Online classification of two mental tasks using a SVM-based BCI system

Author

Hortal, Enrique ; Ubeda, Andres ; Ianez, Eduardo ; Planelles, Daniel ; Azorin, Jose M.

Author_Institution

Biomed. Neuroengineering Group, Miguel Hernandez Univ. of Elche, Elche, Spain

fYear

2013

fDate

6-8 Nov. 2013

Firstpage

1307

Lastpage

1310

Abstract

A Brain-Computer Interface (BCI) can be very useful to help people with several movement disabilities to improve their independence or to assist them in rehabilitation tasks. In this paper, the results of the online classification of two mental tasks from electroencephalographic signals (EEG) are shown. The objective of this paper is to determine whether the accuracy in the online differentiation of two mental tasks could be enough to command a robot arm using two mental tasks. The results demonstrate that the features obtained using periodogram (a Power Spectral Density estimation) and the classification of these using a SVM-based (Support Vector Machine) system can be used in a reliable control of a robot arm. For all the users, the accuracy is around 87±2%. This accuracy is enough to be used to this end in real time.

Keywords

brain-computer interfaces; electroencephalography; feature extraction; medical robotics; medical signal processing; motion control; patient rehabilitation; signal classification; support vector machines; EEG; SVM-based BCI system; brain-computer interface; electroencephalographic signals; feature extraction; mental tasks; movement disabilities; online classification; periodogram; power spectral density estimation; rehabilitation tasks; reliable control; robot arm; support vector machine; Accuracy; Brain-computer interfaces; Electrodes; Electroencephalography; Kernel; Robots; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering (NER), 2013 6th International IEEE/EMBS Conference on

Conference_Location

San Diego, CA

ISSN

1948-3546

Type

conf

DOI

10.1109/NER.2013.6696181

Filename

6696181