then, some attributes of the brain networks including the degree of a node, the clustering coefficient and global efficiency are computed to form a new feature vector. Lastly, we utilize linear discriminant analysis (LDA) to classify the extracted features for personal identification. The performance of the method is quantitatively evaluated on four datasets involving different cognitive tasks: (i) a four-class motor imagery task dataset in BCI Competition IV (2008), (ii) a two-class motor imagery dataset in the BNCI Horizon 2020 project, (iii) a neuromarketing dataset recorded by our laboratory, (iv) a fatigue driving dataset recorded by our laboratory. Empirical results of this paper show that the average identification accuracy of each data set was higher than 0.95 and the best one achieved was 0.99, indicating a promising application in personal identification. This is an open access article distributed under the Creative Commons Attribution-NonCommercial-NoDerivs license (http://creativecommons.org/licenses/by-nc-nd/3.0/). segment) were taken as a sample. The average PLV was computed to get an N × N symmetric matrix V .Step 3. The symmetric matrix V was used as the connectivity matrix of brain network to weigh brain network functional connectivity. The diagonal elements of the matrix V were set to zero to avoid self-connection, which was labeled as V . Then the brain functional network was represented as a weighted undirected graph G by the matrix V .Step 4. The attributes including the degree of nodes, the clustering coefficient and the global efficiency of brain network for each sample were computed. A feature vector combined these attributes was used for classification.Step 5. The LDA projection space was trained by training data. Test data were projected to the LDA projection space, and the category of the test sample was determined by the nearest neighbor rule.

Biometric Systems Utilising Health Data from Wearable Devices

“…The evaluation of BrainID shows 96.97% accuracy on 12 individuals. A similar paper also employed LDA for the classification of EEG signals [50]. The features were extracted by analysing the relationship among EEG channels with the help of phase synchronisation approach.…”

Multi-Granularity Analysis of Brain Networks Assembled With Intra-Frequency and Cross-Frequency Phase Coupling for Human EEG After Stroke

“…Therefore, the characteristic path length and clustering coefficient metrics of the OMST-based brain networks are larger than the brain networks based on the manual threshold method shown in Tables 7 , 8 . Manual thresholding-based brain network analysis is a potential feature selection method for EEG classification tasks (Kong et al, 2018 ; Huang et al, 2021 ). In future study, the comparison and evaluation of different topological filtering methods are worth deeply being studied.…”

A regression method for EEG-based cross-dataset fatigue detection

“…The framework can tackle the domain shift problem in the unlabeled target domain, which is a limitation to domain adaptation in sleep staging. Kong et al (2018) proposed a method for cross-dataset personal identification based on a brain network of EEG signals. The method used brain functional networks and linear discriminant analysis (LDA) to classify personal identification.…”