Response error correction--a demonstration of improved human-machine performance using real-time EEG monitoring

Single-channel electroencephalography decomposition by detector-atom network and its pre-trained model

Signal decomposition techniques utilizing multi-channel spatial features are critical for analyzing, denoising, and classifying electroencephalography (EEG) signals. To facilitate the decomposition of signals recorded with limited channels, this paper presents a novel single-channel decomposition approach that does not rely on multi-channel features. Our model posits that an EEG signal comprises short, shift-invariant waves, referred to as atoms. We design a decomposer as an artificial neural network aimed at estimating these atoms and detecting their time shifts and amplitude modulations within the input signal. The efficacy of our method was validated across various scenarios in brain-computer interfaces and neuroscience, demonstrating enhanced performance. Additionally, cross-dataset validation indicates the feasibility of a pre-trained model, enabling a plug-and-play signal decomposition module.

Post-stimulus encoding of decision confidence in EEG: toward a brain-computer interface for decision making

Objective.When making decisions, humans can evaluate how likely they are to be correct. If this subjective confidence could be reliably decoded from brain activity, it would be possible to build a brain-computer interface (BCI) that improves decision performance by automatically providing more information to the user if needed based on their confidence. But this possibility depends on whether confidence can be decoded right after stimulus presentation and before the response so that a corrective action can be taken in time. Although prior work has shown that decision confidence is represented in brain signals, it is unclear if the representation is stimulus-locked or response-locked, and whether stimulus-locked pre-response decoding is sufficiently accurate for enabling such a BCI.Approach.We investigate the neural correlates of confidence by collecting high-density electroencephalography (EEG) during a perceptual decision task with realistic stimuli. Importantly, we design our task to include a post-stimulus gap that prevents the confounding of stimulus-locked activity by response-locked activity and vice versa, and then compare with a task without this gap.Main results.We perform event-related potential and source-localization analyses. Our analyses suggest that the neural correlates of confidence are stimulus-locked, and that an absence of a post-stimulus gap could cause these correlates to incorrectly appear as response-locked. By preventing response-locked activity from confounding stimulus-locked activity, we then show that confidence can be reliably decoded from single-trial stimulus-locked pre-response EEG alone. We also identify a high-performance classification algorithm by comparing a battery of algorithms. Lastly, we design a simulated BCI framework to show that the EEG classification is accurate enough to build a BCI and that the decoded confidence could be used to improve decision making performance particularly when the task difficulty and cost of errors are high.Significance.Our results show feasibility of non-invasive EEG-based BCIs to improve human decision making.

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.

Single-Trial Classification of Error-Related Potentials in People with Motor Disabilities: A Study in Cerebral Palsy, Stroke, and Amputees

Brain-computer interface performance may be reduced over time, but adapting the classifier could reduce this problem. Error-related potentials (ErrPs) could label data for continuous adaptation. However, this has scarcely been investigated in populations with severe motor impairments. The aim of this study was to detect ErrPs from single-trial EEG in offline analysis in participants with cerebral palsy, an amputation, or stroke, and determine how much discriminative information different brain regions hold. Ten participants with cerebral palsy, eight with an amputation, and 25 with a stroke attempted to perform 300-400 wrist and ankle movements while a sham BCI provided feedback on their performance for eliciting ErrPs. Pre-processed EEG epochs were inputted in a multi-layer perceptron artificial neural network. Each brain region was used as input individually (Frontal, Central, Temporal Right, Temporal Left, Parietal, and Occipital), the combination of the Central region with each of the adjacent regions, and all regions combined. The Frontal and Central regions were most important, and adding additional regions only improved performance slightly. The average classification accuracies were 84 ± 4%, 87± 4%, and 85 ± 3% for cerebral palsy, amputation, and stroke participants. In conclusion, ErrPs can be detected in participants with motor impairments; this may have implications for developing adaptive BCIs or automatic error correction.

Classification of erroneous actions using EEG frequency features: implications for BCI performance. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021;2021:629-632. [PMID: 34891372 DOI: 10.1109/embc46164.2021.9630509] [Citation(s) in RCA: 0] [Impact Index Per Article: 0]

Several studies have demonstrated that error-related neuronal signatures can be successfully detected and used to improve the performance of brain-computer interfaces. However, this has been tested mainly in well-controlled environments and based on temporal features, such as the amplitude of event-related potentials. In this study, we propose a classification algorithm combining frequency features and a weighted SVM to detect the neuronal signatures of errors committed in a complex saccadic go/no-go task. We follow the hypothesis that frequency features yield better discrimination performance in complex tasks, generalize better, and require fewer pre-processing steps. When combining temporal and frequency features, we achieved a balanced classification accuracy of 75% - almost the same as using only frequency features. On the other hand, when using only temporal features, the balanced accuracy decreased to 66%. These findings show that subjects' performance can be automatically detected based on frequency features of error-related neuronal signatures. Additionally, our results revealed that features computed in the pre-response time contribute to the discrimination between correct and erroneous responses, which suggests the existence of error-related patterns even before response execution.

