The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG

EEG-Based Classification of Implicit Intention During Self-Relevant Sentence Reading

From electroencephalography (EEG) data during self-relevant sentence reading, we were able to discriminate two implicit intentions: 1) "agreement" and 2) "disagreement" to the read sentence. To improve the classification accuracy, discriminant features were selected based on Fisher score among EEG frequency bands and electrodes. Especially, the time-frequency representation with Morlet wavelet transforms showed clear differences in gamma, beta, and alpha band powers at frontocentral area, and theta band power at centroparietal area. The best classification accuracy of 75.5% was obtained by a support vector machine classifier with the gamma band features at frontocentral area. This result may enable a new intelligent user-interface which understands users' implicit intention, i.e., unexpressed or hidden intention.

Optimizing Single-Trial EEG Classification by Stationary Matrix Logistic Regression in Brain-Computer Interface

In addition to the noisy and limited spatial resolution characteristics of the electroencephalography (EEG) signal, the intrinsic nonstationarity in the EEG data makes the single-trial EEG classification an even more challenging problem in brain-computer interface (BCI). Variations of the signal properties within a session often result in deteriorated classification performance. This is mainly attributed to the reason that the routine feature extraction or classification method does not take the changes in the signal into account. Although several extensions to the standard feature extraction method have been proposed to reduce the sensitivity to nonstationarity in data, they optimize different objective functions from that of the subsequent classification model, and thereby, the extracted features may not be optimized for the classification. In this paper, we propose an approach that directly optimizes the classifier's discriminativity and robustness against the within-session nonstationarity of the EEG data through a single optimization paradigm, and show that it can greatly improve the performance, in particular for the subjects who have difficulty in controlling a BCI. Moreover, the experimental results on two benchmark data sets demonstrate that our approach significantly outperforms the compared approaches in reducing classification error rates.

Blind Source Separation for Unimodal and Multimodal Brain Networks: A Unifying Framework for Subspace Modeling

In the past decade, numerous advances in the study of the human brain were fostered by successful applications of blind source separation (BSS) methods to a wide range of imaging modalities. The main focus has been on extracting "networks" represented as the underlying latent sources. While the broad success in learning latent representations from multiple datasets has promoted the wide presence of BSS in modern neuroscience, it also introduced a wide variety of objective functions, underlying graphical structures, and parameter constraints for each method. Such diversity, combined with a host of datatype-specific know-how, can cause a sense of disorder and confusion, hampering a practitioner's judgment and impeding further development. We organize the diverse landscape of BSS models by exposing its key features and combining them to establish a novel unifying view of the area. In the process, we unveil important connections among models according to their properties and subspace structures. Consequently, a high-level descriptive structure is exposed, ultimately helping practitioners select the right model for their applications. Equipped with that knowledge, we review the current state of BSS applications to neuroimaging. The gained insight into model connections elicits a broader sense of generalization, highlighting several directions for model development. In light of that, we discuss emerging multi-dataset multidimensional (MDM) models and summarize their benefits for the study of the healthy brain and disease-related changes.

Motor priming in virtual reality can augment motor-imagery training efficacy in restorative brain-computer interaction: a within-subject analysis

Background

The use of Brain–Computer Interface (BCI) technology in neurorehabilitation provides new strategies to overcome stroke-related motor limitations. Recent studies demonstrated the brain's capacity for functional and structural plasticity through BCI. However, it is not fully clear how we can take full advantage of the neurobiological mechanisms underlying recovery and how to maximize restoration through BCI. In this study we investigate the role of multimodal virtual reality (VR) simulations and motor priming (MP) in an upper limb motor-imagery BCI task in order to maximize the engagement of sensory-motor networks in a broad range of patients who can benefit from virtual rehabilitation training.

Methods

In order to investigate how different BCI paradigms impact brain activation, we designed 3 experimental conditions in a within-subject design, including an immersive Multimodal Virtual Reality with Motor Priming (VRMP) condition where users had to perform motor-execution before BCI training, an immersive Multimodal VR condition, and a control condition with standard 2D feedback. Further, these were also compared to overt motor-execution. Finally, a set of questionnaires were used to gather subjective data on Workload, Kinesthetic Imagery and Presence.

Results

Our findings show increased capacity to modulate and enhance brain activity patterns in all extracted EEG rhythms matching more closely those present during motor-execution and also a strong relationship between electrophysiological data and subjective experience.

