An Efficient Classifier for P300 in Brain–Computer Interface Based on Scalar Products
In this paper, a simple but efficient method for detection of P300 waveform in a Brain–Computer Interface (BCI) is presented. The proposed method is based on computing scalar products between the waveforms to be classified and a P300 pattern. Depending on the degree of concentration of the subject and the number of trails, rates of recognition between 85 and 100% have been obtained.
KeywordsBCI EEG signal Signal processing P300 Classification
We want to thank all human subjects who have voluntarily participated in experiment and Ulrich Hoffmann and his team for permission to use the EEG data available on the Internet.
- 9.Donchin E (1980) Presidential address. Surprise!…Surprise? Psychophysiology 18:493–513Google Scholar
- 10.Fabiani M, Gratton G, Karis D, Donchin E (1987) Definition, identification and reliability of the P300 component of the event-related brain potential. In: Ackles PK, Jennings JR, Coles MGH (eds) Advances in psychophysiology, vol 2. JAI Press, New York, pp 1–78Google Scholar
- 11.Polich J (1999) P300 in clinical applications. In: Niedermeyer E, Lopes da Silva FH (eds) Electroencephalography: basic principles, clinical applications and related fields, 4th edn. Williams and Wilkins, Baltimore, pp 1073–1091Google Scholar
- 13.Coles MGH, Rugg MD (1995) Event-related potentials: an introduction. In: Rugg MD, Coles MGH (eds) Electrophysiology of the mind: event-related brain potentials and cognition. Oxford University Press, New YorkGoogle Scholar