Towards the Classification of Error-Related Potentials using Riemannian Geometry

The error-related potential (ErrP) is an event-related potential (ERP) evoked by an experimental participant's recognition of an error during task performance. ErrPs, originally described by cognitive psychologists, have been adopted for use in brain-computer interfaces (BCIs) for the detection and correction of errors, and the online refinement of decoding algorithms. Riemannian geometry-based feature extraction and classification is a new approach to BCI which shows good performance in a range of experimental paradigms, but has yet to be applied to the classification of ErrPs. Here, we describe an experiment that elicited ErrPs in seven normal participants performing a visual discrimination task. Audio feedback was provided on each trial. We used multi-channel electroencephalogram (EEG) recordings to classify ErrPs (success/failure), comparing a Riemannian geometry-based method to a traditional approach that computes time-point features. Overall, the Riemannian approach outperformed the traditional approach (78.2% versus 75.9% accuracy, p <0.05); this difference was statistically significant (p <0.05) in three of seven participants. These results indicate that the Riemannian approach better captured the features from feedback-elicited ErrPs, and may have application in BCI for error detection and correction.

Online asynchronous detection of error-related potentials in participants with a spinal cord injury using a generic classifier

For brain-computer interface (BCI) users, the awareness of an error is associated with a cortical signature known as an error-related potential (ErrP). The incorporation of ErrP detection into BCIs can improve their performance.

OBJECTIVE

This work has three main aims. First, we investigate whether an ErrP classifier is transferable from able-bodied participants to participants with a spinal cord injury (SCI). Second, we test this generic ErrP classifier with SCI and control participants, in an online experiment without offline calibration. Third, we investigate the morphology of ErrPs in both groups of participants.

APPROACH

We used previously recorded electroencephalographic data from able-bodied participants to train an ErrP classifier. We tested the classifier asynchronously, in an online experiment with 16 new participants: 8 participants with SCI and 8 able-bodied control participants. The experiment had no offline calibration and participants received feedback regarding the ErrP detections from the start. To increase the fluidity of the experiment, feedback regarding false positive ErrP detections was not presented to the participants, but these detections were taken into account in the evaluation of the classifier. The generic classifier was not trained with the user's brain signals. However, its performance was optimized during the online experiment by the use of personalized decision thresholds. The classifier's performance was evaluated using trial-based metrics, which considered the asynchronous detection of ErrPs during the entire trial's duration.

MAIN RESULTS

Participants with SCI presented a non-homogenous ErrP morphology, and four of them did not present clear ErrP signals. The generic classifier performed better than chance in participants with clear ErrP signals, independently of the SCI (11 out of 16 participants). Three out of the five participants that obtained chance level results with the generic classifier would have not benefitted from the use of a personalized classifier.

SIGNIFICANCE

This work shows the feasibility of transferring an ErrP classifier from able-bodied participants to participants with SCI, for asynchronous detection of ErrPs in an online experiment without offline calibration, which provided immediate feedback to the users.

Errors in Human-Robot Interactions and Their Effects on Robot Learning

During human-robot interaction, errors will occur. Hence, understanding the effects of interaction errors and especially the effect of prior knowledge on robot learning performance is relevant to develop appropriate approaches for learning under natural interaction conditions, since future robots will continue to learn based on what they have already learned. In this study, we investigated interaction errors that occurred under two learning conditions, i.e., in the case that the robot learned without prior knowledge (cold-start learning) and in the case that the robot had prior knowledge (warm-start learning). In our human-robot interaction scenario, the robot learns to assign the correct action to a current human intention (gesture). Gestures were not predefined but the robot had to learn their meaning. We used a contextual-bandit approach to maximize the expected payoff by updating (a) the current human intention (gesture) and (b) the current human intrinsic feedback after each action selection of the robot. As an intrinsic evaluation of the robot behavior we used the error-related potential (ErrP) in the human electroencephalogram as reinforcement signal. Either gesture errors (human intentions) can be misinterpreted by incorrectly captured gestures or errors in the ErrP classification (human feedback) can occur. We investigated these two types of interaction errors and their effects on the learning process. Our results show that learning and its online adaptation was successful under both learning conditions (except for one subject in cold-start learning). Furthermore, warm-start learning achieved faster convergence, while cold-start learning was less affected by online changes in the current context.

Hybrid brain-computer interface with motor imagery and error-related brain activity

OBJECTIVE

Brain-computer interface (BCI) systems read and interpret brain activity directly from the brain. They can provide a means of communication or locomotion for patients suffering from neurodegenerative diseases or stroke. However, non-stationarity of brain activity limits the reliable transfer of the algorithms that were trained during a calibration session to real-time BCI control. One source of non-stationarity is the user's brain response to the BCI output (feedback), for instance, whether the BCI feedback is perceived as an error by the user or not. By taking such sources of non-stationarity into account, the reliability of the BCI can be improved.

APPROACH

In this work, we demonstrate a real-time implementation of a hybrid motor imagery BCI combining the information from the motor imagery signal and the error-related brain activity simultaneously so as to gain benefit from both sources.

MAIN RESULTS

We show significantly improved performance in real-time BCI control across 12 participants, compared to a conventional motor imagery BCI. The significant improvement is in terms of classification accuracy, target hit rate, subjective perception of control and information-transfer rate. Moreover, our offline analyses of the recorded EEG data show that the error-related brain activity provides a more reliable source of information than the motor imagery signal.

SIGNIFICANCE

This work shows, for the first time, that the error-related brain activity classifier compared to the motor imagery classifier is more consistent when trained on calibration data and tested during online control. This likely explains why the proposed hybrid BCI allows for a more reliable means of communication or rehabilitation for patients in need.

