Unsupervised adaptation of electroencephalogram signal processing based on fuzzy C-means algorithm

Guangquan Liu, Dingguo Zhang, Jianjun Meng, Gan Huang, Xiangyang Zhu

Research output: Contribution to journalArticlepeer-review

14 Scopus citations

Abstract

This paper studies an unsupervised approach for online adaptation of electroencephalogram (EEG) based brain-computer interface (BCI). The approach is based on the fuzzy C-means (FCM) algorithm. It can be used to improve the adaptability of BCIs to the change in brain states by online updating the linear discriminant analysis classifier. In order to evaluate the performance of the proposed approach, we applied it to a set of simulation data and compared with other unsupervised adaptation algorithms. The results show that the FCM-based algorithm can achieve a desirable capability in adapting to changes and discovering class information from unlabeled data. The algorithm has also been tested by the real EEG data recorded in experiments in our laboratory and the data from other sources (set IIb of the BCI Competition IV). The results of real data are consistent with that of simulation data.

Original languageEnglish (US)
Pages (from-to)482-495
Number of pages14
JournalInternational Journal of Adaptive Control and Signal Processing
Volume26
Issue number6
DOIs
StatePublished - Jun 2012

Bibliographical note

Copyright:
Copyright 2012 Elsevier B.V., All rights reserved.

Keywords

  • brain-computer interface
  • electroencephalogram (EEG)
  • fuzzy C-means (FCM)
  • unsupervised adaptation

Fingerprint

Dive into the research topics of 'Unsupervised adaptation of electroencephalogram signal processing based on fuzzy C-means algorithm'. Together they form a unique fingerprint.

Cite this