Convolutional Neural Network for Drowsiness Detection Using EEG Signals
Drowsiness detection (DD) has become a relevant area of active research in biomedical signal processing. Recently, various deep learning (DL) researches based on the EEG signals have been proposed to detect fatigue conditions. The research presented in this paper proposes an EEG classification syste...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/5/1734 |
| _version_ | 1827603944137818112 |
|---|---|
| author | Siwar Chaabene Bassem Bouaziz Amal Boudaya Anita Hökelmann Achraf Ammar Lotfi Chaari |
| author_facet | Siwar Chaabene Bassem Bouaziz Amal Boudaya Anita Hökelmann Achraf Ammar Lotfi Chaari |
| author_sort | Siwar Chaabene |
| collection | DOAJ |
| description | Drowsiness detection (DD) has become a relevant area of active research in biomedical signal processing. Recently, various deep learning (DL) researches based on the EEG signals have been proposed to detect fatigue conditions. The research presented in this paper proposes an EEG classification system for DD based on DL networks. However, the proposed DD system is mainly realized into two procedures; (i) data acquisition and (ii) model analysis. For the data acquisition procedure, two key steps are considered, which are the signal collection using a wearable <i>Emotiv EPOC<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mo>+</mo></msup></semantics></math></inline-formula></i> headset to record 14 channels of EEG, and the signal annotation. Furthermore, a data augmentation (DA) step has been added to the proposed system to overcome the problem of over-fitting and to improve accuracy. As regards the model analysis, a comparative study is also introduced in this paper to argue the choice of DL architecture and frameworks used in our DD system. In this sense, The proposed DD protocol makes use of a convolutional neural network (CNN) architecture implemented using the Keras library. The results showed a high accuracy value (90.42%) in drowsy/awake discrimination and revealed the efficiency of the proposed DD system compared to other research works. |
| first_indexed | 2024-03-09T05:49:55Z |
| format | Article |
| id | doaj.art-2a58505d89254a44be4eac732507a68c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:49:55Z |
| publishDate | 2021-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-2a58505d89254a44be4eac732507a68c2023-12-03T12:18:09ZengMDPI AGSensors1424-82202021-03-01215173410.3390/s21051734Convolutional Neural Network for Drowsiness Detection Using EEG SignalsSiwar Chaabene0Bassem Bouaziz1Amal Boudaya2Anita Hökelmann3Achraf Ammar4Lotfi Chaari5Multimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL), University of Sfax, Sfax 3021, TunisiaMultimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL), University of Sfax, Sfax 3021, TunisiaMultimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL), University of Sfax, Sfax 3021, TunisiaInstitute of Sport Science, Otto-von-Guericke University Magdeburg, 39104 Magdeburg, GermanyInstitute of Sport Science, Otto-von-Guericke University Magdeburg, 39104 Magdeburg, GermanyIRIT-ENSEEIHT, University of Toulouse, 31013 Toulouse, FranceDrowsiness detection (DD) has become a relevant area of active research in biomedical signal processing. Recently, various deep learning (DL) researches based on the EEG signals have been proposed to detect fatigue conditions. The research presented in this paper proposes an EEG classification system for DD based on DL networks. However, the proposed DD system is mainly realized into two procedures; (i) data acquisition and (ii) model analysis. For the data acquisition procedure, two key steps are considered, which are the signal collection using a wearable <i>Emotiv EPOC<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><msup><mrow></mrow><mo>+</mo></msup></semantics></math></inline-formula></i> headset to record 14 channels of EEG, and the signal annotation. Furthermore, a data augmentation (DA) step has been added to the proposed system to overcome the problem of over-fitting and to improve accuracy. As regards the model analysis, a comparative study is also introduced in this paper to argue the choice of DL architecture and frameworks used in our DD system. In this sense, The proposed DD protocol makes use of a convolutional neural network (CNN) architecture implemented using the Keras library. The results showed a high accuracy value (90.42%) in drowsy/awake discrimination and revealed the efficiency of the proposed DD system compared to other research works.https://www.mdpi.com/1424-8220/21/5/1734drowsiness detectionEEG signals<i>Emotiv EPOC</i><sup>+</sup>deep learningdata augmentationconvolutional neural networks |
| spellingShingle | Siwar Chaabene Bassem Bouaziz Amal Boudaya Anita Hökelmann Achraf Ammar Lotfi Chaari Convolutional Neural Network for Drowsiness Detection Using EEG Signals Sensors drowsiness detection EEG signals <i>Emotiv EPOC</i><sup>+</sup> deep learning data augmentation convolutional neural networks |
| title | Convolutional Neural Network for Drowsiness Detection Using EEG Signals |
| title_full | Convolutional Neural Network for Drowsiness Detection Using EEG Signals |
| title_fullStr | Convolutional Neural Network for Drowsiness Detection Using EEG Signals |
| title_full_unstemmed | Convolutional Neural Network for Drowsiness Detection Using EEG Signals |
| title_short | Convolutional Neural Network for Drowsiness Detection Using EEG Signals |
| title_sort | convolutional neural network for drowsiness detection using eeg signals |
| topic | drowsiness detection EEG signals <i>Emotiv EPOC</i><sup>+</sup> deep learning data augmentation convolutional neural networks |
| url | https://www.mdpi.com/1424-8220/21/5/1734 |
| work_keys_str_mv | AT siwarchaabene convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals AT bassembouaziz convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals AT amalboudaya convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals AT anitahokelmann convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals AT achrafammar convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals AT lotfichaari convolutionalneuralnetworkfordrowsinessdetectionusingeegsignals |