Spatio-spectral filters for improving the classification of single trial EEG

By Steven Lemm, Benjamin Blankertz, Gabriel Curio, K. Müller. IEEE Transactions on Biomedical Engineering, 2005

663 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

View Paper: https://www.semanticscholar.org/paper/f7e91d7b0f8d5f5a104bd131debfc4ed03ea79f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Signal Processing

Citations in the corpus

EEG dataset and OpenBMI toolbox for three BCI paradigms: an investigation into BCI illiteracy (2019, neutral): “…on the three paradigms by commonly used machine learning techniques such as common spatial pattern (CSP) [23], com-monspatio-spectralpattern(CSSP)[24],filterbankcommonspa-tial pattern (FBCSP) [25], Bayesian spatio-spectral filter optimization (BSSFO) [26], and canonical correlation analysis…”
Multiple Channel Detection of Steady-State Visual Evoked Potentials for Brain-Computer Interfaces (2007, methodology): “In the EEG literature, this is sometimes referred to as a spatial filter, and producing such combinations is a well established procedure in EEG signal processing [33]–[ 35 ].”
Filter Bank Common Spatial Pattern (FBCSP) in Brain-Computer Interface (2008, background): “Z p , p{1..2m} form the feature vector X p given in (2) as inputs to a classifier. log var var m p p p i X § · ¨ ¸ © ¹ ¦ Z Z (2) From the concept of cortical homunculus [15], different areas of the cerebral cortex control movements of different parts of the body [8].”
A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals (2007, background): “…Li et al 2004a) Combined CSP and PCA (Xu et al 2004b) Singular value decomposition (SVD) (Trejo et al 2003) Common spatio-spatial patterns (CSSP) (Lemm et al 2005) Frequency normalization (Freq-Norm) (Bashashati et al 2005, Borisoff et al 2004, Fatourechi et al 2004, 2005, Yu et al 2002) Local…”
Optimizing Spatial filters for Robust EEG Single-Trial Analysis (2008, methodology): “AUTOMATIC SELECTION OF SPECTRAL FILTER The common spatio-spectral pattern (CSSP) algorithm [31] solves the standard CSP problem on the EEG time series augmented by delayed copies of the original signal, thereby obtaining simultaneously optimized spatial filters in conjunction with simple frequency f”
Introduction to machine learning for brain imaging (2011, methodology): “As a result a number of novel data driven approaches specific to neuroscience have emerged: (a) dimension reduction and projection methods (e.g. Hyvärinen et al. (2001); Ziehe et al. (2000); Parra and Sajda (2003); ∗corresponding author: steven.lemm@cs.tu-berlin.de Morup et al. (2008); von Bünau e”
Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b (2012, methodology): “…limited to, the Common Spatio-Spectral Pattern (CSSP) which optimizes a simple ﬁlter that employed a one time-delayed sample with the CSP algorithm (Lemm et al., 2005); the Common Sparse Spectral-Spatial Pattern (CSSSP) which performs simultaneous optimization of an arbitrary Finite Impulse…”
Brain Computer Interfaces, a Review (2012, methodology): “For these reasons, several methods improving the original CSP method have been proposed to increase the performance: Wavelet Common Spatial Pattern (WCSP) [185], Common Spatio-Spectral Pattern (CSSP) [186], and Common Sparse Spectral Spatial Pattern (CSSSP) [187].”
Subject-Independent Brain–Computer Interfaces Based on Deep Convolutional Neural Networks (2019, methodology): “The CSSP method is implemented utilizing time delay embedding from 1 to 15 [29].”
Multiclass Common Spatial Patterns and Information Theoretic Feature Extraction (2008, neutral): “[6], [13], [22] and the references therein).”
Sub-band Common Spatial Pattern (SBCSP) for Brain-Computer Interface (2007, methodology): “For subject ’aa’, the RBE performs better than CSSP with P 0.05 (t-test), which means we have 95% confidence of rejecting hypothesis that the two means have no difference.”