Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals

Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals

Abstract: Driver fatigue is a major cause of traffic accidents. Electroencephalogram (EEG) is considered one of the most reliable predictors of fatigue. This paper proposes a novel, simple and fast method for driver fatigue detection that can be implemented in real-time by using a single-channel on the scalp. The study has two objectives. The first consists of determining the single most relevant EEG channel to monitor fatigue. This is done using maximum covariance analysis. The second objective consists in developing a deep learning method to detect fatigue from this single channel. For this purpose, spectral features of the signal are first extracted. The sequence of features is used to train a Long Short Term Memory (LSTM), deep learning model, to detect fatigue states. Experiments with 12 EEG signals were conducted to discriminate the fatigue stage from the alert stage. Results showed that TP7 was the most significant channel, which is located in the left tempo-parietal region. A zone associated with spatial awareness, visual-spatial navigation, and the cautiousness faculty. In addition, despite the small dataset, the proposed method predicts fatigue with 75% accuracy and a 1.4-second delay. These promising results provide new insights into relevant data for monitoring driver fatigue.

Saved in:
Bibliographic Details
Main Authors: Quintero Rincón, Antonio, Chaari, Lotfi, Batatia, Hadj
Format: Artículo biblioteca
Language:eng
Published: Institute of Electrical and Electronics Engineers 2022
Subjects:CONDUCTOR, INNOVACION TECNOLOGICA, FATIGA, ELECTROENCEFALOGRAFÍA, REDES GENERATIVAS ADVERSARIAS, APRENDIZAJE PROFUNDO,
Online Access:https://repositorio.uca.edu.ar/handle/123456789/17073
Tags: Add Tag
No Tags, Be the first to tag this record!
id oai:ucacris:123456789-17073
record_format koha
spelling oai:ucacris:123456789-170732023-09-19T19:47:15Z Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals Quintero Rincón, Antonio Chaari, Lotfi Batatia, Hadj CONDUCTOR INNOVACION TECNOLOGICA FATIGA ELECTROENCEFALOGRAFÍA REDES GENERATIVAS ADVERSARIAS APRENDIZAJE PROFUNDO Abstract: Driver fatigue is a major cause of traffic accidents. Electroencephalogram (EEG) is considered one of the most reliable predictors of fatigue. This paper proposes a novel, simple and fast method for driver fatigue detection that can be implemented in real-time by using a single-channel on the scalp. The study has two objectives. The first consists of determining the single most relevant EEG channel to monitor fatigue. This is done using maximum covariance analysis. The second objective consists in developing a deep learning method to detect fatigue from this single channel. For this purpose, spectral features of the signal are first extracted. The sequence of features is used to train a Long Short Term Memory (LSTM), deep learning model, to detect fatigue states. Experiments with 12 EEG signals were conducted to discriminate the fatigue stage from the alert stage. Results showed that TP7 was the most significant channel, which is located in the left tempo-parietal region. A zone associated with spatial awareness, visual-spatial navigation, and the cautiousness faculty. In addition, despite the small dataset, the proposed method predicts fatigue with 75% accuracy and a 1.4-second delay. These promising results provide new insights into relevant data for monitoring driver fatigue. 2023-09-07T11:04:10Z 2023-09-07T11:04:10Z 2022 Artículo Quintero Rincón, A., Chaari, L., Batatia, H. Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals [en línea]. 2022 International Conference on Technology Innovations for Healthcare (ICTIH) : 14 al 16 de septiembre. Magdeburg ; Alemania, 2022. doi: 10.1109/ICTIH57289.2022.10111943. Disponible en: https://repositorio.uca.edu.ar/handle/123456789/17073 2169-3536 https://repositorio.uca.edu.ar/handle/123456789/17073 10.1109/ICTIH57289.2022.10111943 eng Estimación del retardo de tiempo en trenes de espigas en señales electroencefalográficas (EEG) Acceso restringido http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers 2022 International Conference on Technology Innovations for Healthcare (ICTIH) : 14 al 16 de septiembre. Magdeburg ; Alemania, 2022
institution UCA
collection DSpace
country Argentina
countrycode AR
component Bibliográfico
access En linea
databasecode dig-uca
tag biblioteca
region America del Sur
libraryname Sistema de bibliotecas de la UCA
language eng
topic CONDUCTOR
INNOVACION TECNOLOGICA
FATIGA
ELECTROENCEFALOGRAFÍA
REDES GENERATIVAS ADVERSARIAS
APRENDIZAJE PROFUNDO
CONDUCTOR
INNOVACION TECNOLOGICA
FATIGA
ELECTROENCEFALOGRAFÍA
REDES GENERATIVAS ADVERSARIAS
APRENDIZAJE PROFUNDO
spellingShingle CONDUCTOR
INNOVACION TECNOLOGICA
FATIGA
ELECTROENCEFALOGRAFÍA
REDES GENERATIVAS ADVERSARIAS
APRENDIZAJE PROFUNDO
CONDUCTOR
INNOVACION TECNOLOGICA
FATIGA
ELECTROENCEFALOGRAFÍA
REDES GENERATIVAS ADVERSARIAS
APRENDIZAJE PROFUNDO
Quintero Rincón, Antonio
Chaari, Lotfi
Batatia, Hadj
Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
description Abstract: Driver fatigue is a major cause of traffic accidents. Electroencephalogram (EEG) is considered one of the most reliable predictors of fatigue. This paper proposes a novel, simple and fast method for driver fatigue detection that can be implemented in real-time by using a single-channel on the scalp. The study has two objectives. The first consists of determining the single most relevant EEG channel to monitor fatigue. This is done using maximum covariance analysis. The second objective consists in developing a deep learning method to detect fatigue from this single channel. For this purpose, spectral features of the signal are first extracted. The sequence of features is used to train a Long Short Term Memory (LSTM), deep learning model, to detect fatigue states. Experiments with 12 EEG signals were conducted to discriminate the fatigue stage from the alert stage. Results showed that TP7 was the most significant channel, which is located in the left tempo-parietal region. A zone associated with spatial awareness, visual-spatial navigation, and the cautiousness faculty. In addition, despite the small dataset, the proposed method predicts fatigue with 75% accuracy and a 1.4-second delay. These promising results provide new insights into relevant data for monitoring driver fatigue.
format Artículo
topic_facet CONDUCTOR
INNOVACION TECNOLOGICA
FATIGA
ELECTROENCEFALOGRAFÍA
REDES GENERATIVAS ADVERSARIAS
APRENDIZAJE PROFUNDO
author Quintero Rincón, Antonio
Chaari, Lotfi
Batatia, Hadj
author_facet Quintero Rincón, Antonio
Chaari, Lotfi
Batatia, Hadj
author_sort Quintero Rincón, Antonio
title Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
title_short Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
title_full Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
title_fullStr Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
title_full_unstemmed Robust analysis and spectral-based deep learning to detect driving fatigue from EEG signals
title_sort robust analysis and spectral-based deep learning to detect driving fatigue from eeg signals
publisher Institute of Electrical and Electronics Engineers
publishDate 2022
url https://repositorio.uca.edu.ar/handle/123456789/17073
work_keys_str_mv AT quinterorinconantonio robustanalysisandspectralbaseddeeplearningtodetectdrivingfatiguefromeegsignals
AT chaarilotfi robustanalysisandspectralbaseddeeplearningtodetectdrivingfatiguefromeegsignals
AT batatiahadj robustanalysisandspectralbaseddeeplearningtodetectdrivingfatiguefromeegsignals
_version_ 1777662005306458112

Similar Items