Classifying Single Trial EEG: Towards Brain Computer Interfacing

By Benjamin Blankertz, Gabriel Curio, K. Müller. Neural Information Processing Systems, 2001

572 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/fc7d146fd5326b05a155beee147ef842b3aa390c

How researchers see this paper

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

Citations in the corpus

Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms (2004, result): “1) Slow Nonoscillatory EEG Potential Shifts: To quantify the slow potential shifts, such as the lateralized MRP, we proceeded in a similar fashion to our approach in [5] [Berlin BrainComputer Interface (BBCI)].”
EEGLAB, SIFT, NFT, BCILAB, and ERICA: New Tools for Advanced EEG Processing (2011, methodology): “For example, given a collection of data sets, one per subject, containing imagined movements of either [26, 27] (i) Linear discriminant Analysis (LDA) [28] (ii) Resampling (ii) Common Spatial Patterns (CSP) [29] (ii) Quadratic discriminant analysis (QDA) [30] (iii) Artifact rejection (spike…”
Introduction to machine learning for brain imaging (2011, methodology): “Here, it was observed that through a proper preprocessing the class conditional distributions become Gaussian with a very similar covariance structure (cf. Blankertz et al., 2002, 2006a; Dornhege et al., 2007).”
Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a brain-computer interface (2007, background): “SVM has been demonstrated to work well in a number of real-world applications including BCI (Blankertz et al., 2001).”
Brain Computer Interfaces, a Review (2012, methodology): “SVM has been used to classify feature vectors for binary [239,240] and multiclass problems [228,230].”
Machine learning for real-time single-trial EEG-analysis: from brain-computer interfacing to mental state monitoring. (2008, unknown): “While theoretically this abstract mapping f could be learned even from raw EEG data (Blankertz et al., 2002), it has proven to be much more efficient to extract appropriate features from the continuous EEG signal using available physiological a-priori knowledge.”
Learning to Decode Cognitive States from Brain Images (2004, background): “For example, Blankertz, Curio, and Mller (2002) describe experiments training classiﬁers of brain states for single trial EEG data, while (Kjems et al., 2002; Strother et al., 2002) report training brain state classiﬁers for images obtained via Positron Emission Tomography (PET).”
Single-trial analysis and classification of ERP components - A tutorial (2011, unknown): “, 2001), which finally also attracted the machine learning community to the field (Blankertz et al., 2002; Vidaurre and Blankertz, 2010; Hong et al., 2009; Müller et al., 2008; Blankertz et al., 2008b, 2007a, 2006; Parra et al., 2008, 2003; Wang et al., 2004; Tomioka and Müller, 2010).”
The BCI competition III: validating alternative approaches to actual BCI problems (2006, methodology): “The most popular methods are Fisher discriminant [25], [26] and linear SVM [26].”
Comparison of linear, nonlinear, and feature selection methods for EEG signal classification (2003, methodology): “[3] collected data during a “self-paced key typing” task, which includes 413 prekey press epochs of EEG recorded from one subject.”
Optimization for machine learning (2010, methodology): “As a concrete example, we take a data-set from a real brain-computer interface (BCI) experiment, where the task is to predict whether the upcoming voluntary finger movement is either right or left hand from the electroencephalography (EEG) measurements (Blankertz et al., 2002). The data-set is made ”
Spatio-spectral filters for improving the classification of single trial EEG (2005, result): “Note that in contrast to [6], [14] we omitted the regularization (cf.”
The Berlin Brain-Computer Interface: Accurate performance from first-session in BCI-naive subjects (2008, background): “In this regard, the machine-learning approach to BCI has been shown to be highly promising [12], [13].”