Optimizing Spatial filters for Robust EEG Single-Trial Analysis

By Benjamin Blankertz, Ryota Tomioka, Steven Lemm, Motoaki Kawanabe, K.-R. Muller. 2008

2,111 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Signal Processing

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

Methods for interpreting and understanding deep neural networks (2017, neutral): “For classical linear explanation of neural activation patterns in cognitive brain science experiments or Brain Computer Interfacing, see [15, 40, 14, 24].”
On the interpretation of weight vectors of linear models in multivariate neuroimaging (2014, background): “…it possible to cancel out noise and thereby to extract the brain signals of interest with higher sensitivity and speci ﬁ city (Bießmann et al., 2009; Blankertz et al., 2002, 2008, 2011; Comon, 1994; Dähne et al., 2014; Dolce & Waldeier, 1974; Donchin & Hef ﬂ ey, 1978; Haufe et al., 2010;…”
Interpretable Deep Neural Networks for Single-Trial EEG Classification (2016, methodology): “On two example data sets we compare the classification performance of DNN to that of CSP-LDA, a standard technique [9].”
Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms (2011, methodology): “mizing the discriminability of two classes [3], [4].”
EEG datasets for motor imagery brain–computer interface (2017, neutral): “The time window was determined by an algorithm for selection of a discriminative time interval (see the Appendix in [13]).”
Introduction to machine learning for brain imaging (2011, background): “…Lemm et al., 2005; Blankertzetal.,2008b;Dornhegeetal.,2006,2007;TomiokaandMüller, 2010; Parra et al., 2008; Blankertz et al., 2007), (d) measures for determining synchrony, coherence or causal relations in data (e.g. Meinecke etal., 2005;Brunner etal.,2006; Nolteet al., 2004;Marzetti et al.,2008;…”
Transfer Learning: A Riemannian Geometry Framework With Applications to Brain–Computer Interfaces (2018, methodology): “First, EEG signals of a training set are transformed through frequency and/or spatial filters in order to extract discriminant features [8], [16].”
A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update (2018, methodology): “Then, EEG signals are typically preprocessed using various spatial and spectral filters [23], and features are extracted from these signals in order to represent them in a compact form [140].”
Classification of covariance matrices using a Riemannian-based kernel for BCI applications (2013, methodology): “It is common practice in MI-based BCI to use spatial ﬁltering for dimension reduction and variance ratio enhancement between EEG trials coming from diﬀerent motor classes (Blankertz et al., 2008).”
Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces (2015, methodology): “Since the variance of a band-pass filtered signal corresponds to the band-power of the signal in that band, CSP optimizes spatial filters that lead to optimally discriminant band-power features [29].”
Neurophysiological predictor of SMR-based BCI performance (2010, neutral): “Details on the heuristics underlying the selection of frequency band and time interval can be found in Blankertz et al. (2008b).”
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications (2021, background): “However, in contrast to the patterns computed with conventional approaches [24], [63], which only allows visualizing the aggregated information (average activity) per class, the explanations computed with LRP are available for every single input of the deep learning classifier, i.”
A survey of multilinear subspace learning for tensor data (2011, background): “Electroencephalography (EEG) records brain activities as multichannel time series from multiple electrodes placed on the scalp of a subject to provide a direct communication channel between brain and computer, and it is widely used in noninvasive brain computer interfaces (BCI) applications [98].”
Filter Bank Common Spatial Pattern Algorithm on BCI Competition IV Datasets 2a and 2b (2012, methodology): “For effective use of the CSP algorithm, several parameters have to be speciﬁed, namely, the frequency for band-pass ﬁltering of the EEG measurements, the time interval of the EEG measurements taken relative to the stimuli, and the subset of CSP ﬁlters to be used (Blankertz et al., 2008b).”
Regularized Common Spatial Pattern With Aggregation for EEG Classification in Small-Sample Setting (2010, methodology): “inexpensiveness, and high temporal resolution, it is widely used in noninvasive brain–computer interfaces (BCI) [2], [3], where”
The Berlin Brain–Computer Interface: Non-Medical Uses of BCI Technology (2010, methodology): “…the use of modern machine learning and signal processing methods, that allowed to relocate the burden of training from a learning subject toward statistical learning machines and thereby achieve BCI communication for a naïve user already in the first session (Blankertz et al., 2002, 2007a, 2008b).”