Convolutional Neural Network for Drowsiness Detection Using EEG Signals
- Publikationstyp:
- Zeitschriftenaufsatz
- Metadaten:
-
- Autoren
- Siwar Chaabene
- Bassem Bouaziz
- Amal Boudaya
- Anita Hoekelmann
- Achraf Ammar
- Lotfi Chaari
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000628541000001&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.3390/s21051734
- eISSN
- 1424-8220
- Externe Identifier
- Clarivate Analytics Document Solution ID: QW3FY
- PubMed Identifier: 33802357
- Ausgabe der Veröffentlichung
- 5
- Zeitschrift
- SENSORS
- Schlüsselwörter
- drowsiness detection
- EEG signals
- Emotiv EPOC+
- deep learning
- data augmentation
- convolutional neural networks
- classification
- awake/drowsy states
- Artikelnummer
- ARTN 1734
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Titel
- Convolutional Neural Network for Drowsiness Detection Using EEG Signals
- Sub types
- Article
- Ausgabe der Zeitschrift
- 21
Datenquelle: Web of Science (Lite)
- Andere Metadatenquellen:
-
- Abstract
- <jats:p>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 Emotiv EPOC+ 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.</jats:p>
- Autoren
- Siwar Chaabene
- Bassem Bouaziz
- Amal Boudaya
- Anita Hökelmann
- Achraf Ammar
- Lotfi Chaari
- DOI
- 10.3390/s21051734
- eISSN
- 1424-8220
- Ausgabe der Veröffentlichung
- 5
- Zeitschrift
- Sensors
- Sprache
- en
- Online publication date
- 2021
- Paginierung
- 1734 - 1734
- Status
- Published online
- Herausgeber
- MDPI AG
- Herausgeber URL
- http://dx.doi.org/10.3390/s21051734
- Datum der Datenerfassung
- 2021
- Titel
- Convolutional Neural Network for Drowsiness Detection Using EEG Signals
- Ausgabe der Zeitschrift
- 21
Datenquelle: Crossref
- Abstract
- 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+</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.
- Addresses
- Multimedia InfoRmation Systems and Advanced Computing Laboratory (MIRACL), University of Sfax, Sfax 3021, Tunisia.
- Autoren
- Siwar Chaabene
- Bassem Bouaziz
- Amal Boudaya
- Anita Hökelmann
- Achraf Ammar
- Lotfi Chaari
- DOI
- 10.3390/s21051734
- eISSN
- 1424-8220
- Externe Identifier
- PubMed Identifier: 33802357
- PubMed Central ID: PMC7959292
- Open access
- true
- ISSN
- 1424-8220
- Ausgabe der Veröffentlichung
- 5
- Zeitschrift
- Sensors (Basel, Switzerland)
- Schlüsselwörter
- Electroencephalography
- Wakefulness
- Signal Processing, Computer-Assisted
- Neural Networks, Computer
- Sprache
- eng
- Medium
- Electronic
- Online publication date
- 2021
- Open access status
- Open Access
- Paginierung
- 1734
- Datum der Veröffentlichung
- 2021
- Status
- Published
- Publisher licence
- CC BY
- Datum der Datenerfassung
- 2021
- Titel
- Convolutional Neural Network for Drowsiness Detection Using EEG Signals.
- Sub types
- research-article
- Journal Article
- Ausgabe der Zeitschrift
- 21
Files
https://www.mdpi.com/1424-8220/21/5/1734/pdf?version=1614764840 https://europepmc.org/articles/PMC7959292?pdf=render
Datenquelle: Europe PubMed Central
- Abstract
- 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 Emotiv EPOC+ 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.
- Date of acceptance
- 2021
- Autoren
- Siwar Chaabene
- Bassem Bouaziz
- Amal Boudaya
- Anita Hökelmann
- Achraf Ammar
- Lotfi Chaari
- Autoren-URL
- https://www.ncbi.nlm.nih.gov/pubmed/33802357
- DOI
- 10.3390/s21051734
- eISSN
- 1424-8220
- Externe Identifier
- PubMed Central ID: PMC7959292
- Ausgabe der Veröffentlichung
- 5
- Zeitschrift
- Sensors (Basel)
- Schlüsselwörter
- EEG signals
- Emotiv EPOC+
- awake/drowsy states
- classification
- convolutional neural networks
- data augmentation
- deep learning
- drowsiness detection
- Electroencephalography
- Neural Networks, Computer
- Signal Processing, Computer-Assisted
- Wakefulness
- Sprache
- eng
- Country
- Switzerland
- PII
- s21051734
- Datum der Veröffentlichung
- 2021
- Status
- Published online
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2021
- Titel
- Convolutional Neural Network for Drowsiness Detection Using EEG Signals.
- Sub types
- Journal Article
- Ausgabe der Zeitschrift
- 21
Datenquelle: PubMed
- Beziehungen:
- Eigentum von