Abstract

Keyboards and smartphones allow users to express their thoughts freely via manual control. Hands-free communication can be realized with brain–computer interfaces (BCIs) based on code-modulated visual evoked potentials (c-VEPs). Various variations of such spellers have been developed: Low-target systems, multi-target systems and systems with dictionary support. In general, it is not clear which kinds of systems are optimal in terms of reliability, speed, cognitive load, and visual load. The presented study investigates the feasibility of different speller variations. 58 users tested a 4-target speller and a 32-target speller with and without dictionary functionality. For classification, multiple individualized spatial filters were generated via canonical correlation analysis (CCA). We used an asynchronous implementation allowing non-control state, thus aiming for high accuracy rather than speed. All users were able to control the tested spellers. Interestingly, no significant differences in accuracy were found: 94.4%, 95.5% and 94.0% for 4-target spelling, 32-target spelling, and dictionary-assisted 32-target spelling. The mean ITRs were highest for the 32-target interface: 45.2, 96.9 and 88.9 bit/min. The output speed in characters per minute, was highest in dictionary-assisted spelling: 8.2, 19.5 and 31.6 characters/min. According to questionnaire results, 86% of the participants preferred the 32-target speller over the 4-target speller.

Highlights

  • Brain–computer interfaces (BCIs) hold the potential to aid people with severe clinical disorders in their daily life as they allow hands-free control and communication

  • For the code-modulated visual evoked potentials (VEPs) (c-VEPs) paradigm, the flickering patterns are modulated with different time lags of a binary code sequence; EEG templates for each stimulus class need to be generated from data collected in a recording session

  • The few VEP spellers with dictionary support fall in the category of asynchronous low-target systems: Volosyak et al.[31] presented a dictionary feature for an asynchronous multi-step frequency-modulated VEPs (f-VEPs) system, where a drop-down list containing six dictionary suggestions was employed; more recently, we presented an asynchronous multi-step 8-target c-VEP system offering word suggestions based on an n-gram word prediction ­model[32]

Read more

Summary

Introduction

Brain–computer interfaces (BCIs) hold the potential to aid people with severe clinical disorders in their daily life as they allow hands-free control and communication. These systems translate the BCI users’ brain activity, usually acquired non-invasively via electroencephalography (EEG), into control commands for external d­ evices[1]. Various BCI communication applications (typically referred to as spellers) have been realized over the last years They have been categorized according to the analysed brain signal While low-target spellers allow high classification accuracies, the overall spelling speed is limited, as several selection intervals (typically consisting of stimulation intervals and flicker-free intervals for gaze-shifting, where users can shift their gaze to the target) are required for letter selections

Objectives
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call