Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces

Claudia Sannelli, Carmen Vidaurre, Klaus Muller, Benjamin Blankertz

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Citations (Scopus)

Abstract

Laplacian filters are commonly used in Brain Computer Interfacing (BCI). When only data from few channels are available, or when, like at the beginning of an experiment, no previous data from the same user is available complex features cannot be used. In this case band power features calculated from Laplacian filtered channels represents an easy, robust and general feature to control a BCI, since its calculation does not involve any class information. For the same reason, the performance obtained with Laplacian features is poor in comparison to subject-specific optimized spatial filters, such as Common Spatial Patterns (CSP) analysis, which, on the other hand, can be used just in a later phase of the experiment, since they require a considerable amount of training data in order to enroll a stable and good performance. This drawback is particularly evident in case of poor performing BCI users, whose data is highly non-stationary and contains little class relevant information. Therefore, Laplacian filtering is preferred to CSP, e.g., in the initial period of co-adaptive calibration, a novel BCI paradigm designed to alleviate the problem of BCI illiteracy. In fact, in the co-adaptive calibration design the experiment starts with a subject-independent classifier and simple features are needed in order to obtain a fast adaptation of the classifier to the newly acquired user's data. Here, the use of an ensemble of local CSP patches (CSPP) is proposed, which can be considered as a compromise between Laplacians and CSP: CSPP needs less data and channels than CSP, while being superior to Laplacian filtering. This property is shown to be particularly useful for the co-adaptive calibration design and is demonstrated on off-line data from a previous co-adaptive BCI study.

Original languageEnglish
Title of host publication2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Pages4351-4354
Number of pages4
DOIs
Publication statusPublished - 2010 Dec 1
Externally publishedYes
Event2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 - Buenos Aires, Argentina
Duration: 2010 Aug 312010 Sep 4

Other

Other2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
CountryArgentina
CityBuenos Aires
Period10/8/3110/9/4

Fingerprint

Brain computer interface
Brain
Calibration
Classifiers
Experiments

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Sannelli, C., Vidaurre, C., Muller, K., & Blankertz, B. (2010). Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 (pp. 4351-4354). [5626227] https://doi.org/10.1109/IEMBS.2010.5626227

Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces. / Sannelli, Claudia; Vidaurre, Carmen; Muller, Klaus; Blankertz, Benjamin.

2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 4351-4354 5626227.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sannelli, C, Vidaurre, C, Muller, K & Blankertz, B 2010, Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces. in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10., 5626227, pp. 4351-4354, 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10, Buenos Aires, Argentina, 10/8/31. https://doi.org/10.1109/IEMBS.2010.5626227
Sannelli C, Vidaurre C, Muller K, Blankertz B. Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces. In 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. p. 4351-4354. 5626227 https://doi.org/10.1109/IEMBS.2010.5626227
Sannelli, Claudia ; Vidaurre, Carmen ; Muller, Klaus ; Blankertz, Benjamin. / Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces. 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10. 2010. pp. 4351-4354
@inproceedings{3b5184e359ab4d9b916118f2e9fae4dd,
title = "Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces",
abstract = "Laplacian filters are commonly used in Brain Computer Interfacing (BCI). When only data from few channels are available, or when, like at the beginning of an experiment, no previous data from the same user is available complex features cannot be used. In this case band power features calculated from Laplacian filtered channels represents an easy, robust and general feature to control a BCI, since its calculation does not involve any class information. For the same reason, the performance obtained with Laplacian features is poor in comparison to subject-specific optimized spatial filters, such as Common Spatial Patterns (CSP) analysis, which, on the other hand, can be used just in a later phase of the experiment, since they require a considerable amount of training data in order to enroll a stable and good performance. This drawback is particularly evident in case of poor performing BCI users, whose data is highly non-stationary and contains little class relevant information. Therefore, Laplacian filtering is preferred to CSP, e.g., in the initial period of co-adaptive calibration, a novel BCI paradigm designed to alleviate the problem of BCI illiteracy. In fact, in the co-adaptive calibration design the experiment starts with a subject-independent classifier and simple features are needed in order to obtain a fast adaptation of the classifier to the newly acquired user's data. Here, the use of an ensemble of local CSP patches (CSPP) is proposed, which can be considered as a compromise between Laplacians and CSP: CSPP needs less data and channels than CSP, while being superior to Laplacian filtering. This property is shown to be particularly useful for the co-adaptive calibration design and is demonstrated on off-line data from a previous co-adaptive BCI study.",
author = "Claudia Sannelli and Carmen Vidaurre and Klaus Muller and Benjamin Blankertz",
year = "2010",
month = "12",
day = "1",
doi = "10.1109/IEMBS.2010.5626227",
language = "English",
isbn = "9781424441235",
pages = "4351--4354",
booktitle = "2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10",

