Optimizing the stimulus presentation paradigm design for the P300-based brain-computer interface using performance prediction

A P300 Brain-Computer Interface With a Reduced Visual Field

A P300 brain-computer interface (BCI) is a paradigm, where text characters are decoded from event-related potentials (ERPs). In a popular implementation, called P300 speller, a subject looks at a display where characters are flashing and selects one character by attending to it. The selection is recognized as the item with the strongest ERP. The speller performs well when cortical responses to target and non-target stimuli are sufficiently different. Although many strategies have been proposed for improving the BCI spelling, a relatively simple one received insufficient attention in the literature: reduction of the visual field to diminish the contribution from non-target stimuli. Previously, this idea was implemented in a single-stimulus switch that issued an urgent command like stopping a robot. To tackle this approach further, we ran a pilot experiment where ten subjects operated a traditional P300 speller or wore a binocular aperture that confined their sight to the central visual field. As intended, visual field restriction resulted in a replacement of non-target ERPs with EEG rhythms asynchronous to stimulus periodicity. Changes in target ERPs were found in half of the subjects and were individually variable. While classification accuracy was slightly better for the aperture condition (84.3 ± 2.9%, mean ± standard error) than the no-aperture condition (81.0 ± 2.6%), this difference was not statistically significant for the entire sample of subjects (N = 10). For both the aperture and no-aperture conditions, classification accuracy improved over 4 days of training, more so for the aperture condition (from 72.0 ± 6.3% to 87.0 ± 3.9% and from 72.0 ± 5.6% to 97.0 ± 2.2% for the no-aperture and aperture conditions, respectively). Although in this study BCI performance was not substantially altered, we suggest that with further refinement this approach could speed up BCI operations and reduce user fatigue. Additionally, instead of wearing an aperture, non-targets could be removed algorithmically or with a hybrid interface that utilizes an eye tracker. We further discuss how a P300 speller could be improved by taking advantage of the different physiological properties of the central and peripheral vision. Finally, we suggest that the proposed experimental approach could be used in basic research on the mechanisms of visual processing.

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

OBJECTIVE

Going adaptive is a major challenge for the field of brain-computer interface (BCI). This entails a machine that optimally articulates inference about the user's intentions and its own actions. Adaptation can operate over several dimensions which calls for a generic and flexible framework.

APPROACH

We appeal to one of the most comprehensive computational approach to brain (adaptive) functions: the active inference (AI) framework. It entails an explicit (probabilistic) model of the user that the machine interacts with, here involved in a P300-spelling task. This takes the form of a discrete input-output state-space model establishing the link between the machine's (i) observations-a P300 or error potential for instance, (ii) representations-of the user intentions to spell or pause, and (iii) actions-to flash, spell or switch-off the application.

MAIN RESULTS

Using simulations with real EEG data from 18 subjects, results demonstrate the ability of AI to yield a significant increase in bit rate (17%) over state-of-the-art approaches, such as dynamic stopping.

SIGNIFICANCE

Thanks to its flexibility, this one model enables to implement optimal (dynamic) stopping but also optimal flashing (i.e. active sampling), automated error correction, and switching off when the user does not look at the screen anymore. Importantly, this approach enables the machine to flexibly arbitrate between all these possible actions. We demonstrate AI as a unifying and generic framework to implement a flexible interaction behaviour in a given BCI context.

P300 Speller Performance Predictor Based on RSVP Multi-feature

Brain-computer interface (BCI) systems were developed so that people can control computers or machines through their brain activity without moving their limbs. The P300 speller is one of the BCI applications used most commonly, as is very simple and reliable and can achieve satisfactory performance. However, like other BCIs, the P300 speller still has room for improvements in terms of its practical use, for example, selecting the best compromise between spelling accuracy and information transfer rate (ITR; speed) so that the P300 speller can maintain high accuracy while increasing spelling speed. Therefore, seeking correlates of, and predicting, the P300 speller's performance is necessary to understand and improve the technique. In this work, we investigated the correlations between rapid serial visual presentation (RSVP) task features and the P300 speller's performance. Fifty-five subjects participated in the RSVP and conventional matrix P300 speller tasks and RSVP behavioral and electroencephalography (EEG) features were compared in the P300's speller performance. We found that several of the RSVP's event-related potential (ERP) and behavioral features were correlated with the P300 speller's offline binary classification accuracy. Using these features, we propose a simple multi-feature performance predictor (r = 0.53, p = 0.0001) that outperforms any single feature performance predictor, including that of the conventional RSVP T1% predictor (r = 0.28, p = 0.06). This result demonstrates that selective multi-features can predict BCI performance better than a single feature alone.