Classification of EEG-P300 signals using Fisher´s linear discriminant analysis

Author

Turnip, Arjon ; Widyotriatmo, Augie ; Suprijanto

Author_Institution

Tech. Implementation Unit for Instrum. Dev., Indonesian Inst. of Sci., Bandung, Indonesia

fYear

2013

fDate

28-30 Aug. 2013

Firstpage

98

Lastpage

103

Abstract

In this paper, a classifier using Fisher´s Linear Discriminant Analysis is used to investigate the performance of three different extraction methods for brain signal based electroencephalogram (EEG)-P300. EEG-P300 recordings provide an important means of brain-computer communication, but their classification accuracy and transfer rate are limited by unexpected signal variations due to artifacts and noises. A comparison of extraction methods (i.e., AAR, JADE, and SOBI) entailing time-series EEG signals is presented. Finally, the promising results reported here reflect the considerable potential of EEG for the continuous classification of mental states.

Keywords

brain-computer interfaces; electroencephalography; medical signal processing; psychology; signal classification; statistical analysis; time series; EEG-P300 recordings; EEG-P300 signal classification; Fisher linear discriminant analysis; brain signal based electroencephalogram; brain-computer communication; classification accuracy; continuous mental state classification; time-series EEG signals; transfer rate; unexpected signal variations; Accuracy; Band-pass filters; Electroencephalography; Feature extraction; Mathematical model; Signal to noise ratio; Vectors; AAR; Brain computer interface (BCI); Classification accuracy; EEG; JADE; SOBI; Transfer rate;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation Control and Automation (ICA), 2013 3rd International Conference on

Conference_Location

Ungasan

Print_ISBN

978-1-4673-5795-1

Type

conf

DOI

10.1109/ICA.2013.6734053

Filename

6734053