<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Gerwin Schalk</style></author><author><style face="normal" font="default" size="100%">Peter Brunner</style></author><author><style face="normal" font="default" size="100%">Lester A Gerhardt</style></author><author><style face="normal" font="default" size="100%">H Bischof</style></author><author><style face="normal" font="default" size="100%">Jonathan Wolpaw</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Brain-computer interfaces (BCIs): Detection Instead of Classification.</style></title><secondary-title><style face="normal" font="default" size="100%">J Neurosci Methods</style></secondary-title><alt-title><style face="normal" font="default" size="100%">J. Neurosci. Methods</style></alt-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Adult</style></keyword><keyword><style  face="normal" font="default" size="100%">Algorithms</style></keyword><keyword><style  face="normal" font="default" size="100%">Brain</style></keyword><keyword><style  face="normal" font="default" size="100%">Brain Mapping</style></keyword><keyword><style  face="normal" font="default" size="100%">Electrocardiography</style></keyword><keyword><style  face="normal" font="default" size="100%">Electroencephalography</style></keyword><keyword><style  face="normal" font="default" size="100%">Humans</style></keyword><keyword><style  face="normal" font="default" size="100%">Male</style></keyword><keyword><style  face="normal" font="default" size="100%">Man-Machine Systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Normal Distribution</style></keyword><keyword><style  face="normal" font="default" size="100%">Online Systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Signal Detection, Psychological</style></keyword><keyword><style  face="normal" font="default" size="100%">Signal Processing, Computer-Assisted</style></keyword><keyword><style  face="normal" font="default" size="100%">Software Validation</style></keyword><keyword><style  face="normal" font="default" size="100%">User-Computer Interface</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year><pub-dates><date><style  face="normal" font="default" size="100%">01/2008</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://www.ncbi.nlm.nih.gov/pubmed/17920134</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">167</style></volume><pages><style face="normal" font="default" size="100%">51-62</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;Many studies over the past two decades have shown that people can use&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;signals to convey their intent to a&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;computer&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;through&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain-computer interfaces&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;(BCIs). These devices operate by recording signals from the&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;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&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;clinical&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;applications is the current requirement for preliminary analyses to identify the&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;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&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;activity so that any change in&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;relevant&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;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&amp;nbsp;&lt;/span&gt;&lt;span class=&quot;highlight&quot; style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;brain&lt;/span&gt;&lt;span style=&quot;font-family: arial, helvetica, clean, sans-serif; font-size: 13px; line-height: 17px;&quot;&gt;&amp;nbsp;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.&lt;/span&gt;&lt;/p&gt;</style></abstract><issue><style face="normal" font="default" size="100%">1</style></issue></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Krusienski, Dean J.</style></author><author><style face="normal" font="default" size="100%">Sellers, Eric W.</style></author><author><style face="normal" font="default" size="100%">Cabestaing, François</style></author><author><style face="normal" font="default" size="100%">Bayoudh, Sabri</style></author><author><style face="normal" font="default" size="100%">Dennis J. McFarland</style></author><author><style face="normal" font="default" size="100%">Theresa M Vaughan</style></author><author><style face="normal" font="default" size="100%">Jonathan Wolpaw</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">A comparison of classification techniques for the P300 Speller.</style></title><secondary-title><style face="normal" font="default" size="100%">Journal of neural engineering</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Normal Distribution</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2006</style></year><pub-dates><date><style  face="normal" font="default" size="100%">12/2006</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">http://www.ncbi.nlm.nih.gov/pubmed/17124334</style></url></web-urls></urls><volume><style face="normal" font="default" size="100%">3</style></volume><pages><style face="normal" font="default" size="100%">299–305</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">This study assesses the relative performance characteristics of five established classification techniques on data collected using the P300 Speller paradigm, originally described by Farwell and Donchin (1988 Electroenceph. Clin. Neurophysiol. 70 510). Four linear methods: Pearson's correlation method (PCM), Fisher's linear discriminant (FLD), stepwise linear discriminant analysis (SWLDA) and a linear support vector machine (LSVM); and one nonlinear method: Gaussian kernel support vector machine (GSVM), are compared for classifying offline data from eight users. The relative performance of the classifiers is evaluated, along with the practical concerns regarding the implementation of the respective methods. The results indicate that while all methods attained acceptable performance levels, SWLDA and FLD provide the best overall performance and implementation characteristics for practical classification of P300 Speller data.</style></abstract></record></records></xml>