Single-trial EEG Research Articles

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.

Decoding Visual Motions from EEG Using Attention-Based RNN

The main objective of this paper is to use deep neural networks to decode the electroencephalography (EEG) signals evoked when individuals perceive four types of motion stimuli (contraction, expansion, rotation, and translation). Methods for single-trial and multi-trial EEG classification are both investigated in this study. Attention mechanisms and a variant of recurrent neural networks (RNNs) are incorporated as the decoding model. Attention mechanisms emphasize task-related responses and reduce redundant information of EEG, whereas RNN learns feature representations for classification from the processed EEG data. To promote generalization of the decoding model, a novel online data augmentation method that randomly averages EEG sequences to generate artificial signals is proposed for single-trial EEG. For our dataset, the data augmentation method improves the accuracy of our model (based on RNN) and two benchmark models (based on convolutional neural networks) by 5.60%, 3.92%, and 3.02%, respectively. The attention-based RNN reaches mean accuracies of 67.18% for single-trial EEG decoding with data augmentation. When performing multi-trial EEG classification, the amount of training data decreases linearly after averaging, which may result in poor generalization. To address this deficiency, we devised three schemes to randomly combine data for network training. Accordingly, the results indicate that the proposed strategies effectively prevent overfitting and improve the correct classification rate compared with averaging EEG fixedly (by up to 19.20%). The highest accuracy of the three strategies for multi-trial EEG classification achieves 82.92%. The decoding performance for the methods proposed in this work indicates they have application potential in the brain–computer interface (BCI) system based on visual motion perception.

Asynchronous Video Target Detection Based on Single-Trial EEG Signals.

Event-related potentials (ERPs) are widely used in brain-computer interface (BCI) systems to detect sensitive targets. However, asynchronous BCI systems based on video-target-evoked ERPs can pose a challenge in real-world applications due to the absence of an explicit target onset time and the time jitter of the detection latency. To address this challenge, we developed an asynchronous detection framework for video target detection. In this framework, an ERP alignment method based on the principle of iterative minimum distance square error (MDSE) was proposed for constructing an ERP template and aligning signals on the same base to compensate for possible time jitter. Using this method, ERP response characteristics induced by video targets were estimated. Online video target detection results indicated that alignment methods reduced the false alarm more effectively than non-alignment methods. The false alarm of the proposed Aligned-MDSE method was one-third lower than that of existing alignment methods under the same right hit level using limited individual samples. Furthermore, cross-subject results indicated that untrained subjects could directly perform online detection tasks and achieve excellent performance by a general model trained from more than 10 subjects. The proposed asynchronous video target detection framework can thus have a significant impact on real-world BCI applications.

Decoding auditory attention from single-trial EEG for a high-efficiency brain-computer interface.

Brain-computer interface (BCI) systems enable humans to communicate with a machine in a non-verbal and covert way. Many past BCI designs used visual stimuli, due to the robustness of neural signatures evoked by visual input. However, these BCI systems can only be used when visual attention is available. This study proposes a new BCI design using auditory stimuli, decoding spatial attention from electroencephalography (EEG). Results show that this new approach can decode attention with a high accuracy (>75%) and has a high information transfer rate (>10 bits/min) compared to other auditory BCI systems. It also has the potential to allow decoding that does not depend on subject-specific training.

Ketamine Affects Prediction Errors about Statistical Regularities: A Computational Single-Trial Analysis of the Mismatch Negativity.

The auditory mismatch negativity (MMN) is significantly reduced in schizophrenia. Notably, a similar MMN reduction can be achieved with NMDA receptor (NMDAR) antagonists. Both phenomena have been interpreted as reflecting an impairment of predictive coding or, more generally, the "Bayesian brain" notion that the brain continuously updates a hierarchical model to infer the causes of its sensory inputs. Specifically, neurobiological interpretations of predictive coding view perceptual inference as an NMDAR-dependent process of minimizing hierarchical precision-weighted prediction errors (PEs), and disturbances of this putative process play a key role in hierarchical Bayesian theories of schizophrenia. Here, we provide empirical evidence for this theory, demonstrating the existence of multiple, hierarchically related PEs in a "roving MMN" paradigm. We applied a hierarchical Bayesian model to single-trial EEG data from healthy human volunteers of either sex who received the NMDAR antagonist S-ketamine in a placebo-controlled, double-blind, within-subject fashion. Using an unrestricted analysis of the entire time-sensor space, our trial-by-trial analysis indicated that low-level PEs (about stimulus transitions) are expressed early (102-207 ms poststimulus), while high-level PEs (about transition probability) are reflected by later components (152-199 and 215-277 ms) of single-trial responses. Furthermore, we find that ketamine significantly diminished the expression of high-level PE responses, implying that NMDAR antagonism disrupts the inference on abstract statistical regularities. Our findings suggest that NMDAR dysfunction impairs hierarchical Bayesian inference about the world's statistical structure. Beyond the relevance of this finding for schizophrenia, our results illustrate the potential of computational single-trial analyses for assessing potential pathophysiological mechanisms.

