EEG Tensor Research Articles

EEG tensor decomposition delineates neurophysiological principles underlying conflict-modulated action restraint and action cancellation

Executive functions are essential for adaptive behavior. One executive function is the so-called ‘interference control’ or conflict monitoring another one is inhibitory control (i.e., action restraint and action cancelation). Recent evidence suggests an interplay of these processes, which is conceptually relevant given that newer conceptual frameworks imply that nominally different action/response control processes are explainable by a small set of cognitive and neurophysiological processes. The existence of such overarching neural principles has as yet not directly been examined. In the current study, we therefore use EEG tensor decomposition methods, to look into possible common neurophysiological signatures underlying conflict-modulated action restraint and action cancelation as mechanism underlying response inhibition. We show how conflicts differentially modulate action restraint and action cancelation processes and delineate common and distinct neural processes underlying this interplay. Concerning the spatial information modulations are similar in terms of an importance of processes reflected by parieto-occipital electrodes, suggesting that attentional selection processes play a role. Especially theta and alpha activity seem to play important roles. The data also show that tensor decomposition is sensitive to the manner of task implementation, thereby suggesting that switch probability/transitional probabilities should be taken into consideration when choosing tensor decomposition as analysis method. The study provides a blueprint of how to use tensor decomposition methods to delineate common and distinct neural mechanisms underlying action control functions using EEG data.

Multi-domain feature analysis method of MI-EEG signal based on Sparse Regularity Tensor-Train decomposition

Tensor analysis can comprehensively retain multidomain characteristics, which has been employed in EEG studies. However, existing EEG tensor has large dimension, making it difficult to extract features. Traditional Tucker decomposition and Canonical Polyadic decomposition(CP) decomposition algorithms have problems of low computational efficiency and weak capability to extract features. To solve the above problems, Tensor-Train(TT) decomposition is adopted to analyze the EEG tensor. Meanwhile, sparse regularization term can then be added to TT decomposition, resulting in a sparse regular TT decomposition (SR-TT). The SR-TT algorithm is proposed in this paper, which has higher accuracy and stronger generalization ability than state-of-the-art decomposition methods. The SR-TT algorithm was verified with BCI competition III and BCI competition IV dataset and achieved 86.38% and 85.36% classification accuracies, respectively. Meanwhile, compared with traditional tensor decomposition (Tucker and CP) method, the computational efficiency of the proposed algorithm was improved by 16.49 and 31.08 times in BCI competition III and 20.72 and 29.45 times more efficient in BCI competition IV. Besides, the method can leverage tensor decomposition to extract spatial features, and the analysis is performed by pairs of brain topography visualizations to show the changes of active brain regions under the task condition. In conclusion, the proposed SR-TT algorithm in the paper provides a novel insight for tensor EEG analysis.

Cross-Task Mental Workload Recognition Based on EEG Tensor Representation and Transfer Learning.

The accurate evaluation of mental workload of operators in human machine systems is of great significance in ensuring the safety of operators and the correct execution of tasks. However, the effectiveness of EEG based cross-task mental workload evaluation are still unsatisfactory because of the different EEG response patterns in different tasks, which hindered its generalization in real scenario severely. To solve this problem, this paper proposed a feature construction method based on EEG tensor representation and transfer learning, which was verified in various task conditions. Specifically, four working memory load tasks with different types of information were designed firstly. The EEG signals of participants were collected synchronously during task execution. Then, the wavelet transform method was used to perform time-frequency analysis of multi-channel EEG signals, and three-way EEG tensor (time-frequency-channel) features were constructed. EEG tensor features from different tasks were transferred based on the criteria of feature distribution alignment and class-wise discrimination criteria. Finally, the support vector machine was used to construct a 3-class mental workload recognition model. Results showed that compared with the classical feature extraction methods, the proposed method can achieve higher accuracy in both within-task and cross-task mental workload evaluation (91.1% for within-task and 81.3% for cross-task). These results demonstrated that the EEG tensor representation and transfer learning method is feasible and effective for cross-task mental workload evaluation, which can provide theoretical basis and application reference for future researches.

Determination of the number of components in the PARAFAC model with a nonnegative tensor structure: a simulated EEG data study

Parallel factor analysis (PARAFAC) is a powerful tool for detecting latent components in human electroencephalogram (EEG) in the time-space-frequency domain. As an essential parameter, the number of latent components should be set in advance. However, any component number selection method already proposed in the literature became a rule of thumb. Existing studies have demonstrated the methods’ performance on artificial data with a simplified structure, often not mimicking a real data character. On the other hand, the ground-truth latent structure is not always known for real-world data. With the objective to provide a comprehensive overview of component number selection methods and discuss their applicability to EEG, our study focuses on nontrivial and nonnegative simulated data structures resembling real EEG properties as closely as possible. This is achieved through an accurate head model and well-controlled cortical activation sources. By considering different noise levels and disruptions from the optimal structure, the performance of the twelve component number selection methods is closely inspected. Moreover, we validate a new approach for component number selection, which we recently proposed and applied to EEG tasks. We found that methods based on the eigenvalue analysis, variance explained, or presence of redundant components are inappropriate for component number selection in EEG tensor decomposition. On the other hand, three existing methods and the newly proposed approach produced promising results on nontrivial simulated EEG data. Nevertheless, component number selection for PARAFAC analysis of EEG is a complex yet unresolved problem, and new approaches are needed.

Research on the Difference between Environmental Music Perception and Innovation Ability Based on EEG Data.

