Sample-by-Sample Detection of Movement Intention from EEG using a Classifier with Optimized Decision Parameters

Title
Sample-by-Sample Detection of Movement Intention from EEG using a Classifier with Optimized Decision Parameters
Authors
박완주강재환권규현김래현김성필
Keywords
Neurorehabilitation; BCI; EEG; Motor rehabilitation
Issue Date
2012-11
Publisher
International Conference on NeuroRehabilitation
Abstract
A brain-computer interface can be useful for improving the effectiveness of a robot-assisted motor rehabilitation system by allowing it to operate based on user intention. This requires a reliable method for detecting the intention of movement. We propose an algorithm that minimizes the false alarm rate while maintaining substantial detection accuracy to prevent the rehabilitation system from falsely moving the limb with no user intention. The algorithm achieves this by optimizing the threshold of a decision boundary using the Fisher discriminant classifier. We demonstrate the performance of the proposed algorithm such that the proposed algorithm was able to detect movement intention from the human EEG with approximately 78% accuracy, while maintaining an average false alarm rate close to 10%.
URI
http://pubs.kist.re.kr/handle/201004/45706
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE