Finding stationary brain sources in EEG data

Sleep Spindle-Related EEG Connectivity in Children with Attention-Deficit/Hyperactivity Disorder: An Exploratory Study

Attention-deficit/hyperactivity disorder (ADHD) is a neurobehavioral disorder with known brain abnormalities but no biomarkers to support clinical diagnosis. Recently, EEG analysis methods such as functional connectivity have rekindled interest in using EEG for ADHD diagnosis. Most studies have focused on resting-state EEG, while connectivity during sleep and spindle activity has been underexplored. Here we present the results of a preliminary study exploring spindle-related connectivity as a possible biomarker for ADHD. We compared sensor-space connectivity parameters in eight children with ADHD and nine age/sex-matched healthy controls during sleep, before, during, and after spindle activity in various frequency bands. All connectivity parameters were significantly different between the two groups in the delta and gamma bands, and Principal Component Analysis (PCA) in the gamma band distinguished ADHD from healthy subjects. Cluster coefficient and path length values in the sigma band were also significantly different between epochs, indicating different spindle-related brain activity in ADHD.

Similarity-Based Adaptive Window for Improving Classification of Epileptic Seizures with Imbalance EEG Data Stream

Data stream mining techniques have recently received increasing research interest, especially in medical data classification. An unbalanced representation of the classification's targets in these data is a common challenge because classification techniques are biased toward the major class. Many methods have attempted to address this problem but have been exaggeratedly biased toward the minor class. In this work, we propose a method for balancing the presence of the minor class within the current window of the data stream while preserving the data's original majority as much as possible. The proposed method utilized similarity analysis for selecting specific instances from the previous window. This group of minor-class was then added to the current window's instances. Implementing the proposed method using the Siena dataset showed promising results compared to the Skew ensemble method and some other research methods.

IC-U-Net: A U-Net-based Denoising Autoencoder Using Mixtures of Independent Components for Automatic EEG Artifact Removal

Electroencephalography (EEG) signals are often contaminated with artifacts. It is imperative to develop a practical and reliable artifact removal method to prevent the misinterpretation of neural signals and the underperformance of brain-computer interfaces. Based on the U-Net architecture, we developed a new artifact removal model, IC-U-Net, for removing pervasive EEG artifacts and reconstructing brain signals. IC-U-Net was trained using mixtures of brain and non-brain components decomposed by independent component analysis. It uses an ensemble of loss functions to model complex signal fluctuations in EEG recordings. The effectiveness of the proposed method in recovering brain activities and removing various artifacts (e.g., eye blinks/movements, muscle activities, and line/channel noise) was demonstrated in a simulation study and four real-world EEG experiments. IC-U-Net can reconstruct a multi-channel EEG signal and is applicable to most artifact types, offering a promising end-to-end solution for automatically removing artifacts from EEG recordings. It also meets the increasing need to image natural brain dynamics in a mobile setting. The code and pre-trained IC-U-Net model are available at https://github.com/roseDwayane/AIEEG.

Channel selection from source localization: A review of four EEG-based brain-computer interfaces paradigms

Channel selection is a critical part of the classification procedure for multichannel electroencephalogram (EEG)-based brain-computer interfaces (BCI). An optimized subset of electrodes reduces computational complexity and optimizes accuracy. Different tasks activate different sources in the brain and are characterized by distinctive channels. The goal of the current review is to define a subset of electrodes for each of four popular BCI paradigms: motor imagery, motor execution, steady-state visual evoked potentials and P300. Twenty-one studies have been reviewed to identify the most significant activations of cortical sources. The relevant EEG sensors are determined from the reported 3D Talairach coordinates. They are scored by their weighted mean Cohen's d and its confidence interval, providing the magnitude of the corresponding effect size and its statistical significance. Our goal is to create a knowledge-based channel selection framework with a sufficient statistical power. The core channel selection (CCS) could be used as a reference by EEG researchers and would have the advantages of practicality and rapidity, allowing for an easy implementation of semiparametric algorithms.

Embedding decomposition for artifacts removal in EEG signals

Electroencephalogram (EEG) recordings are often contaminated with artifacts. Various methods have been developed to eliminate or weaken the influence of artifacts. However, most of them rely on prior experience for analysis. Here, we propose an deep learning framework to separate neural signal and artifacts in the embedding space and reconstruct the denoised signal, which is called DeepSeparator. DeepSeparator employs an encoder to extract and amplify the features in the raw EEG, a module called decomposer to extract the trend, detect and suppress artifact and a decoder to reconstruct the denoised signal. Besides, DeepSeparator can extract the artifact, which largely increases the model interpretability. The proposed method is tested with a semi-synthetic EEG dataset and a real task-related EEG dataset, suggesting that DeepSeparator outperforms the conventional models in both EOG and EMG artifact removal. DeepSeparator can be extended to multi-channel EEG and data with any arbitrary length. It may motivate future developments and application of deep learning-based EEG denoising. The code for DeepSeparator is available at https://github.com/ncclabsustech/DeepSeparator.