It is of great significance to practice and explore music creation for training creative talents. Perception includes feeling and perception, and feeling is a reflection of individual attributes of objective things directly acting on sensory organs. This paper mainly has a research on the difference between environmental music perception and innovation ability based on EEG data. First, this study performed noise reduction and artifact preprocessing of EEG signals generated by subjects with different levels of consciousness subjected to musical stimulation and then performed tensor decomposition to obtain the tensor component of EEG. The time-domain components of these tensor components were analyzed together with five musical features (fluctuation centroid, fluctuation entropy, pulse clarity, key clarity, and mode), EEG tensor components related to music characteristics were analyzed, the power spectrum and the distribution of responsive brain regions were analyzed, and finally, the differences in the processing of music characteristics by different levels of consciousness were explored.

On the robustness of EEG tensor completion methods

During the acquisition of electroencephalographic (EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor (multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method (TCM). However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were designed. Firstly, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion (STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or not a completion method is useful enough to complete EEG signals.

Graph-theoretical analysis of EEG functional connectivity during balance perturbation in traumatic brain injury: A pilot study.

Traumatic brain injury (TBI) often results in balance impairment, increasing the risk of falls, and the chances of further injuries. However, the underlying neural mechanisms of postural control after TBI are not well understood. To this end, we conducted a pilot study to explore the neural mechanisms of unpredictable balance perturbations in 17 chronic TBI participants and 15 matched healthy controls (HC) using the EEG, MRI, and diffusion tensor imaging (DTI) data. As quantitative measures of the functional integration and segregation of the brain networks during the postural task, we computed the global graph‐theoretic network measures (global efficiency and modularity) of brain functional connectivity derived from source‐space EEG in different frequency bands. We observed that the TBI group showed a lower balance performance as measured by the center of pressure displacement during the task, and the Berg Balance Scale (BBS). They also showed reduced brain activation and connectivity during the balance task. Furthermore, the decrease in brain network segregation in alpha‐band from baseline to task was smaller in TBI than HC. The DTI findings revealed widespread structural damage. In terms of the neural correlates, we observed a distinct role played by different frequency bands: theta‐band modularity during the task was negatively correlated with the BBS in the TBI group; lower beta‐band network connectivity was associated with the reduction in white matter structural integrity. Our future studies will focus on how postural training will modulate the functional brain networks in TBI.

The Automatic Detection of Seizure Based on Tensor Distance And Bayesian Linear Discriminant Analysis.

Electroencephalogram (EEG) plays an important role in recording brain activity to diagnose epilepsy. However, it is not only laborious, but also not very cost effective for medical experts to manually identify the features on EEG. Therefore, automatic seizure detection in accordance with the EEG recordings is significant for the diagnosis and treatment of epilepsy. Here, a new method for detecting seizures using tensor distance (TD) is proposed. First, the time-frequency characteristics of EEG signals are obtained by wavelet transformation, and the tensor representation of EEG signals is then obtained. Tucker decomposition is used to obtain the principal components of the EEG tensor. After, the distances between different categories of EEG tensors are calculated as the EEG features. Finally, the TD features are classified through the Bayesian Linear Discriminant Analysis (Bayesian LDA) classifier. The performance of this method is measured by the sensitivity, specificity, and recognition accuracy. Results indicate 95.12% sensitivity, 97.60% specificity, 97.60% recognition accuracy, and a false detection rate of 0.76 per hour in the invasive EEG dataset, which included 566.57[Formula: see text]h of EEG recording data from 21 patients. Taken together, the results show that TD has a good detection effect for seizure classification and that this method has high computational speed and great potential for real-time diagnosis.

Extraction of Common Task Features in EEG-fMRI Data Using Coupled Tensor-Tensor Decomposition.

The fusion of simultaneously recorded EEG and fMRI data is of great value to neuroscience research due to the complementary properties of the individual modalities. Traditionally, techniques such as PCA and ICA, which rely on strong non-physiological assumptions such as orthogonality and statistical independence, have been used for this purpose. Recently, tensor decomposition techniques such as parallel factor analysis have gained more popularity in neuroimaging applications as they are able to inherently contain the multidimensionality of neuroimaging data and achieve uniqueness in decomposition without making strong assumptions. Previously, the coupled matrix-tensor decomposition (CMTD) has been applied for the fusion of the EEG and fMRI. Only recently the coupled tensor-tensor decomposition (CTTD) has been proposed. Here for the first time, we propose the use of CTTD of a 4th order EEG tensor (space, time, frequency, and participant) and 3rd order fMRI tensor (space, time, participant), coupled partially in time and participant domains, for the extraction of the task related features in both modalities. We used both the sensor-level and source-level EEG for the coupling. The phase shifted paradigm signals were incorporated as the temporal initializers of the CTTD to extract the task related features. The validation of the approach is demonstrated on simultaneous EEG-fMRI recordings from six participants performing an N-Back memory task. The EEG and fMRI tensors were coupled in 9 components out of which seven components had a high correlation (more than 0.85) with the task. The result of the fusion recapitulates the well-known attention network as being positively, and the default mode network working negatively time-locked to the memory task.

Correlated coupled matrix tensor factorization method for simultaneous EEG-fMRI data fusion

ObjectiveFusion of EEG and fMRI data provides complementary information about the brain functions. Thus, data fusion should employ all dimensions of data to both extract the shared information, and distinguish the dissimilarities of modalities. MethodIn this paper, we present a new method based on Advanced Coupled Matrix Tensor Factorization (ACMTF) method to decompose the EEG tensor and fMRI matrix. We remove the confining assumption of identical shