Cited 0 time in webofscience Cited 0 time in scopus

Driver Drowsiness Detection Using EEG Features

Title
Driver Drowsiness Detection Using EEG Features
Authors
Hwang, Se-HyeonPark, MyoungoukKim, JonghwaYun, YongwonSon, Joonwoo
DGIST Authors
Son, Joonwoo
Issue Date
2018-07-19
Citation
20th International Conference on HCI, HCI International 2018, 367-374
Type
Conference
ISBN
9783319922843
ISSN
1865-0929
Abstract
The objective of this paper is to discover the EEG (Electroencephalogram) features that expressed meaningful changes during drowsy driving state compared to the normal driving. For this purpose, 8 healthy male and female participants were recruited to conduct drowsy driving experiment in a fixed-base driving simulator, which reproduced the inside of the actual vehicle. The experimental scenario was driving a 37 km straight highway without any obstacles. The data obtained through this experiment were analyzed using brain wave analysis software. As a result, we found that the alpha RMS (Root mean square) and differentiated alpha RMS waves showed meaningful changes during drowsiness state compared to normal state. In addition, we suggested new brain activity index, which was composed of four brain waves that are alpha, beta, theta and delta, to amplify meaningful change in transition from normal state to drowsiness. The statistical significances of the selected EEG features were tested using One-way ANOVA (Analysis of variance). The result indicated that all three EEG features showed statistical significance (p < 0.005). In conclusion, this paper suggested EEG features which have high accuracy for drowsiness detection. Currently, EEG measurement equipment such as dry type and non-contact type is actively developed. Therefore, it is expected that the drowsiness prevention system using the EEG features will be available in the near future. © Springer International Publishing AG, part of Springer Nature 2018.
URI
http://hdl.handle.net/20.500.11750/9589
DOI
10.1007/978-3-319-92285-0_49
Publisher
Springer
Related Researcher
Files:
There are no files associated with this item.
Collection:
Companion Diagnostics and Medical Technology Research Group2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE