Analysis of dimension reduction by PCA and AdaBoost on spelling paradigm EEG data

Author

Yildirim, A. ; Halici, Ugur

Author_Institution

Dept. of Electr. & Electron. Eng., Middle East Tech. Univ., Ankara, Turkey

fYear

2013

fDate

16-18 Dec. 2013

Firstpage

192

Lastpage

196

Abstract

Spelling Paradigm is a BCI application which aims to construct words by finding letters using P300 signals recorded via channel electrodes attached to the diverse points of the scalp. In this study effects of dimension reduction using Principal Component Analysis (PCA) and AdaBoost methods on time domain characteristics of P300 evoked potentials in Spelling Paradigm are analyzed. Support Vector Machine (SVM) is used for classification.

Keywords

bioelectric potentials; biomedical electrodes; electroencephalography; handicapped aids; learning (artificial intelligence); medical signal processing; principal component analysis; signal classification; support vector machines; AdaBoost; BCI application; P300 evoked potentials; P300 signals; PCA; SVM; Spelling Paradigm EEG data; channel electrodes; dimension reduction analysis; electroencephalography; principal component analysis; scalp; signal classification; support vector machine; time domain characteristics; Electroencephalography; Error analysis; Principal component analysis; Support vector machine classification; Time-domain analysis; Training; Adaboost; Brain Computer Interfaces; Principal Component Analysis; Spelling Paradigm; Support Vector Machine;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering and Informatics (BMEI), 2013 6th International Conference on

Conference_Location

Hangzhou

Print_ISBN

978-1-4799-2760-9

Type

conf

DOI

10.1109/BMEI.2013.6746932

Filename

6746932