Classification of error-related potentials from single-trial EEG in association with executed and imagined movements: a feature and classifier investigation

Error-related potentials (ErrPs) have been proposed for designing adaptive brain-computer interfaces (BCIs). Therefore, ErrPs must be decoded. The aim of this study was to evaluate ErrP decoding using combinations of different feature types and classifiers in BCI paradigms involving motor execution (ME) and imagination (MI). Fifteen healthy subjects performed 510 (ME) and 390 (MI) trials of right/left wrist extensions and foot dorsiflexions. Sham BCI feedback was delivered with an accuracy of 80% (ME) and 70% (MI). Continuous EEG was recorded and divided into ErrP and NonErrP epochs. Temporal, spectral, and discrete wavelet transform (DWT) marginals and template matching features were extracted, and all combinations of feature types were classified using linear discriminant analysis, support vector machine, and random forest classifiers. ErrPs were elicited for both ME and MI paradigms, and the average classification accuracies were significantly higher than the chance level. The highest average classification accuracy was obtained using temporal features and a combination of temporal + DWT features classified with random forest; 89 ± 9% and 83 ± 9% for ME and MI, respectively. These results generally indicate that temporal features should be used when detecting ErrPs, but there is great inter-subject variability, which means that user-specific features should be derived to maximize the performance. Graphical abstract.

Perturbation-evoked potentials can be classified from single-trial EEG

OBJECTIVE

Loss of balance control can have serious consequences on interaction between humans and machines as well as the general well-being of humans. Perceived balance perturbations are always accompanied by a specific cortical activation, the so-called perturbation-evoked potential (PEP). In this study, we investigate the possibility to classify PEPs from ongoing EEG.

APPROACH

Fifteen healthy subjects were exposed to seated whole-body perturbations. Each participant performed 120 trials; they were rapidly tilted to the right and left, 60 times respectively.

MAIN RESULTS

We achieved classification accuracies of more than 85% between PEPs and rest EEG using a window-based classification approach. Different window lengths and electrode layouts were compared. We were able to achieve excellent classification performance (87.6 ± 8.0% accuracy) by using a short window length of 200 ms and a minimal electrode layout consisting of only the Cz electrode. The peak classification accuracy coincides in time with the strongest component of PEPs, called N1.

SIGNIFICANCE

We showed that PEPs can be discriminated against ongoing EEG with high accuracy. These findings can contribute to the development of a system that can detect balance perturbations online.

Neurotechnologies for Human Cognitive Augmentation: Current State of the Art and Future Prospects

Recent advances in neuroscience have paved the way to innovative applications that cognitively augment and enhance humans in a variety of contexts. This paper aims at providing a snapshot of the current state of the art and a motivated forecast of the most likely developments in the next two decades. Firstly, we survey the main neuroscience technologies for both observing and influencing brain activity, which are necessary ingredients for human cognitive augmentation. We also compare and contrast such technologies, as their individual characteristics (e.g., spatio-temporal resolution, invasiveness, portability, energy requirements, and cost) influence their current and future role in human cognitive augmentation. Secondly, we chart the state of the art on neurotechnologies for human cognitive augmentation, keeping an eye both on the applications that already exist and those that are emerging or are likely to emerge in the next two decades. Particularly, we consider applications in the areas of communication, cognitive enhancement, memory, attention monitoring/enhancement, situation awareness and complex problem solving, and we look at what fraction of the population might benefit from such technologies and at the demands they impose in terms of user training. Thirdly, we briefly review the ethical issues associated with current neuroscience technologies. These are important because they may differentially influence both present and future research on (and adoption of) neurotechnologies for human cognitive augmentation: an inferior technology with no significant ethical issues may thrive while a superior technology causing widespread ethical concerns may end up being outlawed. Finally, based on the lessons learned in our analysis, using past trends and considering other related forecasts, we attempt to forecast the most likely future developments of neuroscience technology for human cognitive augmentation and provide informed recommendations for promising future research and exploitation avenues.

Masked and unmasked error-related potentials during continuous control and feedback

The detection of error-related potentials (ErrPs) in tasks with discrete feedback is well established in the brain-computer interface (BCI) field. However, the decoding of ErrPs in tasks with continuous feedback is still in its early stages.

OBJECTIVE

We developed a task in which subjects have continuous control of a cursor's position by means of a joystick. The cursor's position was shown to the participants in two different modalities of continuous feedback: normal and jittered. The jittered feedback was created to mimic the instability that could exist if participants controlled the trajectory directly with brain signals.

APPROACH

This paper studies the electroencephalographic (EEG)-measurable signatures caused by a loss of control over the cursor's trajectory, causing a target miss.

MAIN RESULTS

In both feedback modalities, time-locked potentials revealed the typical frontal-central components of error-related potentials. Errors occurring during the jittered feedback (masked errors) were delayed in comparison to errors occurring during normal feedback (unmasked errors). Masked errors displayed lower peak amplitudes than unmasked errors. Time-locked classification analysis allowed a good distinction between correct and error classes (average Cohen-[Formula: see text], average TPR  =  81.8% and average TNR  =  96.4%). Time-locked classification analysis between masked error and unmasked error classes revealed results at chance level (average Cohen-[Formula: see text], average TPR  =  60.9% and average TNR  =  58.3%). Afterwards, we performed asynchronous detection of ErrPs, combining both masked and unmasked trials. The asynchronous detection of ErrPs in a simulated online scenario resulted in an average TNR of 84.0% and in an average TPR of 64.9%.

