30-Targets Hybrid BNCI Speller Based on SSVEP and EMG

Aya Rezeika, Mihaly Benda, Piotr Stawicki, Felix Gembler, Abdul Saboor, Ivan Volosyak

2018 · 13 citations · 18 references

Concepts

Abstract

Brain-Computer Interface (BCI) interprets brain signals, which are measured by an electroencephalogram (EEG), allowing people to communicate without the need for any muscular movement. One of the most commonly discussed applications in literature is BCI speller as a communication modality for people with disabilities. In Brain-Neural Computer Interface (BNCI) other biosignals are merged with the brain signals to combine the advantages of both. Consequently, the here-studied hybrid BCI system discusses the parallel usage of an Steady-State Visual Evoked Potential (SSVEP) BCI and surface-electromyographic (sEMG) activity to accomplish a faster performance for a more accurate spelling application. sEMG signal was used for the activation of target selection for an SSVEP-based speller. Eight participants carried out three copy-spelling tasks for each system (six in total) to compare between both paradigms: SSVEP alone and the hybrid speller. Results showed that the hybrid speller can achieve faster performances without affecting the accuracy (mean accuracy 92.37%, 93.75%, and 100%, mean ITR 37.37, 33.41, and 31.05 bits/min), verifying our hypothesis. In addition, participants who experienced difficulties controlling the SSVEP speller were able to control the hybrid system.

References

18