TY  - GEN
AB  - Brain–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.
AD  - Oregon Health and Science University
AU  - Lan, Tian
DA  - 2011
DO  - 10.6083/M4RX9920
DO  - DOI
ED  - van Santen, Jan
ED  - Erdogmus, Deniz
ED  - Advisor
ED  - Advisor
ID  - 704
KW  - Brain-Computer Interfaces
KW  - Evoked Potentials
KW  - Machine Learning
KW  - Cognition
KW  - User-Computer Interface
KW  - Artificial Intelligence
KW  - Electroencephalography
L1  - https://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf
L2  - https://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf
L4  - https://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf
LK  - https://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf
N2  - Brain–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.
PB  - Oregon Health and Science University
PY  - 2011
T1  - Feature extraction feature selection and dimensionality reduction techniques for brain computer interface
TI  - Feature extraction feature selection and dimensionality reduction techniques for brain computer interface
UR  - https://digitalcollections.ohsu.edu/record/704/files/706_etd.pdf
Y1  - 2011
ER  -