An experimental study to compare CSP and TSM techniques to extract features during motor imagery tasks

An experimental study to compare CSP and TSM techniques to extract features during motor imagery tasks

For access to this article, please select a purchase option:

Buy chapter PDF
(plus tax if applicable)

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Your details
Why are you recommending this title?
Select reason:
Signal Processing and Machine Learning for Brain-Machine Interfaces — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

Common spatial pattern (CSP) is a well-established technique to extract features from electroencephalographic recordings for classification purpose in motor imagery brain-computer interface (BCI).The CSP algorithm is a mathematical procedure used for separating a multivariate signal into additive components which have maximum differences in variance between two windows; in other terms, CSP increases the signal variance for one condition while minimizing the variance for the other condition. Features computed by means of CSP are fed to a data classifier in order to discriminate between two mental tasks. A novel technique to achieve feature extraction is tangentspace mapping (TSM) that insists on spatial covariance matrices computed from the recorded electroencephalogram signals (EEG). TSM is based on Riemannian geometry, which allows one to estimate statistical features of data distributions over non-Euclidean spaces. The aim of this chapter is twofold: first, to provide a new data-visualization tool to visually inspect data distributions on the Riemannian space of spatial covariance matrices and its tangent bundle; second, to present an experimental comparison of CSP and TSM feature extraction, in conjunction with two classification methods, namely, support-vector machine and linear discriminant analysis. In particular, the experimental comparison performed on a number of data sets will show the superiority of TSM-based feature extraction over CSP.

Chapter Contents:

  • Abstract
  • 3.1 Introduction
  • 3.2 Theoretical concepts and methods
  • 3.2.1 Averaging techniques of SCMs
  • 3.2.2 SCM averages in CSP and TSM methods
  • 3.2.3 Multidimensional scaling (MDS) algorithm
  • 3.3 Experimental results
  • 3.3.1 Classification accuracy
  • Results obtained on the Dataset III_IIIa
  • Results obtained on the Dataset III_IIIb
  • Results obtained on the Dataset III_IVa
  • Results obtained on the Dataset IV_IIa
  • Results obtained on the Dataset JKHH-1
  • 3.3.2 SCMs distributions on tangent spaces
  • Projected SCMs distributions relative to the Dataset III_IIIb
  • SCMs distributions relative to the Dataset III_IVa
  • SCMs distributions relative to the Dataset IV_IIa
  • SCMs distributions relative to the Dataset JKHH-1
  • 3.4 Conclusions
  • References

Inspec keywords: data visualisation; support vector machines; feature extraction; covariance matrices; electroencephalography; brain-computer interfaces; medical signal processing; statistical analysis

Other keywords: data classifier; TSM feature extraction; spatial covariance matrices; electroencephalogram signals; support-vector machine; motor imagery brain-computer interface; BCI; Riemannian geometry; common spatial pattern; data-visualization; CSP algorithm; EEG; statistical features; tangentspace mapping; linear discriminant analysis; multivariate signal

Subjects: Algebra; Knowledge engineering techniques; Graphics techniques; Digital signal processing; Bioelectric signals; Other topics in statistics; Biology and medical computing; Algebra; Other topics in statistics; Signal processing and detection; User interfaces

Preview this chapter:
Zoom in

An experimental study to compare CSP and TSM techniques to extract features during motor imagery tasks, Page 1 of 2

| /docserver/preview/fulltext/books/ce/pbce114e/PBCE114E_ch3-1.gif /docserver/preview/fulltext/books/ce/pbce114e/PBCE114E_ch3-2.gif

Related content

This is a required field
Please enter a valid email address