Detection and classification of single-trial movement-related cortical potentials associated with functional lower limb movements

Objective. Brain-computer interfaces that activate exoskeletons based on decoded movement-related activity have been shown to be useful for stroke rehabilitation. With the advances in the development of exoskeletons it is possible to replicate a number of different functional movements that are relevant to rehabilitate after stroke. In this study, the aim is to detect and classify six different movement tasks of the lower extremities that are used in the activities of daily living. Approach. Thirteen healthy subjects performed six movement tasks (1) Stand-to-sit, (2) Sit-to-stand, (3) Walking, (4) Step up, (5) Side step, and (6) Back step. Each movement task was performed 50 times while continuous EEG was recorded. The continuous EEG was divided into epochs containing the movement intention associated with the movements, and idle activity was obtained from recordings during rest. Temporal, spectral and template matching features were extracted from the EEG channels covering the motor cortex and classified using Random Forest in two ways: (1) movement intention vs. idle activity (estimate of movement intention detection), and (2) classification of movement types. Main results. The classification accuracies associated with movement intention detection were in the range of 80%–90%, while 54 ± 3% of all movement types were classified correctly. The stand-to-sit and sit-to-stand tasks were easiest to classify, while step up often was classified as walking. Significance. The results indicate that it is possible to detect and classify functional movements of the lower extremities from single-trial EEG. This may be implemented in a brain-computer interface that can control an exoskeleton and be used for neurorehabilitation.

Single-Trial EEG Responses Classified Using Latency Features.

Covert attention has been repeatedly shown to impact on EEG responses after single and repeated practice sessions. Machine learning techniques are increasingly adopted to classify single-trial EEG responses thereby primarily relying on amplitude-based features instead of latency-based features. In this study, we investigated changes in EEG response signatures of nine healthy older subjects when performing 10 sessions of covert attention training. We show that, when we trained classifiers to distinguish recorded EEG patterns between the two experimental conditions (a target stimulus is "present" or "not present"), latency-based classifiers outperform the amplitude-based ones and that classification accuracy improved along with behavioral accuracy, providing supportive evidence of brain plasticity.

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.

Selective auditory attention detection based on effective connectivity by single-trial EEG

Objective. Focusing attention on one speaker in an environment with lots of speakers is one of the important abilities of the human auditory system. The temporal dynamics of the attention process and how the brain precisely performs this task are yet unknown. This paper proposes a new method for the selective auditory attention detection (SAAD) from single-trial EEG signals using the brain effective connectivity and complex network analysis for two groups of listeners attending to the left or right ear. Approach. Here, the connectivity matrices of all subjects obtained from the Granger causality method are used to extract different features. Then, by employing the processes of feature selection and optimization, an optimized feature set is determined for the train of a classifier. Main results. Among different measures of brain connectivity (i.e. segregation, integration, and centrality), the evaluation results show that the optimized feature set obtained by the combination of the centrality measures contain the most discriminative features for the classification process. The proposed SAAD method as compared with state-of-the-art attention detection approaches from the literature yields the best performance in terms of various measures. Significance. The new SAAD approach is advantageous, in the sense that the detection of attention is performed from single-trial EEG signals of each subject, without reconstructing the speech stimuli. This means that the proposed method could be employed for real-time applications such as smart hearing aid devices or brain-computer interface (BCI) systems.

Mu-Beta event-related (de)synchronization and EEG classification of left-right foot dorsiflexion kinaesthetic motor imagery for BCI.

