Robust EEG Channel Selection across Subjects for Brain-Computer Interfaces

Abstract

Most EEG-based brain-computer interface (BCI) paradigms come along with specific electrode positions, for example, for a visual-based BCI, electrode positions close to the primary visual cortex are used. For new BCI paradigms it is usually not known where task relevant activity can be measured from the scalp. For individual subjects, Lal et al. in 2004 showed that recording positions can be found without the use of prior knowledge about the paradigm used. However it remains unclear to what extent their method of recursive channel elimination (RCE) can be generalized across subjects. In this paper we transfer channel rankings from a group of subjects to a new subject. For motor imagery tasks the results are promising, although cross-subject channel selection does not quite achieve the performance of channel selection on data of single subjects. Although the RCE method was not provided with prior knowledge about the mental task, channels that are well known to be important (from a physiological point of view) were consistently selected whereas task-irrelevant channels were reliably disregarded

A review of channel selection algorithms for EEG signal processing

“…Schroder et al [65] presented a robust EEG channel selection algorithm across subjects in BCI systems adopting an embedded approach with a sequential search strategy for subset channel selection. They tried to investigate whether channels selected for one subject are useful to the others as well.…”

Cost-Effective EEG Signal Acquisition and Recording System

“…For example, C 3 and C 4 can be used to record the right and left finger movement related signals respectively for brain-computer interfacing (BCI) applications. Also F3, F4, P3 and P4 can be used for recording the ERP P300 signals [7]. In another similar setting, called the Maudsley electrode positioning system, the conventional 10-20 system has been modified to capture better the signals from epileptic foci in epileptic seizure recordings.…”

Composite kernel learning

“…Depending on each BCI paradigm, these EEG signals are recorded from specific electrode positions. However, as stated by Schröder et al (2005), automated channel selection should be performed for each single subject since it leads to better performances or a substantial reduction of the number of useful channels. Reducing the number of channels involved in the decision function is of primary importance for BCI real-life applications, since it makes the acquisition system easier to use and to set-up.…”