Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study. Yger, F., Lotte, F., & Sugiyama, M. In 2015 23rd European Signal Processing Conference (EUSIPCO), pages 2721-2725, Aug, 2015. Paper doi abstract bibtex This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.
@InProceedings{7362879,
author = {F. Yger and F. Lotte and M. Sugiyama},
booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},
title = {Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study},
year = {2015},
pages = {2721-2725},
abstract = {This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.},
keywords = {brain-computer interfaces;covariance matrices;electroencephalography;medical signal processing;signal classification;EEG signal classification;CSP;empirical comparison;covariance matrix averaging methods;averaging EEG signal covariance matrices;brain-computer interfaces;BCI;common spatial pattern algorithm;nonEuclidean structure;Riemannian geometry;small dimensional problems;Covariance matrices;Electroencephalography;Geometry;Symmetric matrices;Feature extraction;Europe;Signal processing;common spatial pattern;SPD matrices;robust averaging;Riemannian geometry;EEG signal classification;brain-computer interface (BCI)},
doi = {10.1109/EUSIPCO.2015.7362879},
issn = {2076-1465},
month = {Aug},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570102435.pdf},
}
Downloads: 0
{"_id":"yBuZ2H2T5ytgJNWwk","bibbaseid":"yger-lotte-sugiyama-averagingcovariancematricesforeegsignalclassificationbasedonthecspanempiricalstudy-2015","authorIDs":[],"author_short":["Yger, F.","Lotte, F.","Sugiyama, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["F."],"propositions":[],"lastnames":["Yger"],"suffixes":[]},{"firstnames":["F."],"propositions":[],"lastnames":["Lotte"],"suffixes":[]},{"firstnames":["M."],"propositions":[],"lastnames":["Sugiyama"],"suffixes":[]}],"booktitle":"2015 23rd European Signal Processing Conference (EUSIPCO)","title":"Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study","year":"2015","pages":"2721-2725","abstract":"This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.","keywords":"brain-computer interfaces;covariance matrices;electroencephalography;medical signal processing;signal classification;EEG signal classification;CSP;empirical comparison;covariance matrix averaging methods;averaging EEG signal covariance matrices;brain-computer interfaces;BCI;common spatial pattern algorithm;nonEuclidean structure;Riemannian geometry;small dimensional problems;Covariance matrices;Electroencephalography;Geometry;Symmetric matrices;Feature extraction;Europe;Signal processing;common spatial pattern;SPD matrices;robust averaging;Riemannian geometry;EEG signal classification;brain-computer interface (BCI)","doi":"10.1109/EUSIPCO.2015.7362879","issn":"2076-1465","month":"Aug","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570102435.pdf","bibtex":"@InProceedings{7362879,\n author = {F. Yger and F. Lotte and M. Sugiyama},\n booktitle = {2015 23rd European Signal Processing Conference (EUSIPCO)},\n title = {Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study},\n year = {2015},\n pages = {2721-2725},\n abstract = {This paper presents an empirical comparison of covariance matrix averaging methods for EEG signal classification. Indeed, averaging EEG signal covariance matrices is a key step in designing brain-computer interfaces (BCI) based on the popular common spatial pattern (CSP) algorithm. BCI paradigms are typically structured into trials and we argue that this structure should be taken into account. Moreover, the non-Euclidean structure of covariance matrices should be taken into consideration as well. We review several approaches from the literature for averaging covariance matrices in CSP and compare them empirically on three publicly available datasets. Our results show that using Riemannian geometry for averaging covariance matrices improves performances for small dimensional problems, but also the limits of this approach when the dimensionality increases.},\n keywords = {brain-computer interfaces;covariance matrices;electroencephalography;medical signal processing;signal classification;EEG signal classification;CSP;empirical comparison;covariance matrix averaging methods;averaging EEG signal covariance matrices;brain-computer interfaces;BCI;common spatial pattern algorithm;nonEuclidean structure;Riemannian geometry;small dimensional problems;Covariance matrices;Electroencephalography;Geometry;Symmetric matrices;Feature extraction;Europe;Signal processing;common spatial pattern;SPD matrices;robust averaging;Riemannian geometry;EEG signal classification;brain-computer interface (BCI)},\n doi = {10.1109/EUSIPCO.2015.7362879},\n issn = {2076-1465},\n month = {Aug},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570102435.pdf},\n}\n\n","author_short":["Yger, F.","Lotte, F.","Sugiyama, M."],"key":"7362879","id":"7362879","bibbaseid":"yger-lotte-sugiyama-averagingcovariancematricesforeegsignalclassificationbasedonthecspanempiricalstudy-2015","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2015/papers/1570102435.pdf"},"keyword":["brain-computer interfaces;covariance matrices;electroencephalography;medical signal processing;signal classification;EEG signal classification;CSP;empirical comparison;covariance matrix averaging methods;averaging EEG signal covariance matrices;brain-computer interfaces;BCI;common spatial pattern algorithm;nonEuclidean structure;Riemannian geometry;small dimensional problems;Covariance matrices;Electroencephalography;Geometry;Symmetric matrices;Feature extraction;Europe;Signal processing;common spatial pattern;SPD matrices;robust averaging;Riemannian geometry;EEG signal classification;brain-computer interface (BCI)"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2015url.bib","creationDate":"2021-02-13T17:31:52.630Z","downloads":0,"keywords":["brain-computer interfaces;covariance matrices;electroencephalography;medical signal processing;signal classification;eeg signal classification;csp;empirical comparison;covariance matrix averaging methods;averaging eeg signal covariance matrices;brain-computer interfaces;bci;common spatial pattern algorithm;noneuclidean structure;riemannian geometry;small dimensional problems;covariance matrices;electroencephalography;geometry;symmetric matrices;feature extraction;europe;signal processing;common spatial pattern;spd matrices;robust averaging;riemannian geometry;eeg signal classification;brain-computer interface (bci)"],"search_terms":["averaging","covariance","matrices","eeg","signal","classification","based","csp","empirical","study","yger","lotte","sugiyama"],"title":"Averaging covariance matrices for EEG signal classification based on the CSP: An empirical study","year":2015,"dataSources":["eov4vbT6mnAiTpKji","knrZsDjSNHWtA9WNT"]}