000000704 001__ 704
000000704 005__ 20260120144837.0
000000704 0247_ $$2DOI$$a10.6083/M4RX9920
000000704 037__ $$aETD
000000704 245__ $$aFeature extraction feature selection and dimensionality reduction techniques for brain computer interface
000000704 260__ $$bOregon Health and Science University
000000704 269__ $$a2011
000000704 336__ $$aDissertation
000000704 502__ $$bPh.D.
000000704 520__ $$aBrain–Computer Interfaces (BCIs) enable direct communication between the brain and computers, offering non-muscular control for applications such as rehabilitation, performance augmentation, and target recognition. Modern non-invasive BCIs rely on EEG signals and machine learning techniques for interpretation, but challenges of robustness, real-time processing, and nonstationarity persist. This thesis investigates feature manipulation—encompassing extraction, selection, and dimensionality reduction—as a strategy to address these issues. Two applications are explored: Augmented Cognition (AugCog) and single-trial Event-Related Potential (ERP) detection. For AugCog, novel linear and nonlinear feature selection methods using Mutual Information and a statistical similarity-based extraction approach are developed. For ERP detection, comparative analyses of feature techniques across time, frequency, and spatial domains are presented. Experimental results demonstrate improved BCI performance over baseline systems, and guidelines for selecting appropriate methods based on data structure are provided.
000000704 540__ $$fCC BY
000000704 542__ $$fIn copyright - single owner
000000704 650__ $$aBrain-Computer Interfaces$$040031
000000704 650__ $$aEvoked Potentials$$018758
000000704 650__ $$aMachine Learning$$011449
000000704 650__ $$aCognition$$016868
000000704 650__ $$aUser-Computer Interface$$027668
000000704 650__ $$aArtificial Intelligence$$015109
000000704 650__ $$aElectroencephalography$$018287
000000704 691__ $$aSchool of Medicine$$041369
000000704 692__ $$aDepartment of Biomedical Engineering$$041397
000000704 7001_ $$aLan, Tian$$uOregon Health and Science University$$041354
000000704 7201_ $$avan Santen, Jan$$uOregon Health and Science University$$041354$$7Personal$$eAdvisor
000000704 7201_ $$aErdogmus, Deniz$$uNortheastern University$$7Personal$$eAdvisor
000000704 8564_ $$95570f075-43c5-409d-ab2c-ddee43e825a8$$s911238$$uhttps://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf$$ePublic$$23a3ef710bd2039107f3603a5a3b6b592$$31
000000704 905__ $$a/rest/prod/np/19/39/24/np193924b
000000704 909CO $$ooai:digitalcollections.ohsu.edu:704$$pstudent-work
000000704 956__ $$aGet Accessible Copy$$uhttps://ohsu.libwizard.com/f/requestaccessibledocument
000000704 980__ $$aTheses and Dissertations