Gaze-independent brain–computer interfaces based on covert attention and feature attention

Treder, Matthias S.; Schmidt, Nico M.; Blankertz, Benjamin

doi:10.1088/1741-2560/8/6/066003

Cited by 166 publications

(169 citation statements)

References 57 publications

Supporting

Mentioning

159

Contrasting

Unclassified

Order By: Relevance

“…RSVP-based BCIs pose a very attractive alternative for the development of gaze-independent systems that are suitable for severely locked-in people with no gaze control [54], [55], [28]. Thus, we believe that the study presented can help improve BCIs aimed at communication systems by the disabled, e.g., by investigating whether the explicit use of the N2pc can help determine which column the user is focusing on.…”

Section: Discussionmentioning

confidence: 99%

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Matran-Fernandez

Poli

2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-Objective. The N2pc event-related potential (ERP) appears on the opposite side of the scalp with respect to the visual hemisphere where an object of interest is located. We explored the feasibility of using it to extract information on the spatial location of targets in aerial images shown by means of a rapid serial visual presentation (RSVP) protocol using single-trial classification. Methods. Images were shown to 11 participants at a presentation rate of 5 Hz while recording electroencephalographic signals.With the resulting ERPs we trained linear classifiers for singletrial detection of target presence and location. We analysed the classifiers' decisions and their raw output scores on independent test sets as well as the averages and voltage distributions of the ERPs. Results. The N2pc is elicited in RSVP presentation of complex images and can be recognised in single trials (the median area under the receiver operating characteristic curve was 0.76 for left vs right classification). Moreover, the peak amplitude of this ERP correlates with the horizontal position of the target within an image. The N2pc varies significantly depending on handedness, and these differences can be used for discriminating participants in terms of their preferred hand. Conclusion and Significance. The N2pc is elicited during RSVP presentation of real complex images and contains analogue information that can be used to roughly infer the horizontal position of targets. Furthermore, differences in the N2pc due to handedness should be taken into account when creating collaborative brain-computer interfaces.

show abstract

Section: Discussionmentioning

confidence: 99%

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Matran-Fernandez

Poli

2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…Since then, several variations have been proposed changing the interface [4] or the modality [5], [6]. The original idea, however, remains; the user communicates by focusing attention to one of several offered options and thereby conveys her/his intention to the BCI.…”

Section: Introductionmentioning

confidence: 99%

Performance optimization of ERP-based BCIs using dynamic stopping

Schreuder

Höhne

Treder

et al. 2011

2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society

View full text Add to dashboard Cite

Abstract-Brain-computer interfaces based on event-related potentials face a trade-off between the speed and accuracy of the system, as both depend on the number of iterations. Increasing the number of iterations leads to a higher accuracy but reduces the speed of the system. This trade-off is generally dealt with by finding a fixed number of iterations that give a good result on the calibration data. We show here that this method is sub optimal and increases the performance significantly in only one out of five datasets. Several alternative methods have been described in literature, and we test the generalization of four of them. One method, called rank diff, significantly increased the performance over all datasets. These findings are important, as they show that 1) one should be cautious when reporting the potential performance of a BCI based on post-hoc offline performance curves and 2) simple methods are available that do boost performance.

show abstract

“…For comparison, P300 spellers that are based on covert attention (i.e. without eye movements) reach an ITR of around 6 bits/min (based on visual spellers reviewed in Riccio et al, 2012) , usually with a combination of trained and untrained participants (e.g., Acqualagna & Blankertz, 2013;Treder et al, 2011) . The performance of our method is thus in the same range as that of the best non-invasive covertattention BCIs to date.…”