SIGNIFICANCE

The time-locked classification results suggest that the masked and unmasked errors were indistinguishable in terms of classification. The asynchronous classification results suggest that the feedback modality did not hinder the asynchronous detection of ErrPs.

Intrinsic interactive reinforcement learning - Using error-related potentials for real world human-robot interaction

Reinforcement learning (RL) enables robots to learn its optimal behavioral strategy in dynamic environments based on feedback. Explicit human feedback during robot RL is advantageous, since an explicit reward function can be easily adapted. However, it is very demanding and tiresome for a human to continuously and explicitly generate feedback. Therefore, the development of implicit approaches is of high relevance. In this paper, we used an error-related potential (ErrP), an event-related activity in the human electroencephalogram (EEG), as an intrinsically generated implicit feedback (rewards) for RL. Initially we validated our approach with seven subjects in a simulated robot learning scenario. ErrPs were detected online in single trial with a balanced accuracy (bACC) of 91%, which was sufficient to learn to recognize gestures and the correct mapping between human gestures and robot actions in parallel. Finally, we validated our approach in a real robot scenario, in which seven subjects freely chose gestures and the real robot correctly learned the mapping between gestures and actions (ErrP detection (90% bACC)). In this paper, we demonstrated that intrinsically generated EEG-based human feedback in RL can successfully be used to implicitly improve gesture-based robot control during human-robot interaction. We call our approach intrinsic interactive RL.

Enhancement of Group Perception via a Collaborative Brain-Computer Interface

OBJECTIVE

We aimed at improving group performance in a challenging visual search task via a hybrid collaborative brain-computer interface (cBCI).

METHODS

Ten participants individually undertook a visual search task where a display was presented for 250 ms, and they had to decide whether a target was present or not. Local temporal correlation common spatial pattern (LTCCSP) was used to extract neural features from response- and stimulus-locked EEG epochs. The resulting feature vectors were extended by including response times and features extracted from eye movements. A classifier was trained to estimate the confidence of each group member. cBCI-assisted group decisions were then obtained using a confidence-weighted majority vote.

RESULTS

Participants were combined in groups of different sizes to assess the performance of the cBCI. Results show that LTCCSP neural features, response times, and eye movement features significantly improve the accuracy of the cBCI over what we achieved with previous systems. For most group sizes, our hybrid cBCI yields group decisions that are significantly better than majority-based group decisions.

CONCLUSION

The visual task considered here was much harder than a task we used in previous research. However, thanks to a range of technological enhancements, our cBCI has delivered a significant improvement over group decisions made by a standard majority vote.

SIGNIFICANCE

With previous cBCIs, groups may perform better than single non-BCI users. Here, cBCI-assisted groups are more accurate than identically sized non-BCI groups. This paves the way to a variety of real-world applications of cBCIs where reducing decision errors is vital.

Spectral Entropy Can Predict Changes of Working Memory Performance Reduced by Short-Time Training in the Delayed-Match-to-Sample Task

Spectral entropy, which was generated by applying the Shannon entropy concept to the power distribution of the Fourier-transformed electroencephalograph (EEG), was utilized to measure the uniformity of power spectral density underlying EEG when subjects performed the working memory tasks twice, i.e., before and after training. According to Signed Residual Time (SRT) scores based on response speed and accuracy trade-off, 20 subjects were divided into two groups, namely high-performance and low-performance groups, to undertake working memory (WM) tasks. We found that spectral entropy derived from the retention period of WM on channel FC4 exhibited a high correlation with SRT scores. To this end, spectral entropy was used in support vector machine classifier with linear kernel to differentiate these two groups. Receiver operating characteristics analysis and leave-one out cross-validation (LOOCV) demonstrated that the averaged classification accuracy (CA) was 90.0 and 92.5% for intra-session and inter-session, respectively, indicating that spectral entropy could be used to distinguish these two different WM performance groups successfully. Furthermore, the support vector regression prediction model with radial basis function kernel and the root-mean-square error of prediction revealed that spectral entropy could be utilized to predict SRT scores on individual WM performance. After testing the changes in SRT scores and spectral entropy for each subject by short-time training, we found that 16 in 20 subjects’ SRT scores were clearly promoted after training and 15 in 20 subjects’ SRT scores showed consistent changes with spectral entropy before and after training. The findings revealed that spectral entropy could be a promising indicator to predict individual’s WM changes by training and further provide a novel application about WM for brain–computer interfaces.

Affective Aspects of Perceived Loss of Control and Potential Implications for Brain-Computer Interfaces

Most brain-computer interfaces (BCIs) focus on detecting single aspects of user states (e.g., motor imagery) in the electroencephalogram (EEG) in order to use these aspects as control input for external systems. This communication can be effective, but unaccounted mental processes can interfere with signals used for classification and thereby introduce changes in the signal properties which could potentially impede BCI classification performance. To improve BCI performance, we propose deploying an approach that potentially allows to describe different mental states that could influence BCI performance. To test this approach, we analyzed neural signatures of potential affective states in data collected in a paradigm where the complex user state of perceived loss of control (LOC) was induced. In this article, source localization methods were used to identify brain dynamics with source located outside but affecting the signal of interest originating from the primary motor areas, pointing to interfering processes in the brain during natural human-machine interaction. In particular, we found affective correlates which were related to perceived LOC. We conclude that additional context information about the ongoing user state might help to improve the applicability of BCIs to real-world scenarios.

