Title :
A comparison of different dimensionality reduction and feature selection methods for single trial ERP detection
Author :
Lan, Tian ; Erdogmus, Deniz ; Black, Lois ; Van Santen, Jan
Author_Institution :
Dept. of Sci. & Eng., Oregon Health & Sci. Univ., Beaverton, OR, USA
fDate :
Aug. 31 2010-Sept. 4 2010
Abstract :
Dimensionality reduction and feature selection is an important aspect of electroencephalography based event related potential detection systems such as brain computer interfaces. In our study, a predefined sequence of letters was presented to subjects in a Rapid Serial Visual Presentation (RSVP) paradigm. EEG data were collected and analyzed offline. A linear discriminant analysis (LDA) classifier was designed as the ERP (Event Related Potential) detector for its simplicity. Different dimensionality reduction and feature selection methods were applied and compared in a greedy wrapper framework. Experimental results showed that PCA with the first 10 principal components for each channel performed best and could be used in both online and offline systems.
Keywords :
electroencephalography; feature extraction; medical signal detection; medical signal processing; principal component analysis; ERP detection; LDA; brain computer interfaces; dimensionality reduction; electroencephalography; event related potential detection; feature selection; greedy wrapper; linear discriminant analysis; rapid serial visual presentation; Accuracy; Electroencephalography; Feature extraction; Principal component analysis; Sensor phenomena and characterization; Time frequency analysis; Algorithms; Discriminant Analysis; Electroencephalography; Humans; Pattern Recognition, Automated; Signal Processing, Computer-Assisted; User-Computer Interface;
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE
Conference_Location :
Buenos Aires
Print_ISBN :
978-1-4244-4123-5
DOI :
10.1109/IEMBS.2010.5627642