Single-trial EEG Research Articles

Decoding speech perception by native and non-native speakers using single-trial electrophysiological data.

Brain-computer interfaces (BCIs) are systems that use real-time analysis of neuroimaging data to determine the mental state of their user for purposes such as providing neurofeedback. Here, we investigate the feasibility of a BCI based on speech perception. Multivariate pattern classification methods were applied to single-trial EEG data collected during speech perception by native and non-native speakers. Two principal questions were asked: 1) Can differences in the perceived categories of pairs of phonemes be decoded at the single-trial level? 2) Can these same categorical differences be decoded across participants, within or between native-language groups? Results indicated that classification performance progressively increased with respect to the categorical status (within, boundary or across) of the stimulus contrast, and was also influenced by the native language of individual participants. Classifier performance showed strong relationships with traditional event-related potential measures and behavioral responses. The results of the cross-participant analysis indicated an overall increase in average classifier performance when trained on data from all participants (native and non-native). A second cross-participant classifier trained only on data from native speakers led to an overall improvement in performance for native speakers, but a reduction in performance for non-native speakers. We also found that the native language of a given participant could be decoded on the basis of EEG data with accuracy above 80%. These results indicate that electrophysiological responses underlying speech perception can be decoded at the single-trial level, and that decoding performance systematically reflects graded changes in the responses related to the phonological status of the stimuli. This approach could be used in extensions of the BCI paradigm to support perceptual learning during second language acquisition.

Bayesian learning for spatial filtering in an EEG-based brain-computer interface.

Spatial filtering for EEG feature extraction and classification is an important tool in brain-computer interface. However, there is generally no established theory that links spatial filtering directly to Bayes classification error. To address this issue, this paper proposes and studies a Bayesian analysis theory for spatial filtering in relation to Bayes error. Following the maximum entropy principle, we introduce a gamma probability model for describing single-trial EEG power features. We then formulate and analyze the theoretical relationship between Bayes classification error and the so-called Rayleigh quotient, which is a function of spatial filters and basically measures the ratio in power features between two classes. This paper also reports our extensive study that examines the theory and its use in classification, using three publicly available EEG data sets and state-of-the-art spatial filtering techniques and various classifiers. Specifically, we validate the positive relationship between Bayes error and Rayleigh quotient in real EEG power features. Finally, we demonstrate that the Bayes error can be practically reduced by applying a new spatial filter with lower Rayleigh quotient.

Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG

While common spatial pattern may be the most widely used feature for discriminating motor imagery based EEG signals, Rayleigh coefficient maximization enable us to have one more effective. However, such a feature is often deteriorated by redundant electrode channels which may result in low classification accuracy, extra subsequent computational load and difficulty in understanding which part of the brain relates to classification-relevant activity. In this paper, we present a channel selection method to deal with these problems, in which an improved genetic algorithm based on the Rayleigh coefficient feature is conducted to determine the optimal subset of channels. Experiment results on two motor imagery EEG datasets verify that our method is effective in channel selection for classifying motor imagery EEG signals.

Brain–heart coupling at the P300 latency is linked to anterior cingulate cortex and insula—A cardio-electroencephalographic covariance tracing study

Prior work on the coupling of cortical and cardiac responses to feedback demonstrated that feedback-evoked single-trial EEG magnitudes 300ms post-stimulus predict the degree of subsequent cardiac acceleration. The main goal of the current study was to explore the neural sources of this phenomenon using (a) independent component analysis in conjunction with dipole fitting and (b) low resolution electromagnetic tomography (LORETA) in N=14 participants who performed a gambling task with feedback presented after each trial. It was shown that independent components localized near anterior cingulate cortex produced robust within-subjects correlations with feedback-evoked heart-period, suggesting that anterior cingulate cortex activity 300ms after feedback presentation predicts the strength of subsequent cardiac acceleration. Moreover, interindividual differences in evoked left insular cortex LORETA-estimated activity at around 300ms moderated within-subjects EEG–heart period correlations. These results suggest that key regions of central autonomic control are involved in cortico-cardiac coupling evoked by feedback stimuli.