A New Perspective for the Training Assessment: Machine Learning-Based Neurometric for Augmented User's Evaluation

Inappropriate training assessment might have either high social costs and economic impacts, especially in high risks categories, such as Pilots, Air Traffic Controllers, or Surgeons. One of the current limitations of the standard training assessment procedures is the lack of information about the amount of cognitive resources requested by the user for the correct execution of the proposed task. In fact, even if the task is accomplished achieving the maximum performance, by the standard training assessment methods, it would not be possible to gather and evaluate information about cognitive resources available for dealing with unexpected events or emergency conditions. Therefore, a metric based on the brain activity (neurometric) able to provide the Instructor such a kind of information should be very important. As a first step in this direction, the Electroencephalogram (EEG) and the performance of 10 participants were collected along a training period of 3 weeks, while learning the execution of a new task. Specific indexes have been estimated from the behavioral and EEG signal to objectively assess the users' training progress. Furthermore, we proposed a neurometric based on a machine learning algorithm to quantify the user's training level within each session by considering the level of task execution, and both the behavioral and cognitive stabilities between consecutive sessions. The results demonstrated that the proposed methodology and neurometric could quantify and track the users' progresses, and provide the Instructor information for a more objective evaluation and better tailoring of training programs.

EEG-based single-trial detection of errors from multiple error-related brain activity

A key ability of the human brain is to monitor erroneous events and adjust behaviors accordingly. Electrophysiological and neuroimaging studies have demonstrated different brain activities related to errors. Meanwhile, the recognition of error-related brain activity as one aspect of performance monitoring has been reported for potential applications in clinical neuroscience and brain-machine interface, where single-trial analysis and classification would provide novel insights on dynamic brain responses to errors. However, procedures of selecting features, as well as procedures of single-trial classification, are not fully investigated for optimal performance. In the present study, we investigated the performance of different configurations of feature extractions in both temporal and frequency domains, for discriminating response errors in a color-word matching Stroop task. Motivated by our previous investigations, we evaluated both temporal and frequency features with component signals, which were obtained from EEG signals via an independent component analysis (ICA). Five component signals (independent components, ICs), originated from the frontal, motor, parietal, and occipital areas, were included in detecting error-related brain activity from single-trial EEG data. The results showed that better performance can be achieved by optimizing time window and frequency range of selected features, sampling scheme of feature-related data, and training of classifiers. However, a simple combination of features from multiple component signals can only slightly improve the detection performance of errors in single-trial data as compared to the frontal IC only. More importantly, it is indicated that four ICs other than the frontal one also carry similar discriminative information about errors in both temporal and frequency domains. The fact suggests flexible means in detecting errors from EEG beyond the frontal brain areas, which might be very valuable in practical applications such that the frontal area is not accessible.

Designing a hands-on brain computer interface laboratory course

Devices and systems that interact with the brain have become a growing field of research and development in recent years. Engineering students are well positioned to contribute to both hardware development and signal analysis techniques in this field. However, this area has been left out of most engineering curricula. We developed an electroencephalography (EEG) based brain computer interface (BCI) laboratory course to educate students through hands-on experiments. The course is offered jointly by the Biomedical Engineering, Electrical Engineering, and Computer Science Departments of Columbia University in the City of New York and is open to senior undergraduate and graduate students. The course provides an effective introduction to the experimental design, neuroscience concepts, data analysis techniques, and technical skills required in the field of BCI.

The Brain Is Faster than the Hand in Split-Second Intentions to Respond to an Impending Hazard: A Simulation of Neuroadaptive Automation to Speed Recovery to Perturbation in Flight Attitude

The goal of this research is to test the potential for neuroadaptive automation to improve response speed to a hazardous event by using a brain-computer interface (BCI) to decode perceptual-motor intention. Seven participants underwent four experimental sessions while measuring brain activity with magnetoencephalograpy. The first three sessions were of a simple constrained task in which the participant was to pull back on the control stick to recover from a perturbation in attitude in one condition and to passively observe the perturbation in the other condition. The fourth session consisted of having to recover from a perturbation in attitude while piloting the plane through the Grand Canyon constantly maneuvering to track over the river below. Independent component analysis was used on the first two sessions to extract artifacts and find an event related component associated with the onset of the perturbation. These two sessions were used to train a decoder to classify trials in which the participant recovered from the perturbation (motor intention) vs. just passively viewing the perturbation. The BCI-decoder was tested on the third session of the same simple task and found to be able to significantly distinguish motor intention trials from passive viewing trials (mean = 69.8%). The same BCI-decoder was then used to test the fourth session on the complex task. The BCI-decoder significantly classified perturbation from no perturbation trials (73.3%) with a significant time savings of 72.3 ms (Original response time of 425.0-352.7 ms for BCI-decoder). The BCI-decoder model of the best subject was shown to generalize for both performance and time savings to the other subjects. The results of our off-line open loop simulation demonstrate that BCI based neuroadaptive automation has the potential to decode motor intention faster than manual control in response to a hazardous perturbation in flight attitude while ignoring ongoing motor and visual induced activity related to piloting the airplane.

Human scalp potentials reflect a mixture of decision-related signals during perceptual choices

Single-unit animal studies have consistently reported decision-related activity mirroring a process of temporal accumulation of sensory evidence to a fixed internal decision boundary. To date, our understanding of how response patterns seen in single-unit data manifest themselves at the macroscopic level of brain activity obtained from human neuroimaging data remains limited. Here, we use single-trial analysis of human electroencephalography data to show that population responses on the scalp can capture choice-predictive activity that builds up gradually over time with a rate proportional to the amount of sensory evidence, consistent with the properties of a drift-diffusion-like process as characterized by computational modeling. Interestingly, at time of choice, scalp potentials continue to appear parametrically modulated by the amount of sensory evidence rather than converging to a fixed decision boundary as predicted by our model. We show that trial-to-trial fluctuations in these response-locked signals exert independent leverage on behavior compared with the rate of evidence accumulation earlier in the trial. These results suggest that in addition to accumulator signals, population responses on the scalp reflect the influence of other decision-related signals that continue to covary with the amount of evidence at time of choice.

Integrating Behavior Modeling with Data Mining to Improve Human Error Prediction in Numerical Data Entry

Human errors in numerical data entry can lead to serious consequence but it is difficult to predict those errors because mechanisms of human errors vary and no contextual clues are available. This study suggests integrating human behavior modeling and data mining as an advanced method to predict human errors. Human behavior modeling utilized top-down inference to transform interactions between task characteristics and conditions into general inclination of an average operator to make errors, while data mining parsed psychophysiological measurements into individual’s likeliness of making errors on a trial-by-trial basis through bottom-up analysis. Specifically, an enhanced Queuing Network-Model Human Processor (QN-MHP) generated modeling features to be combined with real-time EEG features that were collected in a realistic numerical typing experiment, and potential errors were predicted by detecting error-associated features by linear discriminant analysis (LDA) classifiers before responses. The detection could be made as early as 300 milliseconds beforehand, and the results showed that integration improved the LDA classifiers’ performance by 31.7% in keenness ( d') and by 12.5 % in area under ROC curve (AUC) from that of using EEG only. The integration may help implement future adaptive augmented system to prevent cognitive breakdown by determining appropriate automation/augmentation levels.

Errare machinale est: the use of error-related potentials in brain-machine interfaces

The ability to recognize errors is crucial for efficient behavior. Numerous studies have identified electrophysiological correlates of error recognition in the human brain (error-related potentials, ErrPs). Consequently, it has been proposed to use these signals to improve human-computer interaction (HCI) or brain-machine interfacing (BMI). Here, we present a review of over a decade of developments toward this goal. This body of work provides consistent evidence that ErrPs can be successfully detected on a single-trial basis, and that they can be effectively used in both HCI and BMI applications. We first describe the ErrP phenomenon and follow up with an analysis of different strategies to increase the robustness of a system by incorporating single-trial ErrP recognition, either by correcting the machine's actions or by providing means for its error-based adaptation. These approaches can be applied both when the user employs traditional HCI input devices or in combination with another BMI channel. Finally, we discuss the current challenges that have to be overcome in order to fully integrate ErrPs into practical applications. This includes, in particular, the characterization of such signals during real(istic) applications, as well as the possibility of extracting richer information from them, going beyond the time-locked decoding that dominates current approaches.

On the applicability of brain reading for predictive human-machine interfaces in robotics

The ability of today's robots to autonomously support humans in their daily activities is still limited. To improve this, predictive human-machine interfaces (HMIs) can be applied to better support future interaction between human and machine. To infer upcoming context-based behavior relevant brain states of the human have to be detected. This is achieved by brain reading (BR), a passive approach for single trial EEG analysis that makes use of supervised machine learning (ML) methods. In this work we propose that BR is able to detect concrete states of the interacting human. To support this, we show that BR detects patterns in the electroencephalogram (EEG) that can be related to event-related activity in the EEG like the P300, which are indicators of concrete states or brain processes like target recognition processes. Further, we improve the robustness and applicability of BR in application-oriented scenarios by identifying and combining most relevant training data for single trial classification and by applying classifier transfer. We show that training and testing, i.e., application of the classifier, can be carried out on different classes, if the samples of both classes miss a relevant pattern. Classifier transfer is important for the usage of BR in application scenarios, where only small amounts of training examples are available. Finally, we demonstrate a dual BR application in an experimental setup that requires similar behavior as performed during the teleoperation of a robotic arm. Here, target recognition processes and movement preparation processes are detected simultaneously. In summary, our findings contribute to the development of robust and stable predictive HMIs that enable the simultaneous support of different interaction behaviors.

Detection of error related neuronal responses recorded by electrocorticography in humans during continuous movements

Background

Brain-machine interfaces (BMIs) can translate the neuronal activity underlying a user’s movement intention into movements of an artificial effector. In spite of continuous improvements, errors in movement decoding are still a major problem of current BMI systems. If the difference between the decoded and intended movements becomes noticeable, it may lead to an execution error. Outcome errors, where subjects fail to reach a certain movement goal, are also present during online BMI operation. Detecting such errors can be beneficial for BMI operation: (i) errors can be corrected online after being detected and (ii) adaptive BMI decoding algorithm can be updated to make fewer errors in the future.

