A comparison study of visually stimulated brain–computer and eye-tracking interfaces

Suefusa, Kaori; Tanaka, Toshihisa

doi:10.1088/1741-2552/aa6086

Cited by 25 publications

(26 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can be seen that eye tracking predictions had no errors, as the size of the target box was large enough to be detected correctly. This is consistent with the previous studies which have shown that eye tracking classifications are low if the targets are densely located with small sizes [65]. In contrast, the SSVEP predictions showed misclassifications, specifically for frequency six.…”

Section: Discussionsupporting

confidence: 93%

“…Therefore, it is our immediate future plan to study the effect of all these parameters on the performance of the proposed system and to select optimal parameters with best performance. It is important to mention here that, whereas eye-tracker-based spellers' spelling rate is 5 to 10 words per minute [28,98], they require a high sampling rate as well as a high level of user concentration on the target (i.e., "gaze control" without any movement), which is difficult for most people to manage [65,99]. Furthermore, the equipment needed for such eye tracking in real time is, at least at present, expensive, which makes it impractical for application [100].…”

Section: Discussionmentioning

confidence: 99%

“…The data in this paper showed an average accuracy of 85.8% and an average ITR of 90.9 bits/min. Furthermore, eye tracking-based assistive technologies are emerging as an alternative tool to BCIs [65,66]. The development of modern camera systems and the increase of computing power has enabled the gathering of eye tracking data in real time, enabling the use of gaze as a control method for people with disabilities [67][68][69][70][71][72][73].…”

Section: Introductionmentioning

confidence: 99%

“…The development of modern camera systems and the increase of computing power has enabled the gathering of eye tracking data in real time, enabling the use of gaze as a control method for people with disabilities [67][68][69][70][71][72][73]. A comparison study of BCI, eye tracking, and electrooculography interfaces reported that participants found the BCI to be the easiest to use and eye tracking to be the least tiring [65]. They also showed that an SSVEP-based BCI performed better than an eye tracking-based speller when targets are densely located and small in size.…”

Section: Introductionmentioning

confidence: 99%

“…They also showed that an SSVEP-based BCI performed better than an eye tracking-based speller when targets are densely located and small in size. Recently, eye tracking has been combined with EEG to remove ocular artifacts from EEG signals [74,75] and to develop hybrid BCI systems [65,[76][77][78][79][80][81]. All these studies have shown improved performance as compared to EEG only, as well as the feasibility of combining EEG with eye tracking.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Hybrid Speller Design Using Eye Tracking and SSVEP Brain–Computer Interface

Mannan

Kamran

Kang

et al. 2020

Sensors

View full text Add to dashboard Cite

Steady-state visual evoked potentials (SSVEPs) have been extensively utilized to develop brain–computer interfaces (BCIs) due to the advantages of robustness, large number of commands, high classification accuracies, and information transfer rates (ITRs). However, the use of several simultaneous flickering stimuli often causes high levels of user discomfort, tiredness, annoyingness, and fatigue. Here we propose to design a stimuli-responsive hybrid speller by using electroencephalography (EEG) and video-based eye-tracking to increase user comfortability levels when presented with large numbers of simultaneously flickering stimuli. Interestingly, a canonical correlation analysis (CCA)-based framework was useful to identify target frequency with a 1 s duration of flickering signal. Our proposed BCI-speller uses only six frequencies to classify forty-eight targets, thus achieve greatly increased ITR, whereas basic SSVEP BCI-spellers use an equal number of frequencies to the number of targets. Using this speller, we obtained an average classification accuracy of 90.35 ± 3.597% with an average ITR of 184.06 ± 12.761 bits per minute in a cued-spelling task and an ITR of 190.73 ± 17.849 bits per minute in a free-spelling task. Consequently, our proposed speller is superior to the other spellers in terms of targets classified, classification accuracy, and ITR, while producing less fatigue, annoyingness, tiredness and discomfort. Together, our proposed hybrid eye tracking and SSVEP BCI-based system will ultimately enable a truly high-speed communication channel.

show abstract

Section: Discussionsupporting

confidence: 93%