Exploiting error-related potentials in cognitive task based BCI

Error-Related Potentials in Reinforcement Learning-Based Brain-Machine Interfaces

The human brain has been an object of extensive investigation in different fields. While several studies have focused on understanding the neural correlates of error processing, advances in brain-machine interface systems using non-invasive techniques further enabled the use of the measured signals in different applications. The possibility of detecting these error-related potentials (ErrPs) under different experimental setups on a single-trial basis has further increased interest in their integration in closed-loop settings to improve system performance, for example, by performing error correction. Fewer works have, however, aimed at reducing future mistakes or learning. We present a review focused on the current literature using non-invasive systems that have combined the ErrPs information specifically in a reinforcement learning framework to go beyond error correction and have used these signals for learning.

Deep-learning online EEG decoding brain-computer interface using error-related potentials recorded with a consumer-grade headset

Objective:Brain-computer interfaces (BCIs) allow subjects with sensorimotor disability to interact with the environment. Non-invasive BCIs relying on EEG signals such as event-related potentials (ERPs) have been established as a reliable compromise between spatio-temporal resolution and patient impact, but limitations due to portability and versatility preclude their broad application. Here we describe a deep-learning augmented error-related potential (ErrP) discriminating BCI using a consumer-grade portable headset EEG, the Emotiv EPOC+.Approach:We recorded and discriminated ErrPs offline and online from 14 subjects during a visual feedback task.Main results:We achieved online discrimination accuracies of up to 81%, comparable to those obtained with professional 32/64-channel EEG devices via deep-learning using either a generative-adversarial network or an intrinsic-mode function augmentation of the training data and minimalistic computing resources.Significance:Our BCI model has the potential of expanding the spectrum of BCIs to more portable, artificial intelligence-enhanced, efficient interfaces accelerating the routine deployment of these devices outside the controlled environment of a scientific laboratory.

Theoretical Perspective on an Ideomotor Brain-Computer Interface: Toward a Naturalistic and Non-invasive Brain-Computer Interface Paradigm Based on Action-Effect Representation

Recent years have been marked by the fulgurant expansion of non-invasive Brain-Computer Interface (BCI) devices and applications in various contexts (medical, industrial etc.). This technology allows agents "to directly act with thoughts," bypassing the peripheral motor system. Interestingly, it is worth noting that typical non-invasive BCI paradigms remain distant from neuroscientific models of human voluntary action. Notably, bidirectional links between action and perception are constantly ignored in BCI experiments. In the current perspective article, we proposed an innovative BCI paradigm that is directly inspired by the ideomotor principle, which postulates that voluntary actions are driven by the anticipated representation of forthcoming perceptual effects. We believe that (1) adapting BCI paradigms could allow simple action-effect bindings and consequently action-effect predictions and (2) using neural underpinnings of those action-effect predictions as features of interest in AI methods, could lead to more accurate and naturalistic BCI-mediated actions.

Detection of Error-Related Potentials in Stroke Patients from EEG Using an Artificial Neural Network

Error-related potentials (ErrPs) have been proposed as a means for improving brain-computer interface (BCI) performance by either correcting an incorrect action performed by the BCI or label data for continuous adaptation of the BCI to improve the performance. The latter approach could be relevant within stroke rehabilitation where BCI calibration time could be minimized by using a generalized classifier that is continuously being individualized throughout the rehabilitation session. This may be achieved if data are correctly labelled. Therefore, the aims of this study were: (1) classify single-trial ErrPs produced by individuals with stroke, (2) investigate test-retest reliability, and (3) compare different classifier calibration schemes with different classification methods (artificial neural network, ANN, and linear discriminant analysis, LDA) with waveform features as input for meaningful physiological interpretability. Twenty-five individuals with stroke operated a sham BCI on two separate days where they attempted to perform a movement after which they received feedback (error/correct) while continuous EEG was recorded. The EEG was divided into epochs: ErrPs and NonErrPs. The epochs were classified with a multi-layer perceptron ANN based on temporal features or the entire epoch. Additionally, the features were classified with shrinkage LDA. The features were waveforms of the ErrPs and NonErrPs from the sensorimotor cortex to improve the explainability and interpretation of the output of the classifiers. Three calibration schemes were tested: within-day, between-day, and across-participant. Using within-day calibration, 90% of the data were correctly classified with the entire epoch as input to the ANN; it decreased to 86% and 69% when using temporal features as input to ANN and LDA, respectively. There was poor test-retest reliability between the two days, and the other calibration schemes led to accuracies in the range of 63-72% with LDA performing the best. There was no association between the individuals' impairment level and classification accuracies. The results show that ErrPs can be classified in individuals with stroke, but that user- and session-specific calibration is needed for optimal ErrP decoding with this approach. The use of ErrP/NonErrP waveform features makes it possible to have a physiological meaningful interpretation of the output of the classifiers. The results may have implications for labelling data continuously in BCIs for stroke rehabilitation and thus potentially improve the BCI performance.

The value-complexity trade-off for reinforcement learning based brain-computer interfaces

OBJECTIVE

One of the recent developments in the field of brain-computer interfaces (BCI) is the reinforcement learning (RL) based BCI paradigm, which uses neural error responses as the reward feedback on the agent's action. While having several advantages over motor imagery based BCI, the reliability of RL-BCI is critically dependent on the decoding accuracy of noisy neural error signals. A principled method is needed to optimally handle this inherent noise under general conditions.

