Information transfer rate in a five-classes brain-computer interface

By Bernhard Obermaier, Christa Neuper, Christoph Guger, Gert Pfurtscheller. IEEE transactions on neural systems and rehabilitation engineering, 2001

374 citations recorded by the source corpus.

Subfields: Cellular and Molecular Neuroscience, Cognitive Neuroscience, Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/20660ab45361bc28814b83996f4a9d338eceab4c

How researchers see this paper

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

In Cellular and Molecular Neuroscience

In Cognitive Neuroscience

In Electrical and Electronic Engineering

Citations in the corpus

Steady-state somatosensory evoked potentials: suitable brain signals for brain-computer interfaces? (2006, background): “The user has to perform different types of imaginations to get control over an application [1], [2].”
Brain-Computer Interfaces Using Sensorimotor Rhythms: Current State and Future Perspectives (2014, positive): “More degrees of independent control can be achieved by classifying multiple mental states of imageries [41], [89].”
Brain-Machine Interfaces: From Basic Science to Neuroprostheses and Neurorehabilitation. (2017, background): “In an independent BMI, subjects self-initiate actions, for example, by imagining movements (604, 631, 651, 698) or even assisting themselves with overt movements of the limbs (114, 307, 463, 852).”
A survey of signal processing algorithms in brain–computer interfaces based on electrical brain signals (2007, background): “Spectral parameters (Gysels and Celka 2004, Gysels et al 2005, Millan et al 2000a, 2000b, 2002b, 2003a, 2004a, Millan 2004, Millan and Mourino 2003b, Obermaier et al 2001d, Varsta et al 2000) Parametric modeling (Curran et al 2004, Penny et al 2000, Roberts and Penny 2003, Sykacek et al 2004,…”
Control of an Electrical Prosthesis With an SSVEP-Based BCI (2008, background): “However, to control various single movements, more classes should be provided by the BCI resulting in longer training periods and/or a decrease of classification accuracy [6], [10].”
A review of classification algorithms for EEG-based brain–computer interfaces (2007, methodology): “As EEG components used to drive BCI have specific time courses, HMM have been applied to the classification of temporal sequences of BCI features [23] [52] [ 65 ] and even to the classification of raw EEG [66].”
Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms (2004, background): “Interestingly, this is in contrast to the results without using our combination methods where the highest gain is found in a three class setup, a results that was also found in [16], or in some cases with a 2-class setup.”