Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System
Despite the growing interest in the use of electroencephalogram (EEG) signals as a potential biometric for subject identification and the recent advances in the use of deep learning (DL) models to study neurological signals, such as electrocardiogram (ECG), electroencephalogram (EEG), electroretinog...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/23/9547 |
| _version_ | 1797462081572700160 |
|---|---|
| author | Mohamed Benomar Steven Cao Manoj Vishwanath Khuong Vo Hung Cao |
| author_facet | Mohamed Benomar Steven Cao Manoj Vishwanath Khuong Vo Hung Cao |
| author_sort | Mohamed Benomar |
| collection | DOAJ |
| description | Despite the growing interest in the use of electroencephalogram (EEG) signals as a potential biometric for subject identification and the recent advances in the use of deep learning (DL) models to study neurological signals, such as electrocardiogram (ECG), electroencephalogram (EEG), electroretinogram (ERG), and electromyogram (EMG), there has been a lack of exploration in the use of state-of-the-art DL models for EEG-based subject identification tasks owing to the high variability in EEG features across sessions for an individual subject. In this paper, we explore the use of state-of-the-art DL models such as ResNet, Inception, and EEGNet to realize EEG-based biometrics on the BED dataset, which contains EEG recordings from 21 individuals. We obtain promising results with an accuracy of 63.21%, 70.18%, and 86.74% for Resnet, Inception, and EEGNet, respectively, while the previous best effort reported accuracy of 83.51%. We also demonstrate the capabilities of these models to perform EEG biometric tasks in real-time by developing a portable, low-cost, real-time Raspberry Pi-based system that integrates all the necessary steps of subject identification from the acquisition of the EEG signals to the prediction of identity while other existing systems incorporate only parts of the whole system. |
| first_indexed | 2024-03-09T17:31:22Z |
| format | Article |
| id | doaj.art-e9c532cb8f534dc180e05f9b0ab439b5 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T17:31:22Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e9c532cb8f534dc180e05f9b0ab439b52023-11-24T12:16:12ZengMDPI AGSensors1424-82202022-12-012223954710.3390/s22239547Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based SystemMohamed Benomar0Steven Cao1Manoj Vishwanath2Khuong Vo3Hung Cao4Department of Electrical Engineering and Computer Science, University of California, Irvine, CA 92697, USANorthwood High School, Irvine, CA 92620, USADepartment of Computer Science, University of California, Irvine, CA 92697, USADepartment of Computer Science, University of California, Irvine, CA 92697, USADepartment of Electrical Engineering and Computer Science, University of California, Irvine, CA 92697, USADespite the growing interest in the use of electroencephalogram (EEG) signals as a potential biometric for subject identification and the recent advances in the use of deep learning (DL) models to study neurological signals, such as electrocardiogram (ECG), electroencephalogram (EEG), electroretinogram (ERG), and electromyogram (EMG), there has been a lack of exploration in the use of state-of-the-art DL models for EEG-based subject identification tasks owing to the high variability in EEG features across sessions for an individual subject. In this paper, we explore the use of state-of-the-art DL models such as ResNet, Inception, and EEGNet to realize EEG-based biometrics on the BED dataset, which contains EEG recordings from 21 individuals. We obtain promising results with an accuracy of 63.21%, 70.18%, and 86.74% for Resnet, Inception, and EEGNet, respectively, while the previous best effort reported accuracy of 83.51%. We also demonstrate the capabilities of these models to perform EEG biometric tasks in real-time by developing a portable, low-cost, real-time Raspberry Pi-based system that integrates all the necessary steps of subject identification from the acquisition of the EEG signals to the prediction of identity while other existing systems incorporate only parts of the whole system.https://www.mdpi.com/1424-8220/22/23/9547EEGbiometricsdeep learningRaspberry Pi |
| spellingShingle | Mohamed Benomar Steven Cao Manoj Vishwanath Khuong Vo Hung Cao Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System Sensors EEG biometrics deep learning Raspberry Pi |
| title | Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System |
| title_full | Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System |
| title_fullStr | Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System |
| title_full_unstemmed | Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System |
| title_short | Investigation of EEG-Based Biometric Identification Using State-of-the-Art Neural Architectures on a Real-Time Raspberry Pi-Based System |
| title_sort | investigation of eeg based biometric identification using state of the art neural architectures on a real time raspberry pi based system |
| topic | EEG biometrics deep learning Raspberry Pi |
| url | https://www.mdpi.com/1424-8220/22/23/9547 |
| work_keys_str_mv | AT mohamedbenomar investigationofeegbasedbiometricidentificationusingstateoftheartneuralarchitecturesonarealtimeraspberrypibasedsystem AT stevencao investigationofeegbasedbiometricidentificationusingstateoftheartneuralarchitecturesonarealtimeraspberrypibasedsystem AT manojvishwanath investigationofeegbasedbiometricidentificationusingstateoftheartneuralarchitecturesonarealtimeraspberrypibasedsystem AT khuongvo investigationofeegbasedbiometricidentificationusingstateoftheartneuralarchitecturesonarealtimeraspberrypibasedsystem AT hungcao investigationofeegbasedbiometricidentificationusingstateoftheartneuralarchitecturesonarealtimeraspberrypibasedsystem |