Development of a Brain-Computer Interface system based on sensorimotor rhythms

Author

Carra, Michel ; Balbinot, Alexandre

fYear

2012

fDate

9-11 Jan. 2012

Firstpage

1

Lastpage

5

Abstract

In this work we developed a Brain-Computer Interface system using brain signals from somatosensory cortex. As stimulus, arrows were shown to the right and left to five subjects, who perform imaginary hand movement tasks to the side indicated by the arrow. Subject-specific parameters were selected using DSLVQ (Distinctive Sensitive Learning Vector Quantization) and Lateralization Index (LI), in order to extract the most relevant features, resulting in a higher hit rate in the classification stage. Online classification was performed with Linear Discriminant Analysis resulting in hit rates between 81 and 92.1%.

Keywords

brain; brain-computer interfaces; feature extraction; medical signal processing; signal classification; vector quantisation; DSLVQ; brain-computer interface system; distinctive sensitive learning vector quantization; feature extraction; imaginary hand movement tasks; lateralization index; linear discriminant analysis; sensorimotor rhythms; signal classification; Brain computer interfaces; Electroencephalography; Feature extraction; Performance evaluation; Signal processing algorithms; Training; Visualization; brain-computer interface; distinctive sensitive learning vector quantization; electroencephalography; linear discriminant analysis; sensorimotor rhythms;

fLanguage

English

Publisher

ieee

Conference_Titel

Biosignals and Biorobotics Conference (BRC), 2012 ISSNIP

Conference_Location

Manaus

Print_ISBN

978-1-4673-2476-2

Type

conf

DOI

10.1109/BRC.2012.6222194

Filename

6222194