%0 Journal Article %J J Neurosci Methods %D 2008 %T Brain-computer interfaces (BCIs): Detection Instead of Classification. %A Gerwin Schalk %A Peter Brunner %A Lester A Gerhardt %A H Bischof %A Jonathan Wolpaw %K Adult %K Algorithms %K Brain %K Brain Mapping %K Electrocardiography %K Electroencephalography %K Humans %K Male %K Man-Machine Systems %K Normal Distribution %K Online Systems %K Signal Detection, Psychological %K Signal Processing, Computer-Assisted %K Software Validation %K User-Computer Interface %X

Many studies over the past two decades have shown that people can use brain signals to convey their intent to a computer through brain-computer interfaces (BCIs). These devices operate by recording signals from the brain and translating these signals into device commands. They can be used by people who are severely paralyzed to communicate without any use of muscle activity. One of the major impediments in translating this novel technology into clinical applications is the current requirement for preliminary analyses to identify the brain signal features best suited for communication. This paper introduces and validates signal detection, which does not require such analysis procedures, as a new concept in BCI signal processing. This detection concept is realized with Gaussian mixture models (GMMs) that are used to model resting brain activity so that any change in relevant brain signals can be detected. It is implemented in a package called SIGFRIED (SIGnal modeling For Real-time Identification and Event Detection). The results indicate that SIGFRIED produces results that are within the range of those achieved using a common analysis strategy that requires preliminary identification of signal features. They indicate that such laborious analysis procedures could be replaced by merely recording brain signals during rest. In summary, this paper demonstrates how SIGFRIED could be used to overcome one of the present impediments to translation of laboratory BCI demonstrations into clinically practical applications.

%B J Neurosci Methods %V 167 %P 51-62 %8 01/2008 %G eng %U http://www.ncbi.nlm.nih.gov/pubmed/17920134 %N 1 %R 10.1016/j.jneumeth.2007.08.010 %0 Journal Article %J Neuroimage %D 2008 %T Real-time detection of event-related brain activity. %A Gerwin Schalk %A Leuthardt, E C %A Peter Brunner %A Ojemann, J G %A Lester A Gerhardt %A Jonathan Wolpaw %K Adult %K Algorithms %K Brain Mapping %K Computer Systems %K Diagnosis, Computer-Assisted %K Electroencephalography %K Epilepsy %K Evoked Potentials %K Female %K Humans %K Male %K Pattern Recognition, Automated %K Reproducibility of Results %K Sensitivity and Specificity %X

The complexity and inter-individual variation of brain signals impedes real-time detection of events in raw signals. To convert these complex signals into results that can be readily understood, current approaches usually apply statistical methods to data from known conditions after all data have been collected. The capability to provide meaningful visualization of complex brain signals without the requirement to initially collect data from all conditions would provide a new tool, essentially a new imaging technique, that would open up new avenues for the study of brain function. Here we show that a new analysis approach, called SIGFRIED, can overcome this serious limitation of current methods. SIGFRIED can visualize brain signal changes without requiring prior data collection from all conditions. This capacity is particularly well suited to applications in which comprehensive prior data collection is impossible or impractical, such as intraoperative localization of cortical function or detection of epileptic seizures.

%B Neuroimage %V 43 %P 245-9 %8 11/2008 %G eng %U http://www.ncbi.nlm.nih.gov/pubmed/18718544 %N 2 %R 10.1016/j.neuroimage.2008.07.037 %0 Journal Article %J J Neural Eng %D 2007 %T Decoding two-dimensional movement trajectories using electrocorticographic signals in humans. %A Gerwin Schalk %A Kubánek, J %A Miller, John W %A Nicholas R Anderson %A Leuthardt, E C %A Ojemann, J G %A Limbrick, D %A Moran, D %A Lester A Gerhardt %A Jonathan Wolpaw %K Adult %K Algorithms %K Arm %K Brain Mapping %K Cerebral Cortex %K Electroencephalography %K Evoked Potentials, Motor %K Female %K Humans %K Male %K Movement %X

Signals from the brain could provide a non-muscular communication and control system, a brain-computer interface (BCI), for people who are severely paralyzed. A common BCI research strategy begins by decoding kinematic parameters from brain signals recorded during actual arm movement. It has been assumed that these parameters can be derived accurately only from signals recorded by intracortical microelectrodes, but the long-term stability of such electrodes is uncertain. The present study disproves this widespread assumption by showing in humans that kinematic parameters can also be decoded from signals recorded by subdural electrodes on the cortical surface (ECoG) with an accuracy comparable to that achieved in monkey studies using intracortical microelectrodes. A new ECoG feature labeled the local motor potential (LMP) provided the most information about movement. Furthermore, features displayed cosine tuning that has previously been described only for signals recorded within the brain. These results suggest that ECoG could be a more stable and less invasive alternative to intracortical electrodes for BCI systems, and could also prove useful in studies of motor function.

%B J Neural Eng %V 4 %P 264-75 %8 09/2007 %G eng %U http://www.ncbi.nlm.nih.gov/pubmed/17873429 %N 3 %R 10.1088/1741-2560/4/3/012