The left and right foot representation area is located within the interhemispheric fissure of the sensorimotor cortex and share spatial proximity. This makes it difficult to visualize the cortical lateralization of event-related (de)synchronization (ERD/ERS) during left and right foot motor imageries. The aim of this study is to investigate the possibility of using ERD/ERS in the mu, low beta, and high beta bandwidth, during left and right foot dorsiflexion kinaesthetic motor imageries (KMI), as unilateral control commands for a brain-computer interface (BCI). EEG was recorded from nine healthy participants during cue-based left-right foot dorsiflexion KMI tasks. The features were analysed for common average and bipolar references. With each reference, mu and beta band-power features were analysed using time–frequency (TF) maps, scalp topographies, and average time course for ERD/ERS. The cortical lateralization of ERD/ERS, during left and right foot KMI, was confirmed. Statistically significant features were classified using LDA, SVM, and KNN model, and evaluated using the area under ROC curves. An increase in high beta power following the end of KMI for both tasks was recorded, from right and left hemispheres, respectively, at the vertex. The single trial analysis and classification models resulted in high discrimination accuracies, i.e. maximum 83.4% for beta ERS, 79.1% for beta ERD, and 74.0% for mu ERD. With each model the features performed above the statistical chance level of 2-class discrimination for a BCI. Our findings indicate these features can evoke left-right differences in single EEG trials. This suggests that any BCI employing unilateral foot KMI can attain classification accuracy suitable for practical implementation. Given results stipulate the novel utilization of mu and beta as independent control features for discrimination of bilateral foot KMI in a BCI.

Applying deep learning to single-trial EEG data provides evidence for complementary theories on action control

Efficient action control is indispensable for goal-directed behaviour. Different theories have stressed the importance of either attention or response selection sub-processes for action control. Yet, it is unclear to what extent these processes can be identified in the dynamics of neurophysiological (EEG) processes at the single-trial level and be used to predict the presence of conflicts in a given moment. Applying deep learning, which was blind to cognitive theory, on single-trial EEG data allowed to predict the presence of conflict in ~95% of subjects ~33% above chance level. Neurophysiological features related to attentional and motor response selection processes in the occipital cortex and the superior frontal gyrus contributed most to prediction accuracy. Importantly, deep learning was able to identify predictive neurophysiological processes in single-trial neural dynamics. Hence, mathematical (artificial intelligence) approaches may be used to foster the validation and development of links between cognitive theory and neurophysiology of human behavior.

Effects of Sensorineural Hearing Loss on Cortical Synchronization to Competing Speech during Selective Attention.

When selectively attending to a speech stream in multi-talker scenarios, low-frequency cortical activity is known to synchronize selectively to fluctuations in the attended speech signal. Older listeners with age-related sensorineural hearing loss (presbycusis) often struggle to understand speech in such situations, even when wearing a hearing aid. Yet, it is unclear whether a peripheral hearing loss degrades the attentional modulation of cortical speech tracking. Here, we used psychoacoustics and electroencephalography (EEG) in male and female human listeners to examine potential effects of hearing loss on EEG correlates of speech envelope synchronization in cortex. Behaviorally, older hearing-impaired (HI) listeners showed degraded speech-in-noise recognition and reduced temporal acuity compared with age-matched normal-hearing (NH) controls. During EEG recordings, we used a selective attention task with two spatially separated simultaneous speech streams where NH and HI listeners both showed high speech recognition performance. Low-frequency (<10 Hz) envelope-entrained EEG responses were enhanced in the HI listeners, both for the attended speech, but also for tone sequences modulated at slow rates (4 Hz) during passive listening. Compared with the attended speech, responses to the ignored stream were found to be reduced in both HI and NH listeners, allowing for the attended target to be classified from single-trial EEG data with similar high accuracy in the two groups. However, despite robust attention-modulated speech entrainment, the HI listeners rated the competing speech task to be more difficult. These results suggest that speech-in-noise problems experienced by older HI listeners are not necessarily associated with degraded attentional selection.SIGNIFICANCE STATEMENT People with age-related sensorineural hearing loss often struggle to follow speech in the presence of competing talkers. It is currently unclear whether hearing impairment may impair the ability to use selective attention to suppress distracting speech in situations when the distractor is well segregated from the target. Here, we report amplified envelope-entrained cortical EEG responses to attended speech and to simple tones modulated at speech rates (4 Hz) in listeners with age-related hearing loss. Critically, despite increased self-reported listening difficulties, cortical synchronization to speech mixtures was robustly modulated by selective attention in listeners with hearing loss. This allowed the attended talker to be classified from single-trial EEG responses with high accuracy in both older hearing-impaired listeners and age-matched normal-hearing controls.