Imaginary Finger Movements Decoding Using Empirical Mode Decomposition and a Stacked BiLSTM Architecture

Motor Imagery Electroencephalogram (MI-EEG) signals are widely used in Brain-Computer Interfaces (BCI). MI-EEG signals of large limbs movements have been explored in recent researches because they deliver relevant classification rates for BCI systems. However, smaller and noisy signals corresponding to hand-finger imagined movements are less frequently used because they are difficult to classify. This study proposes a method for decoding finger imagined movements of the right hand. For this purpose, MI-EEG signals from C3, Cz, P3, and Pz sensors were carefully selected to be processed in the proposed framework. Therefore, a method based on Empirical Mode Decomposition (EMD) is used to tackle the problem of noisy signals. At the same time, the sequence classification is performed by a stacked Bidirectional Long Short-Term Memory (BiLSTM) network. The proposed method was evaluated using k-fold cross-validation on a public dataset, obtaining an accuracy of 82.26%.

A Survey on EEG Signal Processing Techniques and Machine Learning: Applications to the Neurofeedback of Autobiographical Memory Deficits in Schizophrenia

In this paper, a general overview regarding neural recording, classical signal processing techniques and machine learning classification algorithms applied to monitor brain activity is presented. Currently, several approaches classified as electrical, magnetic, neuroimaging recordings and brain stimulations are available to obtain neural activity of the human brain. Among them, non-invasive methods like electroencephalography (EEG) are commonly employed, as they can provide a high degree of temporal resolution (on the order of milliseconds) and acceptable space resolution. In addition, it is simple, quick, and does not create any physical harm or stress to patients. Concerning signal processing, once the neural signals are acquired, different procedures can be applied for feature extraction. In particular, brain signals are normally processed in time, frequency, and/or space domains. The features extracted are then used for signal classification depending on its characteristics such us the mean, variance or band power. The role of machine learning in this regard has become of key importance during the last years due to its high capacity to analyze complex amounts of data. The algorithms employed are generally classified in supervised, unsupervised and reinforcement techniques. A deep review of the most used machine learning algorithms and the advantages/drawbacks of most used methods is presented. Finally, a study of these procedures utilized in a very specific and novel research field of electroencephalography, i.e., autobiographical memory deficits in schizophrenia, is outlined.

Modeling Spectral Properties in Stationary Processes of Varying Dimensions with Applications to Brain Local Field Potential Signals

In some applications, it is important to compare the stochastic properties of two multivariate time series that have unequal dimensions. A new method is proposed to compare the spread of spectral information in two multivariate stationary processes with different dimensions. To measure discrepancies, a frequency specific spectral ratio (FS-ratio) statistic is proposed and its asymptotic properties are derived. The FS-ratio is blind to the dimension of the stationary process and captures the proportion of spectral power in various frequency bands. Here we develop a technique to automatically identify frequency bands that carry significant spectral power. We apply our method to track changes in the complexity of a 32-channel local field potential (LFP) signal from a rat following an experimentally induced stroke. At every epoch (a distinct time segment from the duration of the experiment), the nonstationary LFP signal is decomposed into stationary and nonstationary latent sources and the complexity is analyzed through these latent stationary sources and their dimensions that can change across epochs. The analysis indicates that spectral information in the Beta frequency band (12–30 Hertz) demonstrated the greatest change in structure and complexity due to the stroke.

A Unified Novel Neural Network Approach and a Prototype Hardware Implementation for Ultra-Low Power EEG Classification

This paper introduces a novel electroencephalogram (EEG) data classification scheme together with its implementation in hardware using an innovative approach. The proposed scheme integrates into a single, end-to-end trainable model a spatial filtering technique and a neural network based classifier. The spatial filters, as well as, the coefficients of the neural network classifier are simultaneously estimated during training. By using different time-locked spatial filters, we introduce for the first time the notion of "attention" in EEG processing, which allows for the efficient capturing of the temporal dependencies and/or variability of the EEG sequential data. One of the most important benefits of our approach is that the proposed classifier is able to construct highly discriminative features directly from raw EEG data and, at the same time, to exploit the function approximation properties of neural networks, in order to produce highly accurate classification results. The evaluation of the proposed methodology, using public available EEG datasets, indicates that it outperforms the standard EEG classification approach based on filtering and classification as two separated steps. Moreover, we present a prototype implementation of the proposed scheme in state-of-the-art reconfigurable hardware; our novel implementation outperforms by more than one order of magnitude, in terms of power efficiency, the conventional CPU-based approaches.