Conclusions

Our data suggest that both VR and particularly MP can enhance the activation of brain patterns present during overt motor-execution. Further, we show changes in the interhemispheric EEG balance, which might play an important role in the promotion of neural activation and neuroplastic changes in stroke patients in a motor-imagery neurofeedback paradigm. In addition, electrophysiological correlates of psychophysiological responses provide us with valuable information about the motor and affective state of the user that has the potential to be used to predict MI-BCI training outcome based on user’s profile. Finally, we propose a BCI paradigm in VR, which gives the possibility of motor priming for patients with low level of motor control.

Spatio-temporal common pattern: A companion method for ERP analysis in the time domain

BACKGROUND

Already used at the incept of research on event-related potentials (ERP) over half a century ago, the arithmetic mean is still the benchmark for ERP estimation. Such estimation, however, requires a large number of sweeps and/or a careful rejection of artifacts affecting the electroencephalographic recording.

NEW METHOD

In this article we propose a method for estimating ERPs as they are naturally contaminated by biological and instrumental artifacts. The proposed estimator makes use of multivariate spatio-temporal filtering to increase the signal-to-noise ratio. This approach integrates a number of relevant advances in ERP data analysis, such as single-sweep adaptive estimation of amplitude and latency and the use of multivariate regression to account for ERP overlapping in time.

RESULTS

We illustrate the effectiveness of the proposed estimator analyzing a dataset comprising 24 subjects involving a visual odd-ball paradigm, without performing any artifact rejection.

COMPARISON WITH EXISTING METHOD(S)

As compared to the arithmetic average, a lower number of sweeps is needed. Furthermore, artifact rejection can be performed roughly using permissive automatic procedures.

CONCLUSION

The proposed ensemble average estimator yields a reference companion to the arithmetic ensemble average estimation, suitable both in clinical and research settings. The method can be applied equally to event related fields (ERF) recorded by means of magnetoencephalography. In this article we describe all necessary methodological details to promote testing and comparison of this proposed method by peers. Furthermore, we release a MATLAB toolbox, a plug-in for the EEGLAB software suite and a stand-alone executable application.

Discrete classification technique applied to TV advertisements liking recognition system based on low-cost EEG headsets

Background

In this paper a new approach is applied to the area of marketing research. The aim of this paper is to recognize how brain activity responds during the visualization of short video advertisements using discrete classification techniques. By means of low cost electroencephalography devices (EEG), the activation level of some brain regions have been studied while the ads are shown to users. We may wonder about how useful is the use of neuroscience knowledge in marketing, or what could provide neuroscience to marketing sector, or why this approach can improve the accuracy and the final user acceptance compared to other works.

Methods

By using discrete techniques over EEG frequency bands of a generated dataset, C4.5, ANN and the new recognition system based on Ameva, a discretization algorithm, is applied to obtain the score given by subjects to each TV ad.

Results

The proposed technique allows to reach more than 75 % of accuracy, which is an excellent result taking into account the typology of EEG sensors used in this work. Furthermore, the time consumption of the algorithm proposed is reduced up to 30 % compared to other techniques presented in this paper.

Conclusions

This bring about a battery lifetime improvement on the devices where the algorithm is running, extending the experience in the ubiquitous context where the new approach has been tested.

Spatial filter adaptation based on the divergence framework for motor imagery EEG classification

To address the nonstationarity issue in EEG-based brain computer interface (BCI), the computational model trained using the training data needs to adapt to the data from the test sessions. In this paper, we propose a novel adaptation approach based on the divergence framework. Cross-session changes can be taken into consideration by searching the discriminative subspaces for test data on the manifold of orthogonal matrices in a semi-supervised manner. Subsequently, the feature space becomes more consistent across sessions and classifiers performance can be enhanced. Experimental results show that the proposed adaptation method yields improvements in classification performance.

Decoding three-dimensional reaching movements using electrocorticographic signals in humans

OBJECTIVE

Electrocorticography (ECoG) signals have emerged as a potential control signal for brain-computer interface (BCI) applications due to balancing signal quality and implant invasiveness. While there have been numerous demonstrations in which ECoG signals were used to decode motor movements and to develop BCI systems, the extent of information that can be decoded has been uncertain. Therefore, we sought to determine if ECoG signals could be used to decode kinematics (speed, velocity, and position) of arm movements in 3D space.

APPROACH

To investigate this, we designed a 3D center-out reaching task that was performed by five epileptic patients undergoing temporary placement of ECoG arrays. We used the ECoG signals within a hierarchical partial-least squares (PLS) regression model to perform offline prediction of hand speed, velocity, and position.