"You Have Reached Your Destination": A Single Trial EEG Classification Study.

Studies have established that it is possible to differentiate between the brain's responses to observing correct and incorrect movements in navigation tasks. Furthermore, these classifications can be used as feedback for a learning-based BCI, to allow real or virtual robots to find quasi-optimal routes to a target. However, when navigating it is important not only to know we are moving in the right direction toward a target, but also to know when we have reached it. We asked participants to observe a virtual robot performing a 1-dimensional navigation task. We recorded EEG and then performed neurophysiological analysis on the responses to two classes of correct movements: those that moved closer to the target but did not reach it, and those that did reach the target. Further, we used a stepwise linear classifier on time-domain features to differentiate the classes on a single-trial basis. A second data set was also used to further test this single-trial classification. We found that the amplitude of the P300 was significantly greater in cases where the movement reached the target. Interestingly, we were able to classify the EEG signals evoked when observing the two classes of correct movements against each other with mean overall accuracy of 66.5 and 68.0% for the two data sets, with greater than chance levels of accuracy achieved for all participants. As a proof of concept, we have shown that it is possible to classify the EEG responses in observing these different correct movements against each other using single-trial EEG. This could be used as part of a learning-based BCI and opens a new door toward a more autonomous BCI navigation system.

Decoding of single-trial EEG reveals unique states of functional brain connectivity that drive rapid speech categorization decisions

Objective. Categorical perception (CP) is an inherent property of speech perception. The response time (RT) of listeners’ perceptual speech identification is highly sensitive to individual differences. While the neural correlates of CP have been well studied in terms of the regional contributions of the brain to behavior, functional connectivity patterns that signify individual differences in listeners’ speed (RT) for speech categorization is less clear. In this study, we introduce a novel approach to address these questions. Approach. We applied several computational approaches to the EEG, including graph mining, machine learning (i.e., support vector machine), and stability selection to investigate the unique brain states (functional neural connectivity) that predict the speed of listeners’ behavioral decisions. Main results. We infer that (i) the listeners’ perceptual speed is directly related to dynamic variations in their brain connectomics, (ii) global network assortativity and efficiency distinguished fast, medium, and slow RTs, (iii) the functional network underlying speeded decisions increases in negative assortativity (i.e., became disassortative) for slower RTs, (iv) slower categorical speech decisions cause excessive use of neural resources and more aberrant information flow within the CP circuitry, (v) slower responders tended to utilize functional brain networks excessively (or inappropriately) whereas fast responders (with lower global efficiency) utilized the same neural pathways but with more restricted organization. Significance. Findings show that neural classifiers (SVM) coupled with stability selection correctly classify behavioral RTs from functional connectivity alone with over 92% accuracy (AUC = 0.9). Our results corroborate previous studies by supporting the engagement of similar temporal (STG), parietal, motor, and prefrontal regions in CP using an entirely data-driven approach.

Interpreting neural decoding models using grouped model reliance.

Machine learning algorithms are becoming increasingly popular for decoding psychological constructs based on neural data. However, as a step towards bridging the gap between theory-driven cognitive neuroscience and data-driven decoding approaches, there is a need for methods that allow to interpret trained decoding models. The present study demonstrates grouped model reliance as a model-agnostic permutation-based approach to this problem. Grouped model reliance indicates the extent to which a trained model relies on conceptually related groups of variables, such as frequency bands or regions of interest in electroencephalographic (EEG) data. As a case study to demonstrate the method, random forest and support vector machine models were trained on within-participant single-trial EEG data from a Sternberg working memory task. Participants were asked to memorize a sequence of digits (0–9), varying randomly in length between one, four and seven digits, where EEG recordings for working memory load estimation were taken from a 3-second retention interval. The present results confirm previous findings insofar as both random forest and support vector machine models relied on alpha-band activity in most subjects. However, as revealed by further analyses, patterns in frequency and topography varied considerably between individuals, pointing to more pronounced inter-individual differences than previously reported.

