Generic Channels Selection in Motor Imagery-Based BCI

Abstract

There has been increasing interest in motor imagery (MI)-based braincomputer interfaces (BCIs). Since the brain activities of MI locate in a certain brain region, how to select appropriate channels is important to improve the performance of BCIs. In this paper, sequential floating forward selection (SFFS) and common spatial pattern (CSP) were used to select the optimal electrode channels. In order to improve the usability of selected channels, a configuration of generic channels was obtained based on the selected channels for each subject. The results showed that the generic channels could yield better performance compared to traditionally used channels.

Bispectrum-Based Channel Selection for Motor Imagery Based Brain-Computer Interfacing

“…In order to solve the problem of performance degradation due to the redundant information and noise across multiple EEG channels [17], many researchers have proposed channel selection methods for MI-based BCI. Considering the neurophysiologic knowledge, the simplest channel selection method is to extract data from EEG channels Cz, C3, and C4, which are located over the motor cortex.…”

“…Channel selection methods can be categorized as either filter [18] or wrapper [17] based methods. Filter methods usually select channels based on F score, mutual information or another criterion.…”

“…In contrast, wrapper methods make use of a classifier to validate the effects of different sets of selected channels. However, those methods are most frequently used to select channels based on their temporal [18], [19] or spatial features [17].…”

Incorporation of dynamic stopping strategy into the high-speed SSVEP-based BCIs

“…In recent years, the non-invasive scalp electroencephalogram (EEG) is widely used in BCIs because of its relatively low hardware costs and high temporal resolution. The most commonly used brain control signals are P300 [2][3][4][5], sensorimotor rhythm (SMR) [6,7], steady-state visual evoked potential (SSVEP) [8][9][10][11] and their combinations [12][13][14][15]. Among them, the SSVEP is a periodic neural response to the repetitive visual stimulation, which occurs in the visual cortex at the flickering frequency and its harmonics [16].…”