MAIN RESULTS

The hierarchical PLS regression model enabled us to predict hand speed, velocity, and position during 3D reaching movements from held-out test sets with accuracies above chance in each patient with mean correlation coefficients between 0.31 and 0.80 for speed, 0.27 and 0.54 for velocity, and 0.22 and 0.57 for position. While beta band power changes were the most significant features within the model used to classify movement and rest, the local motor potential and high gamma band power changes, were the most important features in the prediction of kinematic parameters.

SIGNIFICANCE

We believe that this study represents the first demonstration that truly three-dimensional movements can be predicted from ECoG recordings in human patients. Furthermore, this prediction underscores the potential to develop BCI systems with multiple degrees of freedom in human patients using ECoG.

Analyzing EEG signals to detect unexpected obstacles during walking

Background

When an unexpected perturbation in the environment occurs, the subsequent alertness state may cause a brain activation responding to that perturbation which can be detected and employed by a Brain-Computer Interface (BCI). In this work, the possibility of detecting a sudden obstacle appearance analyzing electroencephalographic (EEG) signals is assessed. For this purpose, different features of EEG signals are evaluated during the appearance of sudden obstacles while a subject is walking on a treadmill. The future goal is to use this procedure to detect any obstacle appearance during walking when the user is wearing a lower limb exoskeleton in order to generate an emergency stop command for the exoskeleton. This would enhance the user-exoskeleton interaction, improving the safety mechanisms of current exoskeletons.

Methods

In order to detect the change in the brain activity when an obstacle suddenly appears, different features of EEG signals are evaluated using the recordings of five healthy subjects. Since the change in the brain activity occurs in the time domain, the features evaluated are: common spatial patterns, average power, slope, and the coefficients of a polynomial fit. A Linear Discriminant Analysis-based classifier is used to differentiate between two conditions: the appearance or not of an obstacle. The evaluation of the performance to detect the obstacles is made in terms of accuracy, true positive (TP) and false positive (FP) rates.

Results

From the offline analysis, the best performance is achieved when the slope or the polynomial coefficients are used as features, with average detection accuracy rates of 74.0 and 79.5 %, respectively. These results are consistent with the pseudo-online results, where a complete EEG recording is segmented into windows of 500 ms and overlapped 400 ms, and a decision about the obstacle appearance is made for each window. The results of the best subject were 11 out of 14 obstacles detected with a rate of 9.09 FPs/min, and 10 out of 14 obstacles detected with a rate of 6.34 FPs/min using slope and polynomial coefficients features, respectively.

Conclusions

An EEG-based BCI can be developed to detect the appearance of unexpected obstacles. The average accuracy achieved is 79.5 % of success rate with a low number of false detections. Thus, the online performance of the BCI would be suitable for commanding in a safely way a lower limb exoskeleton during walking.

A subject-independent pattern-based Brain-Computer Interface

While earlier Brain-Computer Interface (BCI) studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG) signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs) from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30% was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e., happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to “match” their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.

Detection of attempted movement from the EEG during neuromuscular block: proof of principle study in awake volunteers

Brain-Computer Interfaces (BCIs) have the potential to detect intraoperative awareness during general anaesthesia. Traditionally, BCI research is aimed at establishing or improving communication and control for patients with permanent paralysis. Patients experiencing intraoperative awareness also lack the means to communicate after administration of a neuromuscular blocker, but may attempt to move. This study evaluates the principle of detecting attempted movements from the electroencephalogram (EEG) during local temporary neuromuscular blockade. EEG was obtained from four healthy volunteers making 3-second hand movements, both before and after local administration of rocuronium in one isolated forearm. Using offline classification analysis we investigated whether the attempted movements the participants made during paralysis could be distinguished from the periods when they did not move or attempt to move. Attempted movement trials were correctly identified in 81 (68-94)% (mean (95% CI)) and 84 (74-93)% of the cases using 30 and 9 EEG channels, respectively. Similar accuracies were obtained when training the classifier on the participants' actual movements. These results provide proof of the principle that a BCI can detect movement attempts during neuromuscular blockade. Based on this, in the future a BCI may serve as a communication channel between a patient under general anaesthesia and the anaesthesiologist.

