CNN‐Based Personal Identification System Using Resting State Electroencephalography

Abstract

As a biometric characteristic, electroencephalography (EEG) signals have the advantages of being hard to steal and easy to detect liveness, which attract researchers to study EEG-based personal identification technique. Among different EEG protocols, resting state signals are the most practical option since it is more convenient to operate than the other protocols. In this paper, a personal identification system based on resting state EEG is proposed, in which data augmentation and convolutional neural network are combined. The cross-validation is performed on a public database of 109 subjects. The experimental results show that when only 14 EEG channels and 0.5 seconds data are employed, the average accuracy and average equal error rate of the system can reach 99.32% and 0.18%, respectively. Compared with some existing representative works, the proposed system has the advantages of short acquisition time, low computational complexity, and rapid deployment using market available low-cost EEG sensors, which further advances the implementation of practical EEG-based identification systems.

EEG-Based Person Identification during Escalating Cognitive Load

“…Traditional approaches in EEG-based biometric systems include manually extracted features and conventional classification algorithms such as linear discriminant analysis (LDA) [ 51 , 52 ], k-nearest neighbors (k-NN) [ 44 , 53 ], or support vector machine (SVM) [ 54 , 55 ]. Alternatively, deep learning (DL) algorithms [ 37 , 38 , 56 , 57 , 58 , 59 , 60 , 61 , 62 , 63 ] are becoming state-of-the-art in person identification and authentication. These algorithms are able to automate the feature extraction process and eliminate some of the manual human encroachment.…”

“…The highest classification accuracy belongs to open eyes, 88%, which exceeded the state of closed eyes for all examined scenarios. Fan Y. et al [ 37 ] proposed a personal identification system with a combination data augmentation and convolutional neural network based on resting-state EEG from a public database including 109 subjects. Their system reached an average accuracy of 99.32% using only 14 channels.…”

Electroencephalographic (EEG) based Deep Learning (DL): A Comparative Review

“…Physionet data set used by the ref. [4][5][6], [11], [17], [20], [23], [25], [27][28], [33], and [37][38][39] and work on the publicly available dataset consisting of EEG of 109 participants completing various motor/imagery duties, it's a popular benchmark for biometric with EEG. In [9] datasets from four different experiments measuring endogenous brain functions (driving fatigue and emotion) in addition to time-locked artificially created brain responses from 157 subjects, [5] datasets including emotion and combined data.…”

“…Additionally, the signals recorded by EEG systems must be carefully analyzed and interpreted to get useful data regarding the brain's electrical activity. In [2], [4][5][6], [9], [11], [14], [16][17][18][19], [20], [23], [25], [27][28], [30], [33], and [37][38][39] worked on BCI2000 system to record and analyzed EEG using 32 electrodes, while [1][8] [34][40] used AgCl electrodes EEG signals were recorded using a (Bio semi) Active Two system, EEG data were collected at a 512 sampling rate (Hz), AgCl with 32 electrodes works on the (10-20) of the international systems. Another device was using named GALILEO BE Light amplifier equipped with 19 channels/electrodes.…”

“…The design was tested on two baseline scenarios in (RS), (EC, and EO) as shown in [4], [14], [20], [25], [28], [36][37][38][39]. in [10] EC Use this trigger only with the data to build the model and extract the results.…”