Methodology/Principal Findings

Here, we show that error events can be detected from human electrocorticography (ECoG) during a continuous task with high precision, given a temporal tolerance of 300–400 milliseconds. We quantified the error detection accuracy and showed that, using only a small subset of 2×2 ECoG electrodes, 82% of detection information for outcome error and 74% of detection information for execution error available from all ECoG electrodes could be retained.

Conclusions/Significance

The error detection method presented here could be used to correct errors made during BMI operation or to adapt a BMI algorithm to make fewer errors in the future. Furthermore, our results indicate that smaller ECoG implant could be used for error detection. Reducing the size of an ECoG electrode implant used for BMI decoding and error detection could significantly reduce the medical risk of implantation.

Unsupervised adaptation of brain-machine interface decoders

The performance of neural decoders can degrade over time due to non-stationarities in the relationship between neuronal activity and behavior. In this case, brain-machine interfaces (BMI) require adaptation of their decoders to maintain high performance across time. One way to achieve this is by use of periodical calibration phases, during which the BMI system (or an external human demonstrator) instructs the user to perform certain movements or behaviors. This approach has two disadvantages: (i) calibration phases interrupt the autonomous operation of the BMI and (ii) between two calibration phases the BMI performance might not be stable but continuously decrease. A better alternative would be that the BMI decoder is able to continuously adapt in an unsupervised manner during autonomous BMI operation, i.e., without knowing the movement intentions of the user. In the present article, we present an efficient method for such unsupervised training of BMI systems for continuous movement control. The proposed method utilizes a cost function derived from neuronal recordings, which guides a learning algorithm to evaluate the decoding parameters. We verify the performance of our adaptive method by simulating a BMI user with an optimal feedback control model and its interaction with our adaptive BMI decoder. The simulation results show that the cost function and the algorithm yield fast and precise trajectories toward targets at random orientations on a 2-dimensional computer screen. For initially unknown and non-stationary tuning parameters, our unsupervised method is still able to generate precise trajectories and to keep its performance stable in the long term. The algorithm can optionally work also with neuronal error-signals instead or in conjunction with the proposed unsupervised adaptation.

Online detection of error-related potentials boosts the performance of mental typewriters

Background

Increasing the communication speed of brain-computer interfaces (BCIs) is a major aim of current BCI-research. The idea to automatically detect error-related potentials (ErrPs) in order to veto erroneous decisions of a BCI has been existing for more than one decade, but this approach was so far little investigated in online mode.

Methods

In our study with eleven participants, an ErrP detection mechanism was implemented in an electroencephalography (EEG) based gaze-independent visual speller.

Results

Single-trial ErrPs were detected with a mean accuracy of 89.1% (AUC 0.90). The spelling speed was increased on average by 49.0% using ErrP detection. The improvement in spelling speed due to error detection was largest for participants with low spelling accuracy.

Conclusion

The performance of BCIs can be increased by using an automatic error detection mechanism. The benefit for patients with motor disorders is potentially high since they often have rather low spelling accuracies compared to healthy people.

Error-related electrocorticographic activity in humans during continuous movements

Brain-machine interface (BMI) devices make errors in decoding. Detecting these errors online from neuronal activity can improve BMI performance by modifying the decoding algorithm and by correcting the errors made. Here, we study the neuronal correlates of two different types of errors which can both be employed in BMI: (i) the execution error, due to inaccurate decoding of the subjects' movement intention; (ii) the outcome error, due to not achieving the goal of the movement. We demonstrate that, in electrocorticographic (ECoG) recordings from the surface of the human brain, strong error-related neural responses (ERNRs) for both types of errors can be observed. ERNRs were present in the low and high frequency components of the ECoG signals, with both signal components carrying partially independent information. Moreover, the observed ERNRs can be used to discriminate between error types, with high accuracy (≥83%) obtained already from single electrode signals. We found ERNRs in multiple cortical areas, including motor and somatosensory cortex. As the motor cortex is the primary target area for recording control signals for a BMI, an adaptive motor BMI utilizing these error signals may not require additional electrode implants in other brain areas.

Objective and Subjective Evaluation of Online Error Correction during P300-Based Spelling

Error potentials (ErrP) are alterations of EEG traces following the subject’s perception of erroneous feedbacks. They provide a way to recognize misinterpreted commands in brain-computer interfaces (BCI). However, this has been evaluated online in only a couple of studies and mostly with very few subjects. In this study, we implemented a P300-based BCI, including not only online error detection but also, for the first time, automatic correction. We evaluated it in 16 healthy volunteers. Whenever an error was detected, a new decision was made based on the second best guess of a probabilistic classifier. At the group level, correction did neither improve nor deteriorate spelling accuracy. However, automatic correction yielded a higher bit rate than a respelling strategy. Furthermore, the fine examination of interindividual differences in the efficiency of error correction and spelling clearly distinguished between two groups who differed according to individual specificity in ErrP detection. The high specificity group had larger evoked responses and made fewer errors which were corrected more efficiently, yielding a 4% improvement in spelling accuracy and a higher bit rate. Altogether, our results suggest that the more the subject is engaged into the task, the more useful and well accepted the automatic error correction.

