Efficient Generalized Electroencephalography-Based Drowsiness Detection Approach with Minimal Electrodes DOI Creative Commons

Aymen Zayed,

Nidhameddine Belhadj, Khaled Ben Khalifa

и другие.

Sensors, Год журнала: 2024, Номер 24(13), С. 4256 - 4256

Опубликована: Июнь 30, 2024

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance mentioned areas. The implementation drowsiness detection system can greatly help reduce defects accident rates by alerting individuals when they enter drowsy state. This research proposes an electroencephalography (EEG)-based approach detecting drowsiness. EEG signals are passed through preprocessing chain composed artifact removal segmentation ensure accurate followed different feature extraction methods extract features related work explores use machine learning algorithms Support Vector Machine (SVM), K nearest neighbor (KNN), Naive Bayes (NB), Decision Tree (DT), Multilayer Perceptron (MLP) analyze sourced from DROZY database, carefully labeled into two distinct states alertness (awake drowsy). Segmentation 10 s intervals ensures precise detection, while relevant selection layer enhances accuracy generalizability. proposed achieves high 99.84% 96.4% intra (subject subject) inter (cross-subject) modes, respectively. SVM emerges most effective model mode, MLP demonstrates superior mode. offers promising avenue implementing proactive systems enhance occupational safety across industries.

Язык: Английский

Efficient Generalized EEG-Based Drowsiness Detection Approach with Minimal Electrodes DOI Open Access

Aymen Zayed,

Nidhameddine Belhadj, Khaled Ben Khalifa

и другие.

Опубликована: Май 24, 2024

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance mentioned areas. The implementation drowsiness detection system can greatly help reduce defects accident rates by alerting individuals when they enter drowsy state. This research proposes an Electroencephalography (EEG) based approach detecting drowsiness. EEG signals are passed through preprocessing chain composed artifact removal segmentation ensure accurate followed different feature extraction methods extract features related work explores use machine learning algorithms Support Vector Machine (SVM) K Nearest Neighbor (KNN) Naive Bayes (NB) Decision Tree (DT) Multilayer Perceptron (MLP) analyze sourced from DROZY database, carefully labeled into two distinct states alertness (awake, drowsy). Segmentation 10-second intervals ensures precise detection, while relevant selection layer enhances accuracy generalizability. proposed achieves high 99.84% 96.4% intra (subject subject) inter (cross-subject) modes, respectively. SVM emerges most effective model mode, MLP demonstrates superior mode. offers promising avenue implementing proactive systems enhance occupational safety across industries.

Язык: Английский

Процитировано

2
Efficient Generalized Electroencephalography-Based Drowsiness Detection Approach with Minimal Electrodes DOI Creative Commons

Aymen Zayed,

Nidhameddine Belhadj, Khaled Ben Khalifa

и другие.

Sensors, Год журнала: 2024, Номер 24(13), С. 4256 - 4256

Опубликована: Июнь 30, 2024

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance mentioned areas. The implementation drowsiness detection system can greatly help reduce defects accident rates by alerting individuals when they enter drowsy state. This research proposes an electroencephalography (EEG)-based approach detecting drowsiness. EEG signals are passed through preprocessing chain composed artifact removal segmentation ensure accurate followed different feature extraction methods extract features related work explores use machine learning algorithms Support Vector Machine (SVM), K nearest neighbor (KNN), Naive Bayes (NB), Decision Tree (DT), Multilayer Perceptron (MLP) analyze sourced from DROZY database, carefully labeled into two distinct states alertness (awake drowsy). Segmentation 10 s intervals ensures precise detection, while relevant selection layer enhances accuracy generalizability. proposed achieves high 99.84% 96.4% intra (subject subject) inter (cross-subject) modes, respectively. SVM emerges most effective model mode, MLP demonstrates superior mode. offers promising avenue implementing proactive systems enhance occupational safety across industries.

Язык: Английский

Процитировано

0