Reducing Brain Signal Noise in the Prediction of Economic Choices: A Case Study in Neuroeconomics

In order to reduce the noise of brain signals, neuroeconomic experiments typically aggregate data from hundreds of trials collected from a few individuals. This contrasts with the principle of simple and controlled designs in experimental and behavioral economics. We use a frequency domain variant of the stationary subspace analysis (SSA) technique, denoted as DSSA, to filter out the noise (nonstationary sources) in EEG brain signals. The nonstationary sources in the brain signal are associated with variations in the mental state that are unrelated to the experimental task. DSSA is a powerful tool for reducing the number of trials needed from each participant in neuroeconomic experiments and also for improving the prediction performance of an economic choice task. For a single trial, when DSSA is used as a noise reduction technique, the prediction model in a food snack choice experiment has an increase in overall accuracy by around 10% and in sensitivity and specificity by around 20% and in AUC by around 30%, respectively.

Toward an Open-Ended BCI: A User-Centered Coadaptive Design

Brain-computer interfaces (BCIs) allow users to control a device by interpreting their brain activity. For simplicity, these devices are designed to be operated by purposefully modulating specific predetermined neurophysiological signals, such as the sensorimotor rhythm. However, the ability to modulate a given neurophysiological signal is highly variable across individuals, contributing to the inconsistent performance of BCIs for different users. These differences suggest that individuals who experience poor BCI performance with one class of brain signals might have good results with another. In order to take advantage of individual abilities as they relate to BCI control, we need to move beyond the current approaches. In this letter, we explore a new BCI design aimed at a more individualized and user-focused experience, which we call open-ended BCI. Individual users were given the freedom to discover their own mental strategies as opposed to being trained to modulate a given brain signal. They then underwent multiple coadaptive training sessions with the BCI. Our first open-ended BCI performed similarly to comparable BCIs while accommodating a wider variety of mental strategies without a priori knowledge of the specific brain signals any individual might use. Post hoc analysis revealed individual differences in terms of which sensory modality yielded optimal performance. We found a large and significant effect of individual differences in background training and expertise, such as in musical training, on BCI performance. Future research should be focused on finding more generalized solutions to user training and brain state decoding methods to fully utilize the abilities of different individuals in an open-ended BCI. Accounting for each individual's areas of expertise could have important implications on BCI training and BCI application design.

Monitoring alert and drowsy states by modeling EEG source nonstationarity

OBJECTIVE

As a human brain performs various cognitive functions within ever-changing environments, states of the brain characterized by recorded brain activities such as electroencephalogram (EEG) are inevitably nonstationary. The challenges of analyzing the nonstationary EEG signals include finding neurocognitive sources that underlie different brain states and using EEG data to quantitatively assess the state changes.

APPROACH

This study hypothesizes that brain activities under different states, e.g. levels of alertness, can be modeled as distinct compositions of statistically independent sources using independent component analysis (ICA). This study presents a framework to quantitatively assess the EEG source nonstationarity and estimate levels of alertness. The framework was tested against EEG data collected from 10 subjects performing a sustained-attention task in a driving simulator.

MAIN RESULTS

Empirical results illustrate that EEG signals under alert versus drowsy states, indexed by reaction speeds to driving challenges, can be characterized by distinct ICA models. By quantifying the goodness-of-fit of each ICA model to the EEG data using the model deviation index (MDI), we found that MDIs were significantly correlated with the reaction speeds (r  =  -0.390 with alertness models and r  =  0.449 with drowsiness models) and the opposite correlations indicated that the two models accounted for sources in the alert and drowsy states, respectively. Based on the observed source nonstationarity, this study also proposes an online framework using a subject-specific ICA model trained with an initial (alert) state to track the level of alertness. For classification of alert against drowsy states, the proposed online framework achieved an averaged area-under-curve of 0.745 and compared favorably with a classic power-based approach.

SIGNIFICANCE

This ICA-based framework provides a new way to study changes of brain states and can be applied to monitoring cognitive or mental states of human operators in attention-critical settings or in passive brain-computer interfaces.

