Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/28288
Title: Signal processing methods for mental fatigue measurement and monitoring using EEG
Authors: SHEN KAIQUAN
Keywords: Mental fatigue, EEG, signal processing, feature selection, artifact removal, support vector machine
Issue Date: 13-Apr-2009
Source: SHEN KAIQUAN (2009-04-13). Signal processing methods for mental fatigue measurement and monitoring using EEG. ScholarBank@NUS Repository.
Abstract: This thesis is concerned with developing signal-processing methods that enable automatic mental-fatigue measuring and monitoring from the electroencephalogram (EEG) recordings: 1) to address the challenge of automatic removal of the pervasive EEG artifacts, an automatic EEG artifact-removal method is proposed, in which a weighted support vector machine (SVM) together with an error-correction algorithm is used for automatic identification and subsequent removal of artifactual components; 2) to identify the critical EEG features pertinent to mental fatigue, new feature-selection methods are also proposed by exploiting a novel feature-ranking criterion based on the sensitivity analysis of posterior probabilities; 3) to continuously monitor mental fatigue at different levels, a comprehensive pattern recognition system is established. The experimental results of the proposed methods, tested on EEG data recorded from 22 subjects (each underwent a 25-hour sleep deprivation), demonstrated the feasibility of an automatic, objective and non-intrusive EEG method for assessing and monitoring of mental fatigue.
URI: http://scholarbank.nus.edu.sg/handle/10635/28288
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
thesis-KQShen.pdf2.02 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

282
checked on Jan 18, 2018

Download(s)

763
checked on Jan 18, 2018

Google ScholarTM

Check


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