Information transfer of an EEG-based brain computer interface

Author

Schlögl, A. ; Keinrath, C. ; Scherer, R. ; Furtscheller, P.

Author_Institution

Inst. of Biomed. Eng., Univ. of Technol. Graz, Austria

fYear

2003

fDate

20-22 March 2003

Firstpage

641

Lastpage

644

Abstract

The idea of an EEG-based brain computer interface is to support the communication of locked-in-patients. Thus, it is important to quantify the information transfer. Wolpaw et al. (2000) proposed a measure which is derived from the classification error rate. We propose an alternative measure. Both measures are compared and the advantages and disadvantages of both are discussed.

Keywords

autoregressive processes; electroencephalography; medical signal processing; signal classification; user interfaces; EEG-based brain computer interface; adaptive autoregressive parameters; classification error rate; communication theory; information transfer; locked-in-patients; mutual information; quadratic classifier; Biomedical informatics; Biomedical measurements; Bit rate; Brain computer interfaces; Entropy; Error analysis; Mutual information; Signal processing; Signal to noise ratio; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering, 2003. Conference Proceedings. First International IEEE EMBS Conference on

Print_ISBN

0-7803-7579-3

Type

conf

DOI

10.1109/CNE.2003.1196910

Filename

1196910

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3423373