Cargando…

Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery

Common spatial pattern (CSP) is one of the most popular and effective feature extraction methods for motor imagery-based brain-computer interface (BCI), but the inherent drawback of CSP is that the estimation of the covariance matrices is sensitive to noise. In this work, local temporal correlation...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Rui, Xu, Peng, Liu, Tiejun, Zhang, Yangsong, Guo, Lanjin, Li, Peiyang, Yao, Dezhong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi Publishing Corporation 2013
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3853213/
https://www.ncbi.nlm.nih.gov/pubmed/24348740
http://dx.doi.org/10.1155/2013/591216
_version_ 1782478799076589568
author Zhang, Rui
Xu, Peng
Liu, Tiejun
Zhang, Yangsong
Guo, Lanjin
Li, Peiyang
Yao, Dezhong
author_facet Zhang, Rui
Xu, Peng
Liu, Tiejun
Zhang, Yangsong
Guo, Lanjin
Li, Peiyang
Yao, Dezhong
author_sort Zhang, Rui
collection PubMed
description Common spatial pattern (CSP) is one of the most popular and effective feature extraction methods for motor imagery-based brain-computer interface (BCI), but the inherent drawback of CSP is that the estimation of the covariance matrices is sensitive to noise. In this work, local temporal correlation (LTC) information was introduced to further improve the covariance matrices estimation (LTCCSP). Compared to the Euclidean distance used in a previous CSP variant named local temporal CSP (LTCSP), the correlation may be a more reasonable metric to measure the similarity of activated spatial patterns existing in motor imagery period. Numerical comparisons among CSP, LTCSP, and LTCCSP were quantitatively conducted on the simulated datasets by adding outliers to Dataset IVa of BCI Competition III and Dataset IIa of BCI Competition IV, respectively. Results showed that LTCCSP achieves the highest average classification accuracies in all the outliers occurrence frequencies. The application of the three methods to the EEG dataset recorded in our laboratory also demonstrated that LTCCSP achieves the highest average accuracy. The above results consistently indicate that LTCCSP would be a promising method for practical motor imagery BCI application.
format Online
Article
Text
id pubmed-3853213
institution National Center for Biotechnology Information
language English
publishDate 2013
publisher Hindawi Publishing Corporation
record_format MEDLINE/PubMed
spelling pubmed-38532132013-12-12 Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery Zhang, Rui Xu, Peng Liu, Tiejun Zhang, Yangsong Guo, Lanjin Li, Peiyang Yao, Dezhong Comput Math Methods Med Research Article Common spatial pattern (CSP) is one of the most popular and effective feature extraction methods for motor imagery-based brain-computer interface (BCI), but the inherent drawback of CSP is that the estimation of the covariance matrices is sensitive to noise. In this work, local temporal correlation (LTC) information was introduced to further improve the covariance matrices estimation (LTCCSP). Compared to the Euclidean distance used in a previous CSP variant named local temporal CSP (LTCSP), the correlation may be a more reasonable metric to measure the similarity of activated spatial patterns existing in motor imagery period. Numerical comparisons among CSP, LTCSP, and LTCCSP were quantitatively conducted on the simulated datasets by adding outliers to Dataset IVa of BCI Competition III and Dataset IIa of BCI Competition IV, respectively. Results showed that LTCCSP achieves the highest average classification accuracies in all the outliers occurrence frequencies. The application of the three methods to the EEG dataset recorded in our laboratory also demonstrated that LTCCSP achieves the highest average accuracy. The above results consistently indicate that LTCCSP would be a promising method for practical motor imagery BCI application. Hindawi Publishing Corporation 2013 2013-11-20 /pmc/articles/PMC3853213/ /pubmed/24348740 http://dx.doi.org/10.1155/2013/591216 Text en Copyright © 2013 Rui Zhang et al. https://creativecommons.org/licenses/by/3.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Zhang, Rui
Xu, Peng
Liu, Tiejun
Zhang, Yangsong
Guo, Lanjin
Li, Peiyang
Yao, Dezhong
Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title_full Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title_fullStr Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title_full_unstemmed Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title_short Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery
title_sort local temporal correlation common spatial patterns for single trial eeg classification during motor imagery
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3853213/
https://www.ncbi.nlm.nih.gov/pubmed/24348740
http://dx.doi.org/10.1155/2013/591216
work_keys_str_mv AT zhangrui localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT xupeng localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT liutiejun localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT zhangyangsong localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT guolanjin localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT lipeiyang localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery
AT yaodezhong localtemporalcorrelationcommonspatialpatternsforsingletrialeegclassificationduringmotorimagery