Section: Discussionmentioning

confidence: 99%

“…This was problematic for real-world applications, because BCIs are mostly useful if they work without any overt (eye) movement; otherwise, movement-based methods, such as eye PrePrints system used by Stephen Hawking, are much more efficient. However, modern P300 spellers no longer require (eye) movement, and reach impressive accuracy based on covert attention alone (Acqualagna & Blankertz, 2013;Treder, Schmidt, & Blankertz, 2011; reviewed in Riccio, Mattia, Simione, Olivetti, & Cincotti, 2012). For example, a recent system that uses sequentially presented stimuli reached 97.1% selection accuracy with 1.35 characters per minute (Treder et al, 2011) .…”

mentioning

confidence: 99%

“…However, modern P300 spellers no longer require (eye) movement, and reach impressive accuracy based on covert attention alone (Acqualagna & Blankertz, 2013;Treder, Schmidt, & Blankertz, 2011; reviewed in Riccio, Mattia, Simione, Olivetti, & Cincotti, 2012). For example, a recent system that uses sequentially presented stimuli reached 97.1% selection accuracy with 1.35 characters per minute (Treder et al, 2011) .Expressed as information-transfer rate (ITR), which is a common measure for evaluating BCI performance (Yuan et al, 2013), this corresponds to 6.18 bits/min. However, P300 spellers have several practical disadvantages.…”

mentioning

confidence: 99%

See 1 more Smart Citation

The mind-writing pupil: A human-computer interface based on decoding of covert attention through pupillometry

Mathôt

Melmi

Linden

et al. 2015

Preprint

View full text Add to dashboard Cite

We present a new human-computer interface that is based on decoding of attention through pupillometry. Our method builds on the recent finding that covert visual attention affects the pupillary light response: Your pupil constricts when you covertly (without looking at it) attend to a bright, compared to a dark, stimulus. In our method, participants covertly attend to one of several letters with oscillating brightness. Pupil size reflects the brightness of the selected letter, which allows us-with high accuracy and in real time-to determine which letter the participant intends to select. The performance of our method is comparable to the best covert-attention brain-computer interfaces to date, and has several advantages: no movement other than pupil-size change is required; no physical contact is required (i.e. no electrodes); it is easy to use; and it is reliable. Potential applications include: communication with totally locked-in patients, training of sustained attention, and ultra-secure password input. : human-computer interface, brain-computer interface, pupillometry, covert visual attention Manuscript in preparation [v1.1.4; Wed Sep 9 13:22:41 2015; There are many types of BCIs (reviewed in Donoghue, 2008;Nicolas-Alonso & Gomez-Gil, 2012) , which differ in the neural signal that they use (e.g., neural spikes or electroencephalography [EEG]), the way that neural activity is processed (e.g., through a classifier or by measuring overall activity in specific brain areas), and the actions that they perform (e.g. controlling a robotic limb, or writing text). Here we present a new method, which uses pupil size, rather than brain activity, as the controlling signal. Our method is related to two existing methods: the P300 speller (Farwell & Donchin, 1988), which is functionally similar to our method but relies on a different controlling signal; and a recent pupillometry-based method (Stoll et al., 2013) , which is functionally different from our method but relies on the same controlling signal. P300 spellers are among the most successful BCIs (reviewed in Fazel-Rezai et al., 2012) . They exploit the fact that rare visual stimuli elicit positive deflections in the EEG signal about 300 ms after their appearance. This event-related-potential (ERP) component is called the P300, and is largest for stimuli that are overtly (while looking at them) or covertly (without looking at them) attended (e.g., Treder & Blankertz, 2010). In a classic P300 speller, the participant sees a grid of letters. One letter, or sometimes one full column or row of letters, is highlighted at a time. A P300 is elicited each time that a letter is highlighted. The participant selects a letter by attending to it, usually by looking at it directly (i.e. overt attention), which leads to an increased P300 when that letter is highlighted. In its simplest form, the letter that, when highlighted, elicits the highest P300 is selected; however, most P300 spellers now use sophisticated classification techniques, and pool information from mult...

show abstract

Gaze-independent brain–computer interfaces based on covert attention and feature attention

Cited by 166 publications

References 57 publications

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Brain–Computer Interfaces for Detection and Localization of Targets in Aerial Images

Performance optimization of ERP-based BCIs using dynamic stopping

The mind-writing pupil: A human-computer interface based on decoding of covert attention through pupillometry

Contact Info

Product

Resources

About