Harmony search-based hidden Markov model optimization for online classification of single trial eegs during motor imagery tasks

This paper presents an improved method based on single trial EEG data for the online classification of motor imagery tasks for brain-computer interface (BCI) applications. The ultimate goal of this research is the development of a novel classification method that can be used to control an interactive robot agent platform via a BCI system. The proposed classification process is an adaptive learning method based on an optimization process of the hidden Markov model (HMM), which is, in turn, based on meta-heuristic algorithms. We utilize an optimized strategy for the HMM in the training phase of time-series EEG data during motor imagery-related mental tasks. However, this process raises important issues of model interpretation and complexity control. With these issues in mind, we explore the possibility of using a harmony search algorithm that is flexible and thus allows the elimination of tedious parameter assignment efforts to optimize the HMM parameter configuration. In this paper, we illustrate a sequential data analysis simulation, and we evaluate the optimized HMM. The performance results of the proposed BCI experiment show that the optimized HMM classifier is more capable of classifying EEG datasets than ordinary HMM during motor imagery tasks.

Individual EEG differences in affective valence processing in women with low and high neuroticism

ObjectiveIn this study, individual differences in brain electrophysiology during positive and negative affective valence processing in women with different neuroticism scores are quantified. MethodsTwenty-six women scoring high and low on neuroticism participated on this experiment. A support vector machine (SVM)-based classifier was applied on the EEG single trials elicited by high arousal pictures with negative and positive valence scores. Based on the accuracy values obtained from subject identification tasks, the most distinguishing EEG channels among participants were detected, pointing which scalp regions show more distinct patterns. ResultsSignificant differences were obtained, in the EEG heterogeneity between positive and negative valence stimuli, yielding higher accuracy in subject identification using negative pictures. Regarding the topographical analysis, significantly higher accuracy values were reached in occipital areas and in the right hemisphere (p<0.001). ConclusionsMainly, individual differences in EEG can be located in parietooccipital regions. These differences are likely to be due to the different reactivity and coping strategies to unpleasant stimuli in individuals with high neuroticism. In addition, the right hemisphere shows a greater individual specificity. SignificanceAn SVM-based classifier asserts the individual specificity and its topographical differences in electrophysiological activity for women with high neuroticism compared to low neuroticism.

Discriminant and adaptive extensions to local temporal common spatial patterns

An important issue in brain–computer interfaces based on multi-channel EEG signals is to extract spatial filters. Local temporal common spatial patterns (LTCSP) is a recently developed approach to find spatial filters, which takes temporally local information into account. The formulation of LTCSP, however, is essentially a subspace decomposition technique. In this paper, we extend LTCSP from the aspects of discrimination and adaption. The discriminant extension is based on the Fisher discriminant criterion that considers both the between-class and the within-class scatters. By contrast, LTCSP considers maximizing the between-class scatter only. The adaptive extension uses sparse representation to specify the weights between samples in constructing the temporally local scatter matrices. Experiments on single-trial EEG classification confirm the effectiveness of the proposed methods.

5‐HTTLPR and anxiety modulate brain‐heart covariation

To date, little is known about genes affecting the interplay of brain and heart activity. Because serotonin (5-HT) is involved in corticovagal neurotransmission, we tested whether the 5-HT transporter polymorphism 5-HTTLPR affects brain-heart covariation. Further, associations with neuroticism/anxiety (NANX) were tested, as anxiety is related to 5-HT and neurogenic changes of heart period (HP). N = 168 participants performed a time-estimation task while EEG and HP were recorded. Brain-heart covariation was measured using time-lagged within-subject correlations of centromedial feedback-evoked single-trial EEG at 300 ms and subsequent changes of HP. EEG-HP correlations were higher in 5-HTTLPR long allele carriers. Moreover, after negative feedback, EEG-HP correlations and feedback-related negativity amplitudes independently correlated with NANX. The results indicate that individual differences in brain-heart covariation relate to 5-HT and NANX.

