Journal
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
Volume 29, Issue -, Pages 905-915Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2021.3079505
Keywords
Electroencephalography; Fatigue; Calibration; Task analysis; Electrodes; Signal to noise ratio; Entropy; Driver’ s drowsiness detection; electroencephalography; recurrence plot; Gramian angular fields; convolutional neural network
Categories
Funding
- Portuguese Foundation for Science and Technology (FCT) [B-RELIABLE-PTDC/EEIAUT/30935/2017]
- Institute of Systems and Robotics, University of Coimbra (ISR-UC) FCT grant, Portugal [UIDB/00048/2020]
Ask authors/readers for more resources
This paper explores two methodologies for drowsiness detection using EEG signals in a sustained-attention driving task, focusing on cross-subject zero calibration. Comparison of both techniques on a public dataset of 27 subjects shows a superior balanced accuracy of up to 75.87% for leave-one-out cross-validation, demonstrating the possibility to pursue cross-subject zero calibration design.
This paper explores two methodologies for drowsiness detection using EEG signals in a sustained-attention driving task considering pre-event time windows, and focusing on cross-subject zero calibration. Driving accidents are a major cause of injuries and deaths on the road. A considerable portion of those are due to fatigue and drowsiness. Advanced driver assistance systems that could detect mental states which are associated with hazardous situations, such as drowsiness, are of critical importance. EEG signals are used widely for brain-computer interfaces, as well as mental state recognition. However, these systems are still difficult to design due to very low signal-to-noise ratios and cross-subject disparities, requiring individual calibration cycles. To tackle this research domain, here, we explore drowsiness detection based on EEG signals' spatiotemporal image encoding representations in the form of either recurrence plots or gramian angular fields for deep convolutional neural network (CNN) classification. Results comparing both techniques using a public dataset of 27 subjects show a superior balanced accuracy of up to 75.87% for leave-one-out cross-validation, using both techniques, against works in the literature, demonstrating the possibility to pursue cross-subject zero calibration design.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available