EEG features for driver’s mental fatigue detection: a preliminary work

Mental fatigue is one of the most typical human infirmities, resulting from an overload of work and lack of sleep which can reduce one’s intellectual resources. Different EEG features have been studied for detecting mental fatigue. This paper characterizes mental fatigue through the understanding...

Full description

Saved in:
Bibliographic Details
Main Authors: Kamaruzzaman, Muhammad Afiq 'Ammar, Othman, Marini, Hassan, Raini, Abdul Rahman, Abdul Wahab, Mahri, Nurhafizah
Format: Article
Language:English
Published: IIUM Press 2023
Subjects:
Online Access:http://irep.iium.edu.my/104330/1/104330_EEG%20features%20for%20driver%E2%80%99s%20mental%20fatigue.pdf
http://irep.iium.edu.my/104330/
https://journals.iium.edu.my/kict/index.php/IJPCC/article/view/355
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Mental fatigue is one of the most typical human infirmities, resulting from an overload of work and lack of sleep which can reduce one’s intellectual resources. Different EEG features have been studied for detecting mental fatigue. This paper characterizes mental fatigue through the understanding of human EEG features for safe driving behaviour and to create an overview of the potential EEG features which are related to mental fatigue. A narrative review approach is employed for describing the neural activity of the human brain in mental fatigue. Specific EEG features in relation to driving tasks, relation to different EEG band waves, pre-processing and feature extraction methods are discussed. From this preliminary work, the increase of parietal alpha power seems to characterize the driver’s mental fatigue in most of the studies. We searched public EEG repositories for identifying potential data sources for our initial study. Finally, we propose a conceptual model that has potentials for identifying mental weariness. In conclusion, future works may involve the identification of other EEG features of higher importance for generalization across study conditions.