Improving the performance of an EEG-based motor imagery brain computer interface using task evoked changes in pupil diameter

For individuals with high degrees of motor disability or locked-in syndrome, it is impractical or impossible to use mechanical switches to interact with electronic devices. Brain computer interfaces (BCIs) can use motor imagery to detect interaction intention from users but lack the accuracy of mechanical switches. Hence, there exists a strong need to improve the accuracy of EEG-based motor imagery BCIs attempting to implement an on/off switch. Here, we investigate how monitoring the pupil diameter of a person as a psycho-physiological parameter in addition to traditional EEG channels can improve the classification accuracy of a switch-like BCI. We have recently noticed in our lab (work not yet published) how motor imagery is associated with increases in pupil diameter when compared to a control rest condition. The pupil diameter parameter is easily accessible through video oculography since most gaze tracking systems report pupil diameter invariant to head position. We performed a user study with 30 participants using a typical EEG based motor imagery BCI. We used common spatial patterns to separate motor imagery, signaling movement intention, from a rest control condition. By monitoring the pupil diameter of the user and using this parameter as an additional feature, we show that the performance of the classifier trying to discriminate motor imagery from a control condition improves over the traditional approach using just EEG derived features. Given the limitations of EEG to construct highly robust and reliable BCIs, we postulate that multi-modal approaches, such as the one presented here that monitor several psycho-physiological parameters, can be a successful strategy in making BCIs more accurate and less vulnerable to constraints such as requirements for long training sessions or high signal to noise ratio of electrode channels.

Non-invasive single-trial EEG detection of evoked human neocortical population spikes

QUESTION

Human high-frequency (>400 Hz) components of somatosensory evoked potentials (hf-SEPs), which can be recorded non-invasively at the scalp, are generated by cortical population spikes, as inferred from microelectrode recordings in non-human primates. It is a critical limitation to broader neurophysiological study of hf-SEPs in that hundreds of responses have to be averaged to detect hf-SEPs reliably. Here, we establish a framework for detecting human hf-SEPs non-invasively in single trials.

METHODS

Spatio-temporal features were extracted from band-pass filtered (400-900 Hz) hf-SEPs by bilinear Common Spatio-Temporal Patterns (bCSTP) and then classified by a weighted Extreme Learning Machine (w-ELM). The effect of varying signal-to-noise ratio (SNR), number of trials, and degree of w-ELM re-weighting was characterized using surrogate data. For practical demonstration of the algorithm, median nerve hf-SEPs were recorded inside a shielded room in four subjects, spanning the hf-SEP signal-to-noise ratio characteristic for a larger population, utilizing a custom-built 29-channel low-noise EEG amplifier.

RESULTS

Using surrogate data, the SNR proved to be pivotal to detect hf-SEPs in single trials efficiently, with the trade-off between sensitivity and specificity of the algorithm being obtained by the w-ELM re-weighting parameter. In practice, human hf-SEPs were detected non-invasively in single trials with a sensitivity of up to 99% and a specificity of up to 97% in two subjects, even without any recourse to knowledge of stimulus timing. Matching with the results of the surrogate data analysis, these rates dropped to 62-79% sensitivity and 18-31% specificity in two subjects with lower SNR.

CONCLUSIONS

Otherwise buried in background noise, human high-frequency EEG components can be extracted from low-noise recordings. Specifically, refined supervised filter optimization and classification enables the reliable detection of single-trial hf-SEPs, representing non-invasive correlates of cortical population spikes.

SIGNIFICANCE

While low-frequency EEG reflects summed postsynaptic potentials, and thereby neuronal input, we suggest that high-frequency EEG (>400 Hz) can provide non-invasive access to the unaveraged output of neuronal computation, i.e., single-trial population spike activity evoked in the responsive neuronal ensemble.

Adaptation of motor imagery EEG classification model based on tensor decomposition

OBJECTIVE

Session-to-session nonstationarity is inherent in brain-computer interfaces based on electroencephalography. The objective of this paper is to quantify the mismatch between the training model and test data caused by nonstationarity and to adapt the model towards minimizing the mismatch.

APPROACH

We employ a tensor model to estimate the mismatch in a semi-supervised manner, and the estimate is regularized in the discriminative objective function.

MAIN RESULTS

The performance of the proposed adaptation method was evaluated on a dataset recorded from 16 subjects performing motor imagery tasks on different days. The classification results validated the advantage of the proposed method in comparison with other regularization-based or spatial filter adaptation approaches. Experimental results also showed that there is a significant correlation between the quantified mismatch and the classification accuracy.

SIGNIFICANCE

The proposed method approached the nonstationarity issue from the perspective of data-model mismatch, which is more direct than data variation measurement. The results also demonstrated that the proposed method is effective in enhancing the performance of the feature extraction model.

