Channel selection methods for the P300 Speller

Abstract

The P300 Speller brain-computer interface (BCI) allows a user to communicate without muscle activity by reading electrical signals on the scalp via electroencephalogram. Modern BCI systems use multiple electrodes (“channels”) to collect data, which has been shown to improve speller accuracy; however, system cost and setup time can increase substantially with the number of channels in use, so it is in the user’s interest to use a channel set of modest size. This constraint increases the importance of using an effective channel set, but current systems typically utilize the same channel montage for each user. We examine the effect of active channel selection for individuals on speller performance, using generalized standard feature-selection methods, and present a new channel selection method, termed Jumpwise Regression, that extends the Stepwise Linear Discriminant Analysis classifier. Simulating the selections of each method on real P300 Speller data, we obtain results demonstrating that active channel selection can improve speller accuracy for most users relative to a standard channel set, with particular benefit for users who experience low performance using the standard set. Of the methods tested, Jumpwise Regression offers accuracy gains similar to the best-performing feature-selection methods, and is robust enough for online use.

Using the detectability index to predict P300 speller performance

“…For some BCI algorithm parameters or strategies, it is easier to do a grid search over parameter values to maximize performance of a given user dataset, as is typically done in the BCI literature for exploratory analysis, e.g. electrode channel selection [44], classifier type [45], dynamic stopping algorithms [42], etc. However, it is not possible to use such an approach for analyzing different stimulus presentation paradigms.…”

On P300 Detection using Scalar Products

“…4 is an average and b. each waveform exhibiting P300 has its own shape which will not necessary give a high scalar product with the above pattern. To keep things as simple as possible, we selected a list of most important channels by making the scalar product with segments extracted from each one [8], [9]. More precisely we wanted to find which channels are the best in terms of the classification rate.…”

Binary DE-Based Channel Selection and Weighted Ensemble of SVM Classification for Novel Brain–Computer Interface Using Devanagari Script-Based P300 Speller Paradigm

“…Lesser number of electrodes also increases the ITR by reducing the computational complexity. To select the most effective electrode configuration for classification, different electrode/channel selection methods such as recursive A c c e p t e d M a n u s c r i p t 8 channel elimination (Schröder et al, 2005), jump-wise regression (Colwell, Ryan, Throckmorton, Sellers, & Collins, 2014), Gibbs sampling (Speier, Deshpande, & Pouratian, 2015), Multi-ganglion ANN (Gao, Guan, Gao, & Zhou, 2015), Particle Swarm Optimization (PSO) (Jin, et al, 2010) and Genetic Algorithm (GA) (Kee, Ponnambalam, & Loo, 2015;Kee, Chetty, Khoo, & Ponnambalam, 2012) have been developed in recent years. The research shows that the best electrode configuration is subject dependent and hence the best configuration need to be selected for each subject (Blankertz et al, 2008;Rivet, Cecotti, Maby, & Mattout, 2012;Xu et al, 2013).…”