Cognitive-Driven Binaural Beamforming Using EEG-Based Auditory Attention Decoding

Identifying the target speaker in hearing aid applications is an essential ingredient to improve speech intelligibility. Recently, a least-squares-based auditory attention decoding (AAD) method has been proposed to identify the target speaker from single-trial EEG recordings in an acoustic scenario with two competing speakers. Aiming at enhancing the target speaker and suppressing the interfering speaker and ambient noise, in this article, we propose a cognitive-driven speech enhancement system, consisting of a binaural beamformer which is steered based on AAD and estimated relative transfer function (RTF) vectors, which require estimates of the direction-of-arrivals (DOAs) of both speakers. For binaural beamforming and to generate reference signals for AAD, we consider either minimum-variance-distortionless-response (MVDR) beamformers or linearly-constrained-minimum-variance (LCMV) beamformers. Contrary to the binaural MVDR beamformer, the binaural LCMV beamformer allows to preserve the spatial impression of the acoustic scene and to control the suppression of the interfering speaker, which is important when intending to switch attention between speakers. The speech enhancement performance of the proposed system is evaluated in terms of the binaural signal-to-interference-plus-noise ratio ( $\text {SINR}$ ) improvement in anechoic and reverberant conditions. Furthermore, we investigate the impact of RTF and DOA estimation errors and AAD errors on the speech enhancement performance. The experimental results show that the proposed system using LCMV beamformers yields a larger decoding performance and binaural $\text {SINR}$ improvement compared to using MVDR beamformers.

Detection of single-trial EEG of the neural correlates of familiar faces recognition using machine-learning algorithms

Detection of single-trial EEG of the neural correlates of familiar faces recognition using machine-learning algorithms

Towards error categorisation in BCI: single-trial EEG classification between different errors

Objective. Error-related potentials (ErrP) are generated in the brain when humans perceive errors. These ErrP signals can be used to classify actions as erroneous or non-erroneous, using single-trial electroencephalography (EEG). A small number of studies have demonstrated the feasibility of using ErrP detection as feedback for reinforcement-learning-based brain-computer interfaces (BCI), confirming the possibility of developing more autonomous BCI. These systems could be made more efficient with specific information about the type of error that occurred. A few studies differentiated the ErrP of different errors from each other, based on direction or severity. However, errors cannot always be categorised in these ways. We aimed to investigate the feasibility of differentiating very similar error conditions from each other, in the absence of previously explored metrics. Approach. In this study, we used two data sets with 25 and 14 participants to investigate the differences between errors. The two error conditions in each task were similar in terms of severity, direction and visual processing. The only notable differences between them were the varying cognitive processes involved in perceiving the errors, and differing contexts in which the errors occurred. We used a linear classifier with a small feature set to differentiate the errors on a single-trial basis. Main results. For both data sets, we observed neurophysiological distinctions between the ErrPs related to each error type. We found further distinctions between age groups. Furthermore, we achieved statistically significant single-trial classification rates for most participants included in the classification phase, with mean overall accuracy of 65.2% and 65.6% for the two tasks. Significance. As a proof of concept our results showed that it is feasible, using single-trial EEG, to classify these similar error types against each other. This study paves the way for more detailed and efficient learning in BCI, and thus for a more autonomous human-machine interaction.

Predicting individual decision-making responses based on single-trial EEG

Decision-making plays an essential role in the interpersonal interactions and cognitive processing of individuals. There has been increasing interest in being able to predict an individual’s decision-making response (i.e., acceptance or rejection). We proposed an electroencephalogram (EEG)-based computational intelligence framework to predict individual responses. Specifically, the discriminative spatial network pattern (DSNP), a supervised learning approach, was applied to single-trial EEG data to extract the DSNP feature from the single-trial brain network. A linear discriminate analysis (LDA) trained on the DSNP features was then used to predict the individual response trial-by-trial. To verify the performance of the proposed DSNP, we recruited two independent subject groups, and recorded the EEGs using two types of EEG systems. The performances of the trial-by-trial predictors achieved an accuracy of 0.88 ± 0.09 for the first dataset, and 0.90 ± 0.10 for the second dataset. These trial-by-trial prediction performances suggested that individual responses could be predicted trial-by-trial by using the specific pattern of single-trial EEG networks, and our proposed method has the potential to establish the biologically inspired artificial intelligence decision system.

Classification of load in visual working memory using single-trial EEG data

Classification of load in visual working memory using single-trial EEG data