Prediction of hand movement from the event-related EEG using neural networks

Author

Erfanian, Abbas ; Moghaddas, Saeid

Author_Institution

Dept. of Biomed. Eng., Iran Univ. of Sci. & Technol., Tehran, Iran

Volume

1

fYear

1999

fDate

1999

Abstract

This article explores the use of single-channel EEG to predict the hand movement including grasping, opening, and holding. A feedforward neural network with the backpropagation learning rule was trained to discriminate between three different patterns of EEG using the mean absolute value (MAV), variance, and the relative power of the Beta band to the Alpha band as the features. It was found that 80% of the novel data and 98.7% of the trained data were classified correctly

Keywords

backpropagation; biomechanics; electroencephalography; feedforward neural nets; medical signal processing; EEG patterns; alpha band; backpropagation learning rule; beta band; electrodiagnostics; event-related EEG; grasping; hand movement prediction; holding; opening; trained data; Biological neural networks; Electrodes; Electroencephalography; Feedforward neural networks; Grasping; Intelligent systems; Mathematics; Multilayer perceptrons; Neural networks; Physics;

fLanguage

English

Publisher

ieee

Conference_Titel

[Engineering in Medicine and Biology, 1999. 21st Annual Conference and the 1999 Annual Fall Meetring of the Biomedical Engineering Society] BMES/EMBS Conference, 1999. Proceedings of the First Joint

Conference_Location

Atlanta, GA

ISSN

1094-687X

Print_ISBN

0-7803-5674-8

Type

conf

DOI

10.1109/IEMBS.1999.802508

Filename

802508