Context-aware brain-computer interfaces: exploring the information space of user, technical system and environment

Brain-computer interface (BCI) systems are usually applied in highly controlled environments such as research laboratories or clinical setups. However, many BCI-based applications are implemented in more complex environments. For example, patients might want to use a BCI system at home, and users without disabilities could benefit from BCI systems in special working environments. In these contexts, it might be more difficult to reliably infer information about brain activity, because many intervening factors add up and disturb the BCI feature space. One solution for this problem would be adding context awareness to the system. We propose to augment the available information space with additional channels carrying information about the user state, the environment and the technical system. In particular, passive BCI systems seem to be capable of adding highly relevant context information-otherwise covert aspects of user state. In this paper, we present a theoretical framework based on general human-machine system research for adding context awareness to a BCI system. Building on that, we present results from a study on a passive BCI, which allows access to the covert aspect of user state related to the perceived loss of control. This study is a proof of concept and demonstrates that context awareness could beneficially be implemented in and combined with a BCI system or a general human-machine system. The EEG data from this experiment are available for public download at www.phypa.org.

A collaborative brain-computer interface for improving human performance

Electroencephalogram (EEG) based brain-computer interfaces (BCI) have been studied since the 1970s. Currently, the main focus of BCI research lies on the clinical use, which aims to provide a new communication channel to patients with motor disabilities to improve their quality of life. However, the BCI technology can also be used to improve human performance for normal healthy users. Although this application has been proposed for a long time, little progress has been made in real-world practices due to technical limits of EEG. To overcome the bottleneck of low single-user BCI performance, this study proposes a collaborative paradigm to improve overall BCI performance by integrating information from multiple users. To test the feasibility of a collaborative BCI, this study quantitatively compares the classification accuracies of collaborative and single-user BCI applied to the EEG data collected from 20 subjects in a movement-planning experiment. This study also explores three different methods for fusing and analyzing EEG data from multiple subjects: (1) Event-related potentials (ERP) averaging, (2) Feature concatenating, and (3) Voting. In a demonstration system using the Voting method, the classification accuracy of predicting movement directions (reaching left vs. reaching right) was enhanced substantially from 66% to 80%, 88%, 93%, and 95% as the numbers of subjects increased from 1 to 5, 10, 15, and 20, respectively. Furthermore, the decision of reaching direction could be made around 100–250 ms earlier than the subject's actual motor response by decoding the ERP activities arising mainly from the posterior parietal cortex (PPC), which are related to the processing of visuomotor transmission. Taken together, these results suggest that a collaborative BCI can effectively fuse brain activities of a group of people to improve the overall performance of natural human behavior.

Using brain-computer interfaces and brain-state dependent stimulation as tools in cognitive neuroscience

Large efforts are currently being made to develop and improve online analysis of brain activity which can be used, e.g., for brain-computer interfacing (BCI). A BCI allows a subject to control a device by willfully changing his/her own brain activity. BCI therefore holds the promise as a tool for aiding the disabled and for augmenting human performance. While technical developments obviously are important, we will here argue that new insight gained from cognitive neuroscience can be used to identify signatures of neural activation which reliably can be modulated by the subject at will. This review will focus mainly on oscillatory activity in the alpha band which is strongly modulated by changes in covert attention. Besides developing BCIs for their traditional purpose, they might also be used as a research tool for cognitive neuroscience. There is currently a strong interest in how brain-state fluctuations impact cognition. These state fluctuations are partly reflected by ongoing oscillatory activity. The functional role of the brain state can be investigated by introducing stimuli in real-time to subjects depending on the actual state of the brain. This principle of brain-state dependent stimulation may also be used as a practical tool for augmenting human behavior. In conclusion, new approaches based on online analysis of ongoing brain activity are currently in rapid development. These approaches are amongst others informed by new insight gained from electroencephalography/magnetoencephalography studies in cognitive neuroscience and hold the promise of providing new ways for investigating the brain at work.

Neuroergonomics

Neuroergonomics is the study of the human brain in relation to performance at work and other everyday settings. Research using two classes of methods—neuroimaging and molecular genetics—is described in four areas: (a) multitasking and mental workload, (b) human error, (c) neuroadaptive interfaces, and (d) individual differences in cognition. The findings show that theoretical and practical understanding of how humans interact with and use technology can be considerably enriched if we also consider the human brain that makes such activities possible.

Adaptation of hybrid human-computer interaction systems using EEG error-related potentials

Performance improvement in both humans and artificial systems strongly relies in the ability of recognizing erroneous behavior or decisions. This paper, that builds upon previous studies on EEG error-related signals, presents a hybrid approach for human computer interaction that uses human gestures to send commands to a computer and exploits brain activity to provide implicit feedback about the recognition of such commands. Using a simple computer game as a case study, we show that EEG activity evoked by erroneous gesture recognition can be classified in single trials above random levels. Automatic artifact rejection techniques are used, taking into account that subjects are allowed to move during the experiment. Moreover, we present a simple adaptation mechanism that uses the EEG signal to label newly acquired samples and can be used to re-calibrate the gesture recognition system in a supervised manner. Offline analysis show that, although the achieved EEG decoding accuracy is far from being perfect, these signals convey sufficient information to significantly improve the overall system performance.