Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/118195
DC FieldValue
dc.titleModelling and Classification of Motor Imagery EEG for BCI
dc.contributor.authorLI XINYANG
dc.date.accessioned2014-12-31T18:00:21Z
dc.date.available2014-12-31T18:00:21Z
dc.date.issued2014-08-14
dc.identifier.citationLI XINYANG (2014-08-14). Modelling and Classification of Motor Imagery EEG for BCI. ScholarBank@NUS Repository.
dc.identifier.urihttp://scholarbank.nus.edu.sg/handle/10635/118195
dc.description.abstractDiscriminative analysis of EEG signals is crucial for the usability and reliability of brain computer interface (BCI) systems based on motor imagery EEG. This thesis has studied feature extraction for motor imagery EEG classification in BCI from the perspectives of model generalization and adaptation. In the presence of causal relationships in EEG signals, a computational model has been constructed for discriminative learning of propagation and spatial patterns. Ensemble learning of spatial filters has been proposed to improve the model generalization by considering the data-model mismatch. This mismatch has been investigated for model adaption to address the issue of significant signal nonstationarity. The relationship between the shift of discriminative subspaces and that in feature spaces has been analyzed. Experimental studies have been conducted to validate the proposed methods.
dc.language.isoen
dc.subjectEEG, motor imagery, brain computer interface, feature extraction, signal processing, classification
dc.typeThesis
dc.contributor.departmentNUS GRAD SCH FOR INTEGRATIVE SCI & ENGG
dc.contributor.supervisorONG SIM HENG
dc.description.degreePh.D
dc.description.degreeconferredDOCTOR OF PHILOSOPHY
dc.identifier.isiutNOT_IN_WOS
Appears in Collections:Ph.D Theses (Open)

Show simple item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
LiXY.pdf1.23 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

257
checked on Jan 16, 2021

Download(s)

286
checked on Jan 16, 2021

Google ScholarTM

Check


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