Krusienski Dean J, Sellers Eric W, Cabestaing François, Bayoudh Sabri, McFarland Dennis J, Vaughan Theresa M, Wolpaw Jonathan R
Wadsworth Center, New York State Department of Health, Albany, NY 12201, USA.
J Neural Eng. 2006 Dec;3(4):299-305. doi: 10.1088/1741-2560/3/4/007. Epub 2006 Oct 26.
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.
本研究评估了五种既定分类技术在使用P300拼写器范式收集的数据上的相对性能特征，该范式最初由法韦尔和唐钦于1988年描述（《脑电图与临床神经生理学》，第70卷，第510页）。比较了四种线性方法：皮尔逊相关法（PCM）、费舍尔线性判别法（FLD）、逐步线性判别分析（SWLDA）和线性支持向量机（LSVM）；以及一种非线性方法：高斯核支持向量机（GSVM），用于对来自八位用户的离线数据进行分类。评估了分类器的相对性能，以及与各自方法实施相关的实际问题。结果表明，虽然所有方法都达到了可接受的性能水平，但SWLDA和FLD在P300拼写器数据的实际分类中提供了最佳的总体性能和实施特征。