}

TY - GEN

T1 - Common spatial pattern patches - An optimized filter ensemble for adaptive Brain-Computer Interfaces

AU - Sannelli, Claudia

AU - Vidaurre, Carmen

AU - Muller, Klaus

AU - Blankertz, Benjamin

PY - 2010/12/1

Y1 - 2010/12/1

N2 - Laplacian filters are commonly used in Brain Computer Interfacing (BCI). When only data from few channels are available, or when, like at the beginning of an experiment, no previous data from the same user is available complex features cannot be used. In this case band power features calculated from Laplacian filtered channels represents an easy, robust and general feature to control a BCI, since its calculation does not involve any class information. For the same reason, the performance obtained with Laplacian features is poor in comparison to subject-specific optimized spatial filters, such as Common Spatial Patterns (CSP) analysis, which, on the other hand, can be used just in a later phase of the experiment, since they require a considerable amount of training data in order to enroll a stable and good performance. This drawback is particularly evident in case of poor performing BCI users, whose data is highly non-stationary and contains little class relevant information. Therefore, Laplacian filtering is preferred to CSP, e.g., in the initial period of co-adaptive calibration, a novel BCI paradigm designed to alleviate the problem of BCI illiteracy. In fact, in the co-adaptive calibration design the experiment starts with a subject-independent classifier and simple features are needed in order to obtain a fast adaptation of the classifier to the newly acquired user's data. Here, the use of an ensemble of local CSP patches (CSPP) is proposed, which can be considered as a compromise between Laplacians and CSP: CSPP needs less data and channels than CSP, while being superior to Laplacian filtering. This property is shown to be particularly useful for the co-adaptive calibration design and is demonstrated on off-line data from a previous co-adaptive BCI study.

AB - Laplacian filters are commonly used in Brain Computer Interfacing (BCI). When only data from few channels are available, or when, like at the beginning of an experiment, no previous data from the same user is available complex features cannot be used. In this case band power features calculated from Laplacian filtered channels represents an easy, robust and general feature to control a BCI, since its calculation does not involve any class information. For the same reason, the performance obtained with Laplacian features is poor in comparison to subject-specific optimized spatial filters, such as Common Spatial Patterns (CSP) analysis, which, on the other hand, can be used just in a later phase of the experiment, since they require a considerable amount of training data in order to enroll a stable and good performance. This drawback is particularly evident in case of poor performing BCI users, whose data is highly non-stationary and contains little class relevant information. Therefore, Laplacian filtering is preferred to CSP, e.g., in the initial period of co-adaptive calibration, a novel BCI paradigm designed to alleviate the problem of BCI illiteracy. In fact, in the co-adaptive calibration design the experiment starts with a subject-independent classifier and simple features are needed in order to obtain a fast adaptation of the classifier to the newly acquired user's data. Here, the use of an ensemble of local CSP patches (CSPP) is proposed, which can be considered as a compromise between Laplacians and CSP: CSPP needs less data and channels than CSP, while being superior to Laplacian filtering. This property is shown to be particularly useful for the co-adaptive calibration design and is demonstrated on off-line data from a previous co-adaptive BCI study.

UR - http://www.scopus.com/inward/record.url?scp=78650827822&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78650827822&partnerID=8YFLogxK

U2 - 10.1109/IEMBS.2010.5626227

DO - 10.1109/IEMBS.2010.5626227

M3 - Conference contribution

C2 - 21096003

AN - SCOPUS:78650827822

SN - 9781424441235

SP - 4351

EP - 4354

BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

ER -