Subject Identification from Low-Density EEG-Recordings of Resting-States: A Study of Feature Extraction and Classification

Abstract

A new concept of low-density electroencephalograms-based (EEG) Subject identification is proposed in this paper. To that aim, EEG recordings of resting-states were analyzed with 3 different classifiers (SVM, k-NN, and naive Bayes) using Empirical Mode Decomposition (EMD) and Discrete Wavelet Transform (DWT) for feature extraction and their accuracies were estimated to compare their performances. To explore the feasibility of using fewer channels with minimum loss of accuracy, the methods were applied to a dataset of 27 Subjects (From 5 sessions of 30 instances per Subject) recorded using the EMOTIV EPOC device with 1 set of 14 channels and 4 subsets (8, 4, 2 and 1 channel) that were selected using a greedy algorithm. The experiments were reproduced using fewer instances each time to observe the evolution of the accuracy using both; fewer channels and fewer instances. The results of this experiments suggest that EMD compared with DWT is a more robust technique for feature extraction from brain signals to identify Subjects during resting-states, particularly when the amount of information is reduced: e.g., using Linear SVM and 30 instances per Subject, the accuracies obtained using 14 channels were 0.91 and 0.95, with 8 channels were 0.87 and 0.89 with EMD and DWT respectively but were reversed in favor of EMD when the number of channels was reduced to 4 channels (0.76 and 0.74), 2 (0.64 and 0.56) and 1 channel (0.46 and 0.31). The general observed trend is that, Linear SVM exhibits higher accuracy rates using high-density EEG (0.91 with 14 channels) while Gaussian naive Bayes exhibits better accuracies when using low-density EEG in comparison with the other classifiers (With EMD 0.88, 0.81, 0.76 and 0.61 respectively for 8, 4, 2 and 1 channel). The findings of these experiments reveal an important insight for continuing the exploration of low-density EEG for Subject identification.

Multi-objective optimization for EEG channel selection and accurate intruder detection in an EEG-based subject identification system

“…In our previous works, we have studied and compared various paradigms, i.e. resting-state potentials and ERPs, using various types of electrodes, a various number of channels, and channel localization [2][3][4]6 . Several parameters are yet to be optimized.…”

“…), record the brain activity corresponding to the response to the presentation, and use it for the identification and authentication process. The internal state of the subject, such as the resting state, could also be used as an alternative obtaining specific information on the subject, as discussed in our previous investigation 4 . The EEG channel selection process is in itself interesting because it can provide information about the most relevant areas in the brain for a certain neural task, for a certain subject or group of subjects.…”

“…Our research has been focused towards a portable (non-invasive) wireless dry single-channel or low-density EEG system for different applications, which can help the subjects identification process by providing EEG information from different channel combinations by using a movable sensor 4 . Following the results found in this work and other applications proposed previously, we will analyze the possibility of a fixed or movable electrode version of a new EEG headset which can incorporate the best results obtained in this work for subject identification and authentication.…”

“…A number of different paradigms are used to stimulate and record EEG signals in various subject identification approaches: imagined speech [1][2][3] , resting-state potentials 4,5 , and event-related potentials (ERPs) 6 . ERPs are very low-voltage signals emitted by the human brain that appears on the scalp in response to specific events or stimuli.…”

Sex differences observed in a study of EEG of linguistic activity and resting-state: Exploring optimal EEG channel configurations

“…The method used for feature extraction and classification is explained in [10] and the greedy algorithm used in [11].…”