GOM-Face: GKP, EOG, and EMG-based multimodal interface with application to humanoid robot control

We present a novel human-machine interface, called GOM-Face , and its application to humanoid robot control. The GOM-Face bases its interfacing on three electric potentials measured on the face: 1) glossokinetic potential (GKP), which involves the tongue movement; 2) electrooculogram (EOG), which involves the eye movement; 3) electromyogram, which involves the teeth clenching. Each potential has been individually used for assistive interfacing to provide persons with limb motor disabilities or even complete quadriplegia an alternative communication channel. However, to the best of our knowledge, GOM-Face is the first interface that exploits all these potentials together. We resolved the interference between GKP and EOG by extracting discriminative features from two covariance matrices: a tongue-movement-only data matrix and eye-movement-only data matrix. With the feature extraction method, GOM-Face can detect four kinds of horizontal tongue or eye movements with an accuracy of 86.7% within 2.77 s. We demonstrated the applicability of the GOM-Face to humanoid robot control: users were able to communicate with the robot by selecting from a predefined menu using the eye and tongue movements.

Recording human cortical population spikes non-invasively--An EEG tutorial

BACKGROUND

Non-invasively recorded somatosensory high-frequency oscillations (sHFOs) evoked by electric nerve stimulation are markers of human cortical population spikes. Previously, their analysis was based on massive averaging of EEG responses. Advanced neurotechnology and optimized off-line analysis can enhance the signal-to-noise ratio of sHFOs, eventually enabling single-trial analysis.

METHODS

The rationale for developing dedicated low-noise EEG technology for sHFOs is unfolded. Detailed recording procedures and tailored analysis principles are explained step-by-step. Source codes in Matlab and Python are provided as supplementary material online.

RESULTS

Combining synergistic hardware and analysis improvements, evoked sHFOs at around 600 Hz ('σ-bursts') can be studied in single-trials. Additionally, optimized spatial filters increase the signal-to-noise ratio of components at about 1 kHz ('κ-bursts') enabling their detection in non-invasive surface EEG.

CONCLUSIONS

sHFOs offer a unique possibility to record evoked human cortical population spikes non-invasively. The experimental approaches and algorithms presented here enable also non-specialized EEG laboratories to combine measurements of conventional low-frequency EEG with the analysis of concomitant cortical population spike responses.

Bayesian common spatial patterns for multi-subject EEG classification

Multi-subject electroencephalography (EEG) classification involves algorithm development for automatically categorizing brain waves measured from multiple subjects who undergo the same mental task. Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for EEG classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is neglected. In the case of multi-subject EEG classification, however, it is desirable to capture inter-subject relatedness in learning a model. In this paper we present a nonparametric Bayesian model for a multi-subject extension of PCSP where subject relatedness is captured by assuming that spatial patterns across subjects share a latent subspace. Spatial patterns and the shared latent subspace are jointly learned by variational inference. We use an infinite latent feature model to automatically infer the dimension of the shared latent subspace, placing Indian Buffet process (IBP) priors on our model. Numerical experiments on BCI competition III IVa and IV 2a dataset demonstrate the high performance of our method, compared to PCSP and existing Bayesian multi-task CSP models.

An automated and fast approach to detect single-trial visual evoked potentials with application to brain-computer interface

OBJECTIVE

This study aims (1) to develop an automated and fast approach for detecting visual evoked potentials (VEPs) in single trials and (2) to apply the single-trial VEP detection approach in designing a real-time and high-performance brain-computer interface (BCI) system.

METHODS

The single-trial VEP detection approach uses common spatial pattern (CSP) as a spatial filter and wavelet filtering (WF) a temporal-spectral filter to jointly enhance the signal-to-noise ratio (SNR) of single-trial VEPs. The performance of the joint spatial-temporal-spectral filtering approach was assessed in a four-command VEP-based BCI system.

RESULTS

The offline classification accuracy of the BCI system was significantly improved from 67.6±12.5% (raw data) to 97.3±2.1% (data filtered by CSP and WF). The proposed approach was successfully implemented in an online BCI system, where subjects could make 20 decisions in one minute with classification accuracy of 90%.

CONCLUSIONS

The proposed single-trial detection approach is able to obtain robust and reliable VEP waveform in an automatic and fast way and it is applicable in VEP based online BCI systems.

SIGNIFICANCE

This approach provides a real-time and automated solution for single-trial detection of evoked potentials or event-related potentials (EPs/ERPs) in various paradigms, which could benefit many applications such as BCI and intraoperative monitoring.

