Tikhonov regularized spectrally weighted common spatial patterns

Author

Ashok, Amit ; Bharathan, Arun K. ; Soujya, V.R. ; Nandakumar, P.

Author_Institution

Dept. of Electron. & Commun. Eng., N.S.S. Coll. of Eng., Palakkad, India

fYear

2013

fDate

13-15 Dec. 2013

Firstpage

315

Lastpage

318

Abstract

Common spatial patterns(CSP) is one of the most popular feature extraction methods used in Brain-computer interfaces(BCI). Different variants of Common spatial patterns exist. One of the best among them is Spectrally weighted common spatial patterns(SPEC-CSP). In this paper we introduce Tikhonov regularized spectrally weighted common spatial patterns(TRSPEC-CSP) and Weighted Tikhonov regularized spectrally weighted common spatial patterns(WTRSPEC-CSP). The proposed methods are not so sensitive to noise and not prone to over fitting. We used dataset 2a of BCI competition IV to evaluate our method. The result shows that proposed methods outperforms SPEC-CSP and the best competitor of the BCI competition IV.

Keywords

brain-computer interfaces; electroencephalography; feature extraction; medical signal processing; spatial filters; BCI competition IV; EEG data; TRSPEC-CSP; Tikhonov regularized spectrally weighted common spatial patterns; WTRSPEC-CSP; brain-computer interfaces; dataset 2a; feature extraction methods; weighted Tikhonov regularized spectrally weighted common spatial patterns; Artificial neural networks; Electroencephalography; Visualization; BCI; Common Spatial Patterns; Motor Imagery;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Communication and Computing (ICCC), 2013 International Conference on

Conference_Location

Thiruvananthapuram

Print_ISBN

978-1-4799-0573-7

Type

conf

DOI

10.1109/ICCC.2013.6731671

Filename

6731671