EEG-Based Hypo-vigilance Detection
Using Convolutional Neural Network
Amal Boudaya
1,2(B) , Bassem Bouaziz
1,2(B) , Siwar Chaabene
1,2 , Lotfi Chaari
3 ,
Achraf Ammar
4 , and Anita H¨ okelmann
4
1 Multimedia InfoRmation Systems and Advanced Computing Laboratory
(MIRACL), University of Sfax, 3021 Sfax, Tunisia
amalboudaya71@gmail.com, Bassem.Bouaziz@isims.usf.tn,
siwarchaabene@gmail.com
2 Digital Research Center of Sfax, B.P. 275, 3021 Sakiet Ezzit, Sfax, Tunisia
3 University of Toulouse, IRIT-ENSEEIHT, Toulouse, France
lotfi.chaari@toulouse-inp.fr
4 Institute of Sport Science, Otto-von-Guericke University Magdeburg,
39104 Magdeburg, Germany
ammar.achraf@ymail.com, anita.hoekelmann@ovgu.de
Abstract. Hypo-vigilance detection is becoming an important active
research areas in the biomedical signal processing field. For this purpose,
electroencephalogram (EEG) is one of the most common modalities in
drowsiness and awakeness detection. In this context, we propose a new
EEG classification method for detecting fatigue state. Our method makes
use of a and awakeness detection. In this context, we propose a new EEG
classification method for detecting fatigue state. Our method makes use
of a Convolutional Neural Network (CNN) architecture. We define an
experimental protocol using the Emotiv EPOC+ headset. After that, we
evaluate our proposed method on a recorded and annotated dataset. The
reported results demonstrate high detection accuracy (93%) and indicate
that the proposed method is an efficient alternative for hypo-vigilance
detection as compared with other methods.
Keywords: Hypo-vigilance detection · EEG · CNN
1 Introduction
Hypo-vigilance has been one of the major causes of accidents in many areas
such as driving [1], aviation [2] and military sector [3]. Hence, the drowsiness
problem has gained great interest from researchers. This is today a real up to
date problem within the current Covid-19 [4] pandemic where medical stuff is
generally overbooked. In fact, the drowsy condition is expressed predominantly
by the emergence of various behavioral signs such as heaviness in terms of reaction, reflex reduction, occurrences of yawning, heaviness of the eyelids and/or
the difficulty of keeping the head in the frontal position relative to the field of
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 69–78, 2020.
https://doi.org/10.1007/978-3-030-51517-1_6
Using Convolutional Neural Network
Amal Boudaya
1,2(B) , Bassem Bouaziz
1,2(B) , Siwar Chaabene
1,2 , Lotfi Chaari
3 ,
Achraf Ammar
4 , and Anita H¨ okelmann
4
1 Multimedia InfoRmation Systems and Advanced Computing Laboratory
(MIRACL), University of Sfax, 3021 Sfax, Tunisia
amalboudaya71@gmail.com, Bassem.Bouaziz@isims.usf.tn,
siwarchaabene@gmail.com
2 Digital Research Center of Sfax, B.P. 275, 3021 Sakiet Ezzit, Sfax, Tunisia
3 University of Toulouse, IRIT-ENSEEIHT, Toulouse, France
lotfi.chaari@toulouse-inp.fr
4 Institute of Sport Science, Otto-von-Guericke University Magdeburg,
39104 Magdeburg, Germany
ammar.achraf@ymail.com, anita.hoekelmann@ovgu.de
Abstract. Hypo-vigilance detection is becoming an important active
research areas in the biomedical signal processing field. For this purpose,
electroencephalogram (EEG) is one of the most common modalities in
drowsiness and awakeness detection. In this context, we propose a new
EEG classification method for detecting fatigue state. Our method makes
use of a and awakeness detection. In this context, we propose a new EEG
classification method for detecting fatigue state. Our method makes use
of a Convolutional Neural Network (CNN) architecture. We define an
experimental protocol using the Emotiv EPOC+ headset. After that, we
evaluate our proposed method on a recorded and annotated dataset. The
reported results demonstrate high detection accuracy (93%) and indicate
that the proposed method is an efficient alternative for hypo-vigilance
detection as compared with other methods.
Keywords: Hypo-vigilance detection · EEG · CNN
1 Introduction
Hypo-vigilance has been one of the major causes of accidents in many areas
such as driving [1], aviation [2] and military sector [3]. Hence, the drowsiness
problem has gained great interest from researchers. This is today a real up to
date problem within the current Covid-19 [4] pandemic where medical stuff is
generally overbooked. In fact, the drowsy condition is expressed predominantly
by the emergence of various behavioral signs such as heaviness in terms of reaction, reflex reduction, occurrences of yawning, heaviness of the eyelids and/or
the difficulty of keeping the head in the frontal position relative to the field of
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 69–78, 2020.
https://doi.org/10.1007/978-3-030-51517-1_6