On the quantification of SSVEP frequency responses in human EEG in realistic BCI conditions

This article concerns one of the most important problems of brain-computer interfaces (BCI) based on Steady State Visual Evoked Potentials (SSVEP), that is the selection of the a-priori most suitable frequencies for stimulation. Previous works related to this problem were done either with measuring systems that have little in common with actual BCI systems (e.g., single flashing LED) or were presented on a small number of subjects, or the tested frequency range did not cover a broad spectrum. Their results indicate a strong SSVEP response around 10 Hz, in the range 13–25 Hz, and at high frequencies in the band of 40–60 Hz. In the case of BCI interfaces, stimulation with frequencies from various ranges are used. The frequencies are often adapted for each user separately. The selection of these frequencies, however, was not yet justified in quantitative group-level study with proper statistical account for inter-subject variability. The aim of this study is to determine the SSVEP response curve, that is, the magnitude of the evoked signal as a function of frequency. The SSVEP response was induced in conditions as close as possible to the actual BCI system, using a wide range of frequencies (5–30 Hz, in step of 1 Hz). The data were obtained for 10 subjects. SSVEP curves for individual subjects and the population curve was determined. Statistical analysis were conducted both on the level of individual subjects and for the group. The main result of the study is the identification of the optimal range of frequencies, which is 12–18 Hz, for the registration of SSVEP phenomena. The applied criterion of optimality was: to find the largest contiguous range of frequencies yielding the strong and constant-level SSVEP response.

Reducing multi-sensor data to a single time course that reveals experimental effects

Background

Multi-sensor technologies such as EEG, MEG, and ECoG result in high-dimensional data sets. Given the high temporal resolution of such techniques, scientific questions very often focus on the time-course of an experimental effect. In many studies, researchers focus on a single sensor or the average over a subset of sensors covering a “region of interest” (ROI). However, single-sensor or ROI analyses ignore the fact that the spatial focus of activity is constantly changing, and fail to make full use of the information distributed over the sensor array.

Methods

We describe a technique that exploits the optimality and simplicity of matched spatial filters in order to reduce experimental effects in multivariate time series data to a single time course. Each (multi-sensor) time sample of each trial is replaced with its projection onto a spatial filter that is matched to an observed experimental effect, estimated from the remaining trials (Effect-Matched Spatial filtering, or EMS filtering). The resulting set of time courses (one per trial) can be used to reveal the temporal evolution of an experimental effect, which distinguishes this approach from techniques that reveal the temporal evolution of an anatomical source or region of interest.

Results

We illustrate the technique with data from a dual-task experiment and use it to track the temporal evolution of brain activity during the psychological refractory period. We demonstrate its effectiveness in separating the means of two experimental conditions, and in significantly improving the signal-to-noise ratio at the single-trial level. It is fast to compute and results in readily-interpretable time courses and topographies. The technique can be applied to any data-analysis question that can be posed independently at each sensor, and we provide one example, using linear regression, that highlights the versatility of the technique.

Conclusion

The approach described here combines established techniques in a way that strikes a balance between power, simplicity, speed of processing, and interpretability. We have used it to provide a direct view of parallel and serial processes in the human brain that previously could only be measured indirectly. An implementation of the technique in MatLab is freely available via the internet.

Discriminative Learning of Propagation and Spatial Pattern for Motor Imagery EEG Analysis

Effective learning and recovery of relevant source brain activity patterns is a major challenge to brain-computer interface using scalp EEG. Various spatial filtering solutions have been developed. Most current methods estimate an instantaneous demixing with the assumption of uncorrelatedness of the source signals. However, recent evidence in neuroscience suggests that multiple brain regions cooperate, especially during motor imagery, a major modality of brain activity for brain-computer interface. In this sense, methods that assume uncorrelatedness of the sources become inaccurate. Therefore, we are promoting a new methodology that considers both volume conduction effect and signal propagation between multiple brain regions. Specifically, we propose a novel discriminative algorithm for joint learning of propagation and spatial pattern with an iterative optimization solution. To validate the new methodology, we conduct experiments involving 16 healthy subjects and perform numerical analysis of the proposed algorithm for EEG classification in motor imagery brain-computer interface. Results from extensive analysis validate the effectiveness of the new methodology with high statistical significance.

