Related Experiment Video
Updated: May 26, 2026

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Published on: September 8, 2023
A comparison among several P300 brain-computer interface speller paradigms
Reza Fazel-Rezai1, Scott Gavett, Waqas Ahmad
1Biomedical Signal Processing Laboratory, Department of Electrical Engineering, University of North Dakota, Grand Forks, 58202-7165, USA. Reza.Fazel-Rezai@engr.und.edu
Abstract:
Since the brain-computer interface (BCI) speller was first proposed by Farwell and Donchin, there have been modifications in the visual aspects of P300 paradigms. Most of the changes are based on the original matrix format such as changes in the number of rows and columns, font size, flash/ blank time, and flash order. The improvement in the resulting accuracy and speed of such systems has always been the ultimate goal. In this study, we have compared several different speller paradigms including row-column, single character flashing, and two region-based paradigms which are not based on the matrix format. In the first region-based paradigm, at the first level, characters and symbols are distributed over seven regions alphabetically, while in the second region-based paradigm they are distributed in the most frequently used order. At the second level, each one of the regions is further subdivided into seven subsets. The experimental results showed that the average accuracy and user acceptability for two region-based paradigms were higher than those for traditional paradigms such as row/column and single character.

