Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/74034
Title: Mental fatigue detection from a brain computer interface(BCI)
Authors: Soh, Kok Weng
Keywords: DRNTU::Engineering::Computer science and engineering::Computer applications::Life and medical sciences
Issue Date: 2018
Abstract: Driving fatigue poses a dangerous threat to road safety due to the decline in the attention and reaction time of drivers. Thus, the development of a fatigue monitoring and feedback system for accident prevention has been a major focus in the field of driving safety. The system requires constant monitoring and estimate of the alertness of the driver. The aim of the project was to develop a new real-time electroencephalogram(EEG) based driving fatigue detection system via the usage of SVM. In order to gather data required for the training of the Support Vector Machines(SVM) an experiment was conducted which required the subjects to complete a 40 minute driving simulator task. A total of 48 features were computed from 4 different EEG channels to differentiate the alert and fatigued states. The features were then fed to a SVM classifier which yielded a raw and smoothed accuracy of 68.8% and 77%, respectively. The results indicated that the parameters can differentiate both states accurately. Thus, they were used to develop a new real-time EEG based driving fatigue detection system.
URI: http://hdl.handle.net/10356/74034
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Mental Fatigue From A BCI - Soh Kok Weng (U1522096B).pdf
  Restricted Access
1.22 MBAdobe PDFView/Open

Page view(s)

124
checked on Sep 25, 2020

Download(s)

24
checked on Sep 25, 2020

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.