Modelling Trial-by-Trial Changes in the Mismatch Negativity

The mismatch negativity (MMN) is a differential brain response to violations of learned regularities. It has been used to demonstrate that the brain learns the statistical structure of its environment and predicts future sensory inputs. However, the algorithmic nature of these computations and the underlying neurobiological implementation remain controversial. This article introduces a mathematical framework with which competing ideas about the computational quantities indexed by MMN responses can be formalized and tested against single-trial EEG data. This framework was applied to five major theories of the MMN, comparing their ability to explain trial-by-trial changes in MMN amplitude. Three of these theories (predictive coding, model adjustment, and novelty detection) were formalized by linking the MMN to different manifestations of the same computational mechanism: approximate Bayesian inference according to the free-energy principle. We thereby propose a unifying view on three distinct theories of the MMN. The relative plausibility of each theory was assessed against empirical single-trial MMN amplitudes acquired from eight healthy volunteers in a roving oddball experiment. Models based on the free-energy principle provided more plausible explanations of trial-by-trial changes in MMN amplitude than models representing the two more traditional theories (change detection and adaptation). Our results suggest that the MMN reflects approximate Bayesian learning of sensory regularities, and that the MMN-generating process adjusts a probabilistic model of the environment according to prediction errors.

A Novel Bayesian Framework for Discriminative Feature Extraction in Brain-Computer Interfaces

As there has been a paradigm shift in the learning load from a human subject to a computer, machine learning has been considered as a useful tool for Brain-Computer Interfaces (BCIs). In this paper, we propose a novel Bayesian framework for discriminative feature extraction for motor imagery classification in an EEG-based BCI in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches. In our framework, the problem of simultaneous spatiospectral filter optimization is formulated as the estimation of an unknown posterior probability density function (pdf) that represents the probability that a single-trial EEG of predefined mental tasks can be discriminated in a state. In order to estimate the posterior pdf, we propose a particle-based approximation method by extending a factored-sampling technique with a diffusion process. An information-theoretic observation model is also devised to measure discriminative power of features between classes. From the viewpoint of classifier design, the proposed method naturally allows us to construct a spectrally weighted label decision rule by linearly combining the outputs from multiple classifiers. We demonstrate the feasibility and effectiveness of the proposed method by analyzing the results and its success on three public databases.

L1-norm based discriminative spatial pattern for single-trial EEG classification

Spatial filtering provides an efficient method for single-trial EEG classification and has been widely used in EEG-based brain computer interfaces. However, scalp-recorded EEG signals are usually very noisy since they could be contaminated by various outliers, such as EOG or EMG artifacts. The outliers may seriously distort the performance of spatial filters. To solve this problem, we propose a new robust spatial filtering algorithm, namely DSP-L1, which is L1-norm based discriminative spatial pattern (DSP). Compared with the conventional DSP, DSP-L1 takes advantage of the robust L1-norm modeling that expects to perform better in suppressing the effect of outliers. Computationally, an iterative approach is introduced to find the spatial filters of DSP-L1. Experimental results on two EEG data sets of motor movements demonstrate the efficiency of the proposed method.

Estimating Brain Connectivity from Single-Trial EEG Recordings

Article Estimating Brain Connectivity from Single-Trial EEG Recordings was published on September 7, 2013 in the journal Biomedical Engineering / Biomedizinische Technik (volume 58, issue SI-1-Track-S).