Approximation-based common principal component for feature extraction in multi-class brain-computer interfaces

Common Spatial Pattern (CSP) is a state-of-the-art method for feature extraction in Brain-Computer Interface (BCI) systems. However it is designed for 2-class BCI classification problems. Current extensions of this method to multiple classes based on subspace union and covariance matrix similarity do not provide a high performance. This paper presents a new approach to solving multi-class BCI classification problems by forming a subspace resembled from original subspaces and the proposed method for this approach is called Approximation-based Common Principal Component (ACPC). We perform experiments on Dataset 2a used in BCI Competition IV to evaluate the proposed method. This dataset was designed for motor imagery classification with 4 classes. Preliminary experiments show that the proposed ACPC feature extraction method when combining with Support Vector Machines outperforms CSP-based feature extraction methods on the experimental dataset.

EEG signal classification using time-varying autoregressive models and common spatial patterns

The performance of EEG signal classification methods based on Common Spatial Patterns (CSP) depends on the operational frequency bands of the events to be discriminated. This problem has been recently addressed by using a sub-band decomposition of the EEG signals through filter banks. Even though this approach has proven effective, the performance still depends on the number of filters that are stacked and the criteria used to determine their cutoff frequencies. Therefore, we propose an alternative approach based on an eigenstructure decomposition of the signals' time-varying autoregressive (TVAR) models. The eigen-based decomposition of the TVAR representation allows for subject-specific estimation of the principal time-varying frequencies, then such principal eigencomponents can be used in the traditional CSP-based classification. A series of simulations show that the proposed classification scheme can achieve high classification rates under realistic conditions, such as low signal-to-noise ratio (SNR), a reduced number of training experiments, and a reduced number of sensors used in the measurements.

The analytic common spatial patterns method for EEG-based BCI data

One of the most important stages in a brain-computer interface (BCI) system is that of extracting features that can reliably discriminate data recorded during different user states. A popular technique used for feature extraction in BCIs is the common spatial patterns (CSP) method, which provides a set of spatial filters that optimally discriminate between two classes of data in the least-squares sense. The method also yields a set of spatial patterns that are associated with the most relevant activity for distinguishing between the two classes. The high recognition rates that have been achieved with the method have led to its widespread adoption in the field. Here, a variant of the CSP method that considers EEG data in its complex form is described. By explicitly considering the amplitude and phase information in the data, the analytic CSP (ACSP) technique can provide a more comprehensive picture of the underlying activity, resulting in improved classification accuracies and more informative spatial patterns than the conventional CSP method. In this paper, we elaborate on the theoretical aspects of the ACSP algorithm and demonstrate the advantages of the method through a number of simulations and through tests on EEG data.

Review of the BCI Competition IV

The BCI competition IV stands in the tradition of prior BCI competitions that aim to provide high quality neuroscientific data for open access to the scientific community. As experienced already in prior competitions not only scientists from the narrow field of BCI compete, but scholars with a broad variety of backgrounds and nationalities. They include high specialists as well as students. The goals of all BCI competitions have always been to challenge with respect to novel paradigms and complex data. We report on the following challenges: (1) asynchronous data, (2) synthetic, (3) multi-class continuous data, (4) session-to-session transfer, (5) directionally modulated MEG, (6) finger movements recorded by ECoG. As after past competitions, our hope is that winning entries may enhance the analysis methods of future BCIs.

Separation of stationary and non-stationary sources with a generalized eigenvalue problem

Non-stationary effects are ubiquitous in real world data. In many settings, the observed signals are a mixture of underlying stationary and non-stationary sources that cannot be measured directly. For example, in EEG analysis, electrodes on the scalp record the activity from several sources located inside the brain, which one could only measure invasively. Discerning stationary and non-stationary contributions is an important step towards uncovering the mechanisms of the data generating system. To that end, in Stationary Subspace Analysis (SSA), the observed signal is modeled as a linear superposition of stationary and non-stationary sources, where the aim is to separate the two groups in the mixture. In this paper, we propose the first SSA algorithm that has a closed form solution. The novel method, Analytic SSA (ASSA), is more than 100 times faster than the state-of-the-art, numerically stable, and guaranteed to be optimal when the covariance between stationary and non-stationary sources is time-constant. In numerical simulations on wide range of settings, we show that our method yields superior results, even for signals with time-varying group-wise covariance. In an application to geophysical data analysis, ASSA extracts meaningful components that shed new light on the Pi 2 pulsations of the geomagnetic field.

Cross-frequency decomposition: a novel technique for studying interactions between neuronal oscillations with different frequencies

OBJECTIVE

We present a novel method for the extraction of neuronal components showing cross-frequency phase synchronization.