APPROACH

By determining a trade-off between the expected value and the informational cost of policies, the info-RL (IRL) algorithm provides optimal low-complexity policies, which are robust under noisy reward conditions and achieve the maximal obtainable value. In this work we utilize the IRL algorithm to characterize the maximal obtainable value under different noise levels, which in turn is used to extract the optimal robust policy for each noise level.

MAIN RESULTS

Our simulation results of a setting with Gaussian noise show that the complexity level of the optimal policy is dependent on the reward magnitude but not on the reward variance, whereas the variance determines whether a lower complexity solution is favorable or not. We show how this analysis can be utilized to select optimal robust policies for an RL-BCI and demonstrate its use on EEG data.

SIGNIFICANCE

We propose here a principled method to determine the optimal policy complexity of an RL problem with a noisy reward, which we argue is particularly useful for RL-based BCI paradigms. This framework may be used to minimize initial training time and allow for a more dynamic and robust shared control between the agent and the operator under different conditions.

The Effect of Static and Dynamic Visual Stimulations on Error Detection Based on Error-Evoked Brain Responses

Error-related potentials (ErrPs) have provided technical support for the brain-computer interface. However, different visual stimulations may affect the ErrPs, and furthermore, affect the error recognition based on ErrPs. Therefore, the study aimed to investigate how people respond to different visual stimulations (static and dynamic) and find the best time window for different stimulation. Nineteen participants were recruited in the ErrPs-based tasks with static and dynamic visual stimulations. Five ErrPs were statistically compared, and the classification accuracies were obtained through linear discriminant analysis (LDA) with nine different time windows. The results showed that the P3, N6, and P8 with correctness were significantly different from those with error in both stimulations, while N1 only existed in static. The differences between dynamic and static errors existed in N1 and P2. The highest accuracy was obtained in the time window related to N1, P3, N6, and P8 for the static condition, and in the time window related to P3, N6, and P8 for the dynamic. In conclusion, the early components of ErrPs may be affected by stimulation modes, and the late components are more sensitive to errors. The error recognition with static stimulation requires information from the entire epoch, while the late windows should be focused more within the dynamic case.

Development of a robust asynchronous brain-switch using ErrP-based error correction

OBJECTIVE

The ultimate goal of many brain-computer interface (BCI) research efforts is to provide individuals with severe motor impairments with a communication channel that they can control at will. To achieve this goal, an important system requirement is asynchronous control, whereby users can initiate intentional brain activation in a self-paced rather than system-cued manner. However, to date, asynchronous BCIs have been explored in a minority of BCI studies and their performance is generally below that of system-paced alternatives. In this paper, we present an asynchronous electroencephalography (EEG) BCI that detects a non-motor imagery cognitive task and investigated the possibility of improving its performance using error-related potentials (ErrP).

APPROACH

Ten able-bodied adults attended two sessions of data collection each, one for training and one for testing the BCI. The visual interface consisted of a centrally located cartoon icon. For each participant, an asynchronous BCI differentiated among the idle state and a personally selected cognitive task (mental arithmetic, word generation or figure rotation). The BCI continuously analyzed the EEG data stream and displayed real-time feedback (i.e. icon fell over) upon detection of brain activity indicative of a cognitive task. The BCI also monitored the EEG signals for the presence of error-related potentials following the presentation of feedback. An ErrP classifier was invoked to automatically alter the task classifier outcome when an error-related potential was detected.

MAIN RESULTS

The average post-error correction trial success rate across participants, 85% [Formula: see text] 12%, was significantly higher (p   <  0.05) than that pre-error correction (78% [Formula: see text] 11%).

SIGNIFICANCE

Our findings support the addition of ErrP-correction to maximize the performance of asynchronous BCIs..

An Event-Driven AR-Process Model for EEG-Based BCIs With Rapid Trial Sequences

Electroencephalography (EEG) is an effective non-invasive measurement method to infer user intent in brain-computer interface (BCI) systems for control and communication, however, these systems often lack sufficient accuracy and speed due to low separability of class-conditional EEG feature distributions. Many factors impact system performance, including inadequate training datasets and models' ignorance of the temporal dependency of brain responses to serial stimuli. Here, we propose a signal model for event-related responses in the EEG evoked with a rapid sequence of stimuli in BCI applications. The model describes the EEG as a superposition of impulse responses time-locked to stimuli corrupted with an autoregressive noise process. The performance of the signal model is assessed in the context of RSVP keyboard, a language-model-assisted EEG-based BCI for typing. EEG data obtained for model calibration from 10 healthy participants are used to fit and compare two models: the proposed sequence-based EEG model and the trial-based feature-class-conditional distribution model that ignores temporal dependencies, which has been used in the previous work. The simulation studies indicate that the earlier model that ignores temporal dependencies may be causing drastic reductions in achievable information transfer rate (ITR). Furthermore, the proposed model, with better regularization, may achieve improved accuracy with fewer calibration data samples, potentially helping to reduce calibration time. Specifically, results show an average 8.6% increase in (cross-validated) calibration AUC for a single channel of EEG, and 54% increase in the ITR in a typing task.