Tracking non-stationary EEG sources using adaptive online recursive independent component analysis

Electroencephalographic (EEG) source-level analyses such as independent component analysis (ICA) have uncovered features related to human cognitive functions or artifactual activities. Among these methods, Online Recursive ICA (ORICA) has been shown to achieve fast convergence in decomposing high-density EEG data for real-time applications. However, its adaptation performance has not been fully explored due to the difficulty in choosing an appropriate forgetting factor: the weight applied to new data in a recursive update which determines the trade-off between the adaptation capability and convergence quality. This study proposes an adaptive forgetting factor for ORICA (adaptive ORICA) to learn and adapt to non-stationarity in the EEG data. Using a realistically simulated non-stationary EEG dataset, we empirically show adaptive forgetting factors outperform other commonly-used non-adaptive rules when underlying source dynamics are changing. Standard offline ICA can only extract a subset of the changing sources while adaptive ORICA can recover all. Applied to actual EEG data recorded from a task-switching experiments, adaptive ORICA can learn and re-learn the task-related components as they change. With an adaptive forgetting factor, adaptive ORICA can track non-stationary EEG sources, opening many new online applications in brain-computer interfaces and in monitoring of brain dynamics.

Classifying multiple types of hand motions using electrocorticography during intraoperative awake craniotomy and seizure monitoring processes-case studies

In this work, some case studies were conducted to classify several kinds of hand motions from electrocorticography (ECoG) signals during intraoperative awake craniotomy & extraoperative seizure monitoring processes. Four subjects (P1, P2 with intractable epilepsy during seizure monitoring and P3, P4 with brain tumor during awake craniotomy) participated in the experiments. Subjects performed three types of hand motions (Grasp, Thumb-finger motion and Index-finger motion) contralateral to the motor cortex covered with ECoG electrodes. Two methods were used for signal processing. Method I: autoregressive (AR) model with burg method was applied to extract features, and additional waveform length (WL) feature has been considered, finally the linear discriminative analysis (LDA) was used as the classifier. Method II: stationary subspace analysis (SSA) was applied for data preprocessing, and the common spatial pattern (CSP) was used for feature extraction before LDA decoding process. Applying method I, the three-class accuracy of P1~P4 were 90.17, 96.00, 91.77, and 92.95% respectively. For method II, the three-class accuracy of P1~P4 were 72.00, 93.17, 95.22, and 90.36% respectively. This study verified the possibility of decoding multiple hand motion types during an awake craniotomy, which is the first step toward dexterous neuroprosthetic control during surgical implantation, in order to verify the optimal placement of electrodes. The accuracy during awake craniotomy was comparable to results during seizure monitoring. This study also indicated that ECoG was a promising approach for precise identification of eloquent cortex during awake craniotomy, and might form a promising BCI system that could benefit both patients and neurosurgeons.

Robust Common Spatial Filters with a Maxmin Approach

Electroencephalographic signals are known to be nonstationary and easily affected by artifacts; therefore, their analysis requires methods that can deal with noise. In this work, we present a way to robustify the popular common spatial patterns (CSP) algorithm under a maxmin approach. In contrast to standard CSP that maximizes the variance ratio between two conditions based on a single estimate of the class covariance matrices, we propose to robustly compute spatial filters by maximizing the minimum variance ratio within a prefixed set of covariance matrices called the tolerance set. We show that this kind of maxmin optimization makes CSP robust to outliers and reduces its tendency to overfit. We also present a data-driven approach to construct a tolerance set that captures the variability of the covariance matrices over time and shows its ability to reduce the nonstationarity of the extracted features and significantly improve classification accuracy. We test the spatial filters derived with this approach and compare them to standard CSP and a state-of-the-art method on a real-world brain-computer interface (BCI) data set in which we expect substantial fluctuations caused by environmental differences. Finally we investigate the advantages and limitations of the maxmin approach with simulations.

EEG data space adaptation to reduce intersession nonstationarity in brain-computer interface

A major challenge in EEG-based brain-computer interfaces (BCIs) is the intersession nonstationarity in the EEG data that often leads to deteriorated BCI performances. To address this issue, this letter proposes a novel data space adaptation technique, EEG data space adaptation (EEG-DSA), to linearly transform the EEG data from the target space (evaluation session), such that the distribution difference to the source space (training session) is minimized. Using the Kullback-Leibler (KL) divergence criterion, we propose two versions of the EEG-DSA algorithm: the supervised version, when labeled data are available in the evaluation session, and the unsupervised version, when labeled data are not available. The performance of the proposed EEG-DSA algorithm is evaluated on the publicly available BCI Competition IV data set IIa and a data set recorded from 16 subjects performing motor imagery tasks on different days. The results show that the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the results without adaptation in terms of classification accuracy. The results also show that for subjects with poor BCI performances when no adaptation is applied, the proposed EEG-DSA algorithm in both the supervised and unsupervised versions significantly outperforms the unsupervised bias adaptation algorithm (PMean).

