Single-trial analysis and classification of ERP components - A tutorial

By Benjamin Blankertz, Steven Lemm, Matthias Sebastian Treder, Stefan Haufe, K. Müller. 2011

1,195 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, methodology): “…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 the extracted features a regularized LDA classifier with analytically determined shrinkage parameter [17] was trained.”
Decomposing Spatiotemporal Brain Patterns into Topographic Latent Sources (2014, positive): “This algorithm has been shown to achieve state-of-the-art performance in brain-computer interface applications (Blankertz et al., 2011).”
A Deep Learning Scheme for Motor Imagery Classification based on Restricted Boltzmann Machines (2017, background): “However, the EEG recordings are usually of low signalto-noise ratio (SNR) due to the volume-conduction effect, which makes it very challenging to accurately understand brain dynamics and classify different motor imageries [4].”
A Review on the Computational Methods for Emotional State Estimation from the Human EEG (2013, methodology): “However, recent developments of the single-trial ERP computation methods increase a possibility to use ERP features for online emotional state estimation [42– 46].”
Flashing characters with famous faces improves ERP-based brain–computer interface performance (2011, background): “Many researchers have addressed this issue by improving (1) the quality of signal processing and the development of novel classiﬁcation techniques (e.g. Krusienski et al (2006), (2008), Blankertz et al (2011); for a review see Lotte et al (2007)) and (2) procedural aspects of the oddball paradigm.”
Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals (2011, methodology): “Given the ranking, the minimum number of features yielding a cross-validation error which deviates less than one standard error from the minimal cross-validation error is 9 for the SVM and only 6 for the RLDA.”
Robust artifactual independent component classification for BCI practitioners (2014, methodology): “Different classes of imagined movements are distinguished with an ERP-type analysis [49, 52]: EEG is band-pass ﬁltered between 4 and 8 Hz, before a small number of class-discriminative intervals is determined on the calibration data.”
Multiclass Brain–Computer Interface Classification by Riemannian Geometry (2012, methodology): “Regularised classification algorithms are usually needed in this case to tackle this problem [3], [16].”
A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update (2018, background): “They are the typical features used to classify Event Related Potentials (ERP), which are temporal variations in EEG signals’ amplitudes time-locked to a given event/stimulus [22, 136].”
Transfer Learning: A Riemannian Geometry Framework With Applications to Brain–Computer Interfaces (2018, methodology): “This is done by supervised techniques like, for instance, Linear Discriminant Analysis (LDA) [9].”
Review of the BCI Competition IV (2012, background): “…slower over the last years, despite of a drastic initial performance boost which was made possible by the introduction of machine learning methods (Blankertz et al., 2003, 2011; Schröder et al., 2003). resistance, pupil dilation, etc.) or in a hybrid setup (Millán et al., 2010; Pfurtscheller et…”
BCILAB: a platform for brain–computer interface development (2013, methodology): “…used methods is what we call here the windowed means approach, a linear model, typically linear discriminant analysis (LDA) [61], applied to per-channel averages of the EEG signal over one or more short time window segments, possibly with additional preprocessing (see [62] for a good tutorial).”