METHODS

In general the method can be applied for the detection of phase interactions between components with frequencies f1 and f2, where f2 ≈ rf1 and r is some integer. We refer to the method as cross-frequency decomposition (CFD), which consists of the following steps: (a) extraction of f1-oscillations with the spatio-spectral decomposition algorithm (SSD); (b) frequency modification of the f1-oscillations obtained with SSD; and (c) finding f2-oscillations synchronous with f1-oscillations using least-squares estimation.

RESULTS

Our simulations showed that CFD was capable of recovering interacting components even when the signal-to-noise ratio was as low as 0.01. An application of CFD to the real EEG data demonstrated that cross-frequency phase synchronization between alpha and beta oscillations can originate from the same or remote neuronal populations.

CONCLUSIONS

CFD allows a compact representation of the sets of interacting components. The application of CFD to EEG data allows differentiating cross-frequency synchronization arising due to genuine neurophysiological interactions from interactions occurring due to quasi-sinusoidal waveform of neuronal oscillations.

SIGNIFICANCE

CFD is a method capable of extracting cross-frequency coupled neuronal oscillations even in the presence of strong noise.

Multisubject learning for common spatial patterns in motor-imagery BCI

Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern filter (CSP) as preprocessing step before feature extraction and classification. The CSP method is a supervised algorithm and therefore needs subject-specific training data for calibration, which is very time consuming to collect. In order to reduce the amount of calibration data that is needed for a new subject, one can apply multitask (from now on called multisubject) machine learning techniques to the preprocessing phase. Here, the goal of multisubject learning is to learn a spatial filter for a new subject based on its own data and that of other subjects. This paper outlines the details of the multitask CSP algorithm and shows results on two data sets. In certain subjects a clear improvement can be seen, especially when the number of training trials is relatively low.

Adaptive training session for a P300 speller brain-computer interface

With a brain-computer interface (BCI), it is nowadays possible to achieve a direct pathway between the brain and computers thanks to the analysis of some particular brain activities. The detection of even-related potentials, like the P300 in the oddball paradigm exploited in P300-speller, provides a way to create BCIs by assigning several detected ERP to a command. Due to the noise present in the electroencephalographic signal, the detection of an ERP and its different components requires efficient signal processing and machine learning techniques. As a consequence, a calibration session is needed for training the models, which can be a drawback if its duration is too long. Although the model depends on the subject, the goal is to provide a reliable model for the P300 detection over time. In this study, we propose a new method to evaluate the optimal number of symbols (i.e. the number of ERP that shall be detected given a determined target probability) that should be spelt during the calibration process. The goal is to provide a usable system with a minimum calibration duration and such that it can automatically switch between the training and online sessions. The method allows to adaptively adjust the number of training symbols to each subject. The evaluation has been tested on data recorded on 20 healthy subjects. This procedure lets drastically reduced the calibration session: height symbols during the training session reach an initialized system with an average accuracy of 80% after five epochs.

A subject-independent brain-computer interface based on smoothed, second-order baselining

A brain-computer interface (BCI) enables direct communication from the brain to devices, bypassing the traditional pathway of peripheral nerves and muscles. Traditional approaches to BCIs require the user to train for weeks or even months to learn to control the BCI. In contrast, BCIs based on machine learning only require a calibration session of less than an hour before the system can be used, since the machine adapts to the user's existing brain signals. However, this calibration session has to be repeated before each use of the BCI due to inter-session variability, which makes using a BCI still a time-consuming and an error-prone enterprise. In this work, we present a second-order baselining procedure that reduces these variations, and enables the creation of a BCI that can be applied to new subjects without such a calibration session. The method was validated with a motor-imagery classification task performed by 109 subjects. Results showed that our subject-independent BCI without calibration performs as well as the popular common spatial patterns (CSP)-based BCI that does use a calibration session.

Low cost electroencephalographic acquisition amplifier to serve as teaching and research tool

We described the development and testing of a low cost, easily constructed electroencephalographic (EEG) acquisition amplifier for noninvasive Brain Computer Interface (BCI) education and research. The acquisition amplifier was constructed from newly available off-the-shelf integrated circuit components, and readily sends a 24-bit data stream via USB (Universal Serial Bus) to a computer platform. We demonstrate here the hardware's use in the analysis of a visually evoked P300 paradigm for a choose one-of-eight task. This clearly shows the applicability of this system as a low cost teaching and research tool.