Optimizing spatial filters by minimizing within-class dissimilarities in electroencephalogram-based brain-computer interface

A major challenge in electroencephalogram (EEG)-based brain-computer interfaces (BCIs) is the inherent nonstationarities in the EEG data. Variations of the signal properties from intra and inter sessions often lead to deteriorated BCI performances, as features extracted by methods such as common spatial patterns (CSP) are not invariant against the changes. To extract features that are robust and invariant, this paper proposes a novel spatial filtering algorithm called Kullback-Leibler (KL) CSP. The CSP algorithm only considers the discrimination between the means of the classes, but does not consider within-class scatters information. In contrast, the proposed KLCSP algorithm simultaneously maximizes the discrimination between the class means, and minimizes the within-class dissimilarities measured by a loss function based on the KL divergence. The performance of the proposed KLCSP algorithm is compared against two existing algorithms, CSP and stationary CSP (sCSP), using the publicly available BCI competition III dataset IVa and a large dataset from stroke patients performing neuro-rehabilitation. The results show that the proposed KLCSP algorithm significantly outperforms both the CSP and the sCSP algorithms, in terms of classification accuracy, by reducing within-class variations. This results in more compact and separable features.

Adaptive Classification on Brain-Computer Interfaces Using Reinforcement Signals

We introduce a probabilistic model that combines a classifier with an extra reinforcement signal (RS) encoding the probability of an erroneous feedback being delivered by the classifier. This representation computes the class probabilities given the task related features and the reinforcement signal. Using expectation maximization (EM) to estimate the parameter values under such a model shows that some existing adaptive classifiers are particular cases of such an EM algorithm. Further, we present a new algorithm for adaptive classification, which we call constrained means adaptive classifier, and show using EEG data and simulated RS that this classifier is able to significantly outperform state-of-the-art adaptive classifiers.

Toward a direct measure of video quality perception using EEG

An approach to the direct measurement of perception of video quality change using electroencephalography (EEG) is presented. Subjects viewed 8-s video clips while their brain activity was registered using EEG. The video signal was either uncompressed at full length or changed from uncompressed to a lower quality level at a random time point. The distortions were introduced by a hybrid video codec. Subjects had to indicate whether they had perceived a quality change. In response to a quality change, a positive voltage change in EEG (the so-called P3 component) was observed at latency of about 400-600 ms for all subjects. The voltage change positively correlated with the magnitude of the video quality change, substantiating the P3 component as a graded neural index of the perception of video quality change within the presented paradigm. By applying machine learning techniques, we could classify on a single-trial basis whether a subject perceived a quality change. Interestingly, some video clips wherein changes were missed (i.e., not reported) by the subject were classified as quality changes, suggesting that the brain detected a change, although the subject did not press a button. In conclusion, abrupt changes of video quality give rise to specific components in the EEG that can be detected on a single-trial basis. Potentially, a neurotechnological approach to video assessment could lead to a more objective quantification of quality change detection, overcoming the limitations of subjective approaches (such as subjective bias and the requirement of an overt response). Furthermore, it allows for real-time applications wherein the brain response to a video clip is monitored while it is being viewed.

Brain-computer interfacing in discriminative and stationary subspaces

The non-stationary nature of neurophysiological measurements, e.g. EEG, makes classification of motion intentions a demanding task. Variations in the underlying brain processes often lead to significant and unexpected changes in the feature distribution resulting in decreased classification accuracy in Brain Computer Interfacing (BCI). Several methods were developed to tackle this problem by either adapting to these changes or extracting features that are invariant. Recently, a method called Stationary Subspace Analysis (SSA) was proposed and applied to BCI data. It diminishes the influence of non-stationary changes as learning and classification is performed in a stationary subspace of the data which can be extracted by SSA. In this paper we extend this method in two ways. First we propose a variant of SSA that allows to extract stationary subspaces from labeled data without disregarding class-related variations or treating class-differences as non-stationarities. Second we propose a discriminant variant of SSA that trades-off stationarity and discriminativity, thus it allows to extract stationary subspaces without losing relevant information. We show that learning in a discriminative and stationary subspace is advantageous for BCI application and outperforms the standard SSA method.