A comparison of classification techniques for the P300 Speller
University at Albany, State University of New York · Wadsworth Center · +5 more institutions
Abstract
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…
Citation impact
- FWCI
- 8.23
- Percentile
- 100%
- References
- 30
Authors
7- DJDean J. KrusienskiCorresponding
University at Albany, State University of New York, Wadsworth Center, New York State Department of Health
- EWEric W. Sellers
University at Albany, State University of New York, Wadsworth Center, New York State Department of Health
- FCFrançois Cabestaing
Centre National de la Recherche Scientifique, Laboratoire d'Automatique, Génie Informatique et Signal
- SBSabri Bayoudh
Institut de Recherche en Informatique et Systèmes Aléatoires, Université de Rennes
- DJDennis J. McFarland
University at Albany, State University of New York, Wadsworth Center, New York State Department of Health
Topics & keywords
- Linear discriminant analysis
- Computer science
- Support vector machine
- Artificial intelligence
- Pattern recognition (psychology)
- Kernel Fisher discriminant analysis
- Machine learning
- Kernel (algebra)
- Reduced inequalities