Local Temporal Correlation Common Spatial Patterns for Single Trial EEG Classification during Motor Imagery

Common spatial pattern (CSP) is one of the most popular and effective feature extraction methods for motor imagery-based brain-computer interface (BCI), but the inherent drawback of CSP is that the estimation of the covariance matrices is sensitive to noise. In this work, local temporal correlation (LTC) information was introduced to further improve the covariance matrices estimation (LTCCSP). Compared to the Euclidean distance used in a previous CSP variant named local temporal CSP (LTCSP), the correlation may be a more reasonable metric to measure the similarity of activated spatial patterns existing in motor imagery period. Numerical comparisons among CSP, LTCSP, and LTCCSP were quantitatively conducted on the simulated datasets by adding outliers to Dataset IVa of BCI Competition III and Dataset IIa of BCI Competition IV, respectively. Results showed that LTCCSP achieves the highest average classification accuracies in all the outliers occurrence frequencies. The application of the three methods to the EEG dataset recorded in our laboratory also demonstrated that LTCCSP achieves the highest average accuracy. The above results consistently indicate that LTCCSP would be a promising method for practical motor imagery BCI application.

Recognition of Human Implicit Intention based on fMRI and EEG

Recognition of Human Implicit Intention based on fMRI and EEG

Spontaneous pre-stimulus fluctuations in the activity of right fronto-parietal areas influence inhibitory control performance

Inhibitory control refers to the ability to suppress planned or ongoing cognitive or motor processes. Electrophysiological indices of inhibitory control failure have been found to manifest even before the presentation of the stimuli triggering the inhibition, suggesting that pre-stimulus brain-states modulate inhibition performance. However, previous electrophysiological investigations on the state-dependency of inhibitory control were based on averaged event-related potentials (ERPs), a method eliminating the variability in the ongoing brain activity not time-locked to the event of interest. These studies thus left unresolved whether spontaneous variations in the brain-state immediately preceding unpredictable inhibition-triggering stimuli also influence inhibitory control performance. To address this question, we applied single-trial EEG topographic analyses on the time interval immediately preceding NoGo stimuli in conditions where the responses to NoGo trials were correctly inhibited [correct rejection (CR)] vs. committed [false alarms (FAs)] during an auditory spatial Go/NoGo task. We found a specific configuration of the EEG voltage field manifesting more frequently before correctly inhibited responses to NoGo stimuli than before FAs. There was no evidence for an EEG topography occurring more frequently before FAs than before CR. The visualization of distributed electrical source estimations of the EEG topography preceding successful response inhibition suggested that it resulted from the activity of a right fronto-parietal brain network. Our results suggest that the fluctuations in the ongoing brain activity immediately preceding stimulus presentation contribute to the behavioral outcomes during an inhibitory control task. Our results further suggest that the state-dependency of sensory-cognitive processing might not only concern perceptual processes, but also high-order, top-down inhibitory control mechanisms.

Quantifying attentional modulation of auditory-evoked cortical responses from single-trial electroencephalography

Selective auditory attention is essential for human listeners to be able to communicate in multi-source environments. Selective attention is known to modulate the neural representation of the auditory scene, boosting the representation of a target sound relative to the background, but the strength of this modulation, and the mechanisms contributing to it, are not well understood. Here, listeners performed a behavioral experiment demanding sustained, focused spatial auditory attention while we measured cortical responses using electroencephalography (EEG). We presented three concurrent melodic streams; listeners were asked to attend and analyze the melodic contour of one of the streams, randomly selected from trial to trial. In a control task, listeners heard the same sound mixtures, but performed the contour judgment task on a series of visual arrows, ignoring all auditory streams. We found that the cortical responses could be fit as weighted sum of event-related potentials evoked by the stimulus onsets in the competing streams. The weighting to a given stream was roughly 10 dB higher when it was attended compared to when another auditory stream was attended; during the visual task, the auditory gains were intermediate. We then used a template-matching classification scheme to classify single-trial EEG results. We found that in all subjects, we could determine which stream the subject was attending significantly better than by chance. By directly quantifying the effect of selective attention on auditory cortical responses, these results reveal that focused auditory attention both suppresses the response to an unattended stream and enhances the response to an attended stream. The single-trial classification results add to the growing body of literature suggesting that auditory attentional modulation is sufficiently robust that it could be used as a control mechanism in brain–computer interfaces (BCIs).

