Capsule Neural Network Based Error Correlation Potential Detection for EEG Topographies

At present, the detection of error-related potentials is useful for the application of real-time error instruction correction techniques in brain-machine interface online systems. This paper, however, proposes a strategy for error-correlation potential detection based on EEG topographies, which tran...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2021-03, Vol.1802 (4), p.42039
Main Authors: Wang, Qingyu, Wei, Lan, Zhou, Zhengkang, Wang, Zhuoer
Format: Article
Language:English
Subjects:
Error correction
Error detection
Man-machine interfaces
Neural networks
On-line systems
Physics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:At present, the detection of error-related potentials is useful for the application of real-time error instruction correction techniques in brain-machine interface online systems. This paper, however, proposes a strategy for error-correlation potential detection based on EEG topographies, which translate the sequence of EEG topographies over time into a spatial position relationship between the features contained in different pictures. As the capsule network incorporates relative position relationships between features, i.e., positional information, a high classification accuracy can be achieved with a small dataset. Experimental evaluation has shown that the proposed method yields significant performance improvements compared to conventional processing methods.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/1802/4/042039