Do the stimuli of an SSVEP-based BCI really have to be the same as the stimuli used for training it?

Évain, Andéol; Argelaguet, Ferran; Casiez, Géry; Roussel, Nicolas; Lécuyer, Anatole

doi:10.1080/2326263x.2016.1193458

Cited by 3 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to combine several two-class LDA classifier to classify between more classes, the chosen class is the one maximizing d i . Previous studies Évain et al ( 2016 ) have found that such a classifier shows a precision of the order of 65% for each 0.5 s time window. A better accuracy can be reached by adding a voting step.…”

Section: Combining Gaze and Bci Inputs For Target Selectionmentioning

confidence: 87%

“…The resulting optimal parameters found in this pre-experiment (see Table 2 ) were used for the main experiment. Overall, the sequential method is prone to generate false positives, because of the limited precision of the BCI, the raw accuracy of the BCI classifier p is estimated at 65%, based on previous studies with similar design and signal processing (Évain et al, 2016 ). Thus, in order to optimize the sensitivity, the chosen parameters were quite conservative, with a high threshold of activation.…”

Section: Experimental Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Design and Evaluation of Fusion Approach for Combining Brain and Gaze Inputs for Target Selection

et al. 2016

Self Cite

View full text Add to dashboard Cite

Gaze-based interfaces and Brain-Computer Interfaces (BCIs) allow for hands-free human–computer interaction. In this paper, we investigate the combination of gaze and BCIs. We propose a novel selection technique for 2D target acquisition based on input fusion. This new approach combines the probabilistic models for each input, in order to better estimate the intent of the user. We evaluated its performance against the existing gaze and brain–computer interaction techniques. Twelve participants took part in our study, in which they had to search and select 2D targets with each of the evaluated techniques. Our fusion-based hybrid interaction technique was found to be more reliable than the previous gaze and BCI hybrid interaction techniques for 10 participants over 12, while being 29% faster on average. However, similarly to what has been observed in hybrid gaze-and-speech interaction, gaze-only interaction technique still provides the best performance. Our results should encourage the use of input fusion, as opposed to sequential interaction, in order to design better hybrid interfaces.

show abstract

Section: Combining Gaze and Bci Inputs For Target Selectionmentioning

confidence: 87%

Section: Experimental Evaluationmentioning

confidence: 99%

Design and Evaluation of Fusion Approach for Combining Brain and Gaze Inputs for Target Selection

et al. 2016

Self Cite

View full text Add to dashboard Cite

show abstract

“…Qualitative properties: Shape, spherical or rectangular/sharp, symmetrical or not, convex or concave, etc; Size, big/small, or fitting in one's hand, etc; Material, it can be rugged or smooth, organic or plastic, etc; Color, the difference in colours of targets in SSVEP [74] influenced performance. The largest SSVEP response was produced by red light at 11Hz [91].…”

Section: Object Propertiesmentioning

confidence: 99%

“…Moreover, word auto-completions were developed for faster P300 spelling [75]. For SSVEP, 'using distant targets of different colours seems to lead to the best and more robust performance in all end use contexts' [76]. In addition, SSVEP does not require a high visual attention or cognitive workload [17].…”

Section: Related Work On Bci User Trainingmentioning

confidence: 99%

“…The perception (affordance) of object properties (in visual, auditory or haptic modality) does not necessarily depend on any previous experience (a priori knowledge), can vary in: 4.4.1.1. Qualitative properties Shape, spherical or rectangular/sharp, symmetrical or not, convex or concave, etc; Size, big/small, or fitting in one's hand, etc; Material, it can be rugged or smooth, organic or plastic, etc; Colour, the difference in colours of targets in SSVEP [76] influenced performance. The largest SSVEP response was produced by red light at 11 Hz [93].…”

Section: Object Propertiesmentioning

confidence: 99%

See 1 more Smart Citation

Standardization of protocol design for user training in EEG-based Brain-Computer Interface

Mladenović¹

2020

J. Neural Eng.

View full text Add to dashboard Cite

Brain-computer interfaces (BCIs) are systems that enable a person to interact with a machine using only neural activity. Such interaction can be non-intuitive for the user hence training methods are developed to increase one's understanding, confidence and motivation, which would in parallel increase system performance. To clearly address the current issues in the BCI user training protocol design, here it is divided into introductory period and BCI interaction period. First, the introductory period (before BCI interaction) must be considered as equally important as the BCI interaction for user training. To support this claim, a review of papers show that BCI performance can depend on the methodologies presented in such introductory period. To standardize its design, the literature from human-computer interaction (HCI) is adjusted to the BCI context. Second, during the user-BCI interaction, the interface can take a large spectrum of forms (2D, 3D, size, color etc.) and modalities (visual, auditory or haptic etc.) without following any design standard or guidelines. Namely, studies that explore perceptual affordance on neural activity show that motor neurons can be triggered from a simple observation of certain objects, and depending on objects' properties (size, location etc.) neural reactions can vary greatly. Surprisingly, the effects of perceptual affordance were not investigated in the BCI context. Both inconsistent introductions to BCI as well as variable interface designs make it difficult to reproduce experiments, predict their outcomes and compare results between them. To address these issues, a protocol design standardization for user training is proposed.

show abstract

Evaluating the Effect of Stimuli Color and Frequency on SSVEP

Duart

Quiles

Suay

et al. 2020

Sensors

View full text Add to dashboard Cite

Brain–computer interfaces (BCI) can extract information about the subject’s intentions by registering and processing electroencephalographic (EEG) signals to generate actions on physical systems. Steady-state visual-evoked potentials (SSVEP) are produced when the subject stares at flashing visual stimuli. By means of spectral analysis and by measuring the signal-to-noise ratio (SNR) of its harmonic contents, the observed stimulus can be identified. Stimulus color matters, and some authors have proposed red because of its ability to capture attention, while others refuse it because it might induce epileptic seizures. Green has also been proposed and it is claimed that white may generate the best signals. Regarding frequency, middle frequencies are claimed to produce the best SNR, although high frequencies have not been thoroughly studied, and might be advantageous due to the lower spontaneous cerebral activity in this frequency band. Here, we show white, red, and green stimuli, at three frequencies: 5 (low), 12 (middle), and 30 (high) Hz to 42 subjects, and compare them in order to find which one can produce the best SNR. We aim to know if the response to white is as strong as the one to red, and also if the response to high frequency is as strong as the one triggered by lower frequencies. Attention has been measured with the Conner’s Continuous Performance Task version 2 (CPT-II) task, in order to search for a potential relationship between attentional capacity and the SNR previously obtained. An analysis of variance (ANOVA) shows the best SNR with the middle frequency, followed by the low, and finally the high one. White gives as good an SNR as red at 12 Hz and so does green at 5 Hz, with no differences at 30 Hz. These results suggest that middle frequencies are preferable and that using the red color can be avoided. Correlation analysis also show a correlation between attention and the SNR at low frequency, so suggesting that for the low frequencies, more attentional capacity leads to better results.

show abstract

Do the stimuli of an SSVEP-based BCI really have to be the same as the stimuli used for training it?

Cited by 3 publications

References 20 publications

Design and Evaluation of Fusion Approach for Combining Brain and Gaze Inputs for Target Selection

Design and Evaluation of Fusion Approach for Combining Brain and Gaze Inputs for Target Selection

Standardization of protocol design for user training in EEG-based Brain-Computer Interface

Evaluating the Effect of Stimuli Color and Frequency on SSVEP

Contact Info

Product

Resources

About