Optimizing spatial spectral patterns jointly with channel configuration for brain–computer interface

The power of common spatial pattern (CSP) has been widely validated in electroencephalogram (EEG) based brain–computer interface (BCI). However, its effectiveness is highly dependent on subject-specific time segment, channel configuration and frequency band. Hence, the preprocessing procedure of CSP algorithm is critical to enhance the performance of BCI system. This paper proposes a feature extraction and selection method based on common spatial and spectral pattern for motor imagery brain–computer interface (BCI). We formulate the optimization of spatial spectral patterns, channel configuration and time segment as maximizing the proposed criterions including mutual information algorithm, Fisher ratio algorithm and wrapper method. The proposed method is evaluated on single trial EEG from dataset IVa of BCI competition III. The results show that best features are selected by a wrapper method and these features in cross-validation yield better performance compared to most of the reported results.

How about taking a low‐cost, small, and wireless EEG for a walk?

To build a low-cost, small, and wireless electroencephalogram (EEG) system suitable for field recordings, we merged consumer EEG hardware with an EEG electrode cap. Auditory oddball data were obtained while participants walked outdoors on university campus. Single-trial P300 classification with linear discriminant analysis revealed high classification accuracies for both indoor (77%) and outdoor (69%) recording conditions. We conclude that good quality, single-trial EEG data suitable for mobile brain-computer interfaces can be obtained with affordable hardware.

Combining features from ERP components in single-trial EEG for discriminating four-category visual objects

Categorization of images containing visual objects can be successfully recognized using single-trial electroencephalograph (EEG) measured when subjects view images. Previous studies have shown that task-related information contained in event-related potential (ERP) components could discriminate two or three categories of object images. In this study, we investigated whether four categories of objects (human faces, buildings, cats and cars) could be mutually discriminated using single-trial EEG data. Here, the EEG waveforms acquired while subjects were viewing four categories of object images were segmented into several ERP components (P1, N1, P2a and P2b), and then Fisher linear discriminant analysis (Fisher-LDA) was used to classify EEG features extracted from ERP components. Firstly, we compared the classification results using features from single ERP components, and identified that the N1 component achieved the highest classification accuracies. Secondly, we discriminated four categories of objects using combining features from multiple ERP components, and showed that combination of ERP components improved four-category classification accuracies by utilizing the complementarity of discriminative information in ERP components. These findings confirmed that four categories of object images could be discriminated with single-trial EEG and could direct us to select effective EEG features for classifying visual objects.

Single trial time–frequency domain analysis of error processing in post-traumatic stress disorder

Error processing studies in psychology and psychiatry are relatively common. Event-related potentials (ERPs) are often used as measures of error processing, two such response-locked ERPs being the error-related negativity (ERN) and the error-related positivity (Pe). The ERN and Pe occur following committed error in reaction time tasks as low frequency (4–8Hz) electroencephalographic (EEG) oscillations registered at the midline fronto-central sites. We created an alternative method for analyzing error processing using time–frequency analysis in the form of a wavelet transform. A study was conducted in which subjects with PTSD and healthy control completed a forced-choice task. Single trial EEG data from errors in the task were processed using a continuous wavelet transform. Coefficients from the transform that corresponded to the theta range were averaged to isolate a theta waveform in the time–frequency domain. Measures called the time–frequency ERN and Pe were obtained from these waveforms for five different channels and then averaged to obtain a single time–frequency ERN and Pe for each error trial. A comparison of the amplitude and latency for the time–frequency ERN and Pe between the PTSD and control group was performed. A significant group effect was found on the amplitude of both measures. These results indicate that the developed single trial time–frequency error analysis method is suitable for examining error processing in PTSD and possibly other psychiatric disorders.