A Synchronous Motor Imagery Based Neural Physiological Paradigm for Brain Computer Interface Speller.

Lei Cao,Jie Li,Niels Birbaumer,Oladazimi Maysam,Bin Xia,Hong Xie

doi:10.3389/fnhum.2017.00274

Abstract

Brain Computer Interface (BCI) speller is a typical BCI-based application to help paralyzed patients express their thoughts. This paper proposed a novel motor imagery based BCI speller with Oct-o-spell paradigm for word input. Furthermore, an intelligent input method was used for improving the performance of the BCI speller. For the English word spelling experiment, we compared synchronous control with previous asynchronous control under the same experimental condition. There were no significant differences between these two control methods in the classification accuracy, information transmission rate (ITR) or letters per minute (LPM). And the accuracy rates of over 70% validated the feasibility for these two control strategies. It was indicated that MI-based synchronous control protocol was feasible for BCI speller. And the efficiency of the predictive text entry (PTE) mode was superior to that of the Non-PTE mode.

Highlights

Brain-computer interface (BCI) system builds a communication bridge between the brain and the external world by transforming neural signals into control commands without body movement (Birbaumer et al, 1999; Pfurtscheller et al, 2000; Guger et al, 2003; Blankertz et al, 2004; Birbaumer, 2006; Wolpaw, 2014)
We developed a 2-D cursor control strategy using the modified Hex-o-Spell paradigm and an asynchronous control switch was used for starting the system
There were no significant differences between these two control methods in Accuracy rate (ACC), information transmission rate (ITR) or letters per minute (LPM)

Summary

Introduction

Brain-computer interface (BCI) system builds a communication bridge between the brain and the external world by transforming neural signals into control commands without body movement (Birbaumer et al, 1999; Pfurtscheller et al, 2000; Guger et al, 2003; Blankertz et al, 2004; Birbaumer, 2006; Wolpaw, 2014). Electroencephalogram (EEG) is commonly used for BCI This technology is developed based on neurophysiological patterns such as event related potentials (ERPs) (Blankertz et al, 2011; Zhang et al, 2012; Jin et al, 2014; Yeom et al, 2014), slow cortical potentials (Mensh et al, 2004; Kübler and Birbaumer, 2008),event-related desynchronization/synchronization (Pfurtscheller and Neuper, 2006; Pfurtscheller et al, 2010; Lisi et al, 2014; Sandhya et al, 2014) and steady-state evoked potentials (SSVEPs) (Müller-Putz and Pfurtscheller, 2008; Wang et al, 2008; Allison et al, 2010). P300 spellers have been studied for improving signal processing (Kindermans et al, 2012; Throckmorton et al, 2013; Mainsah et al, 2014a; Speier et al, 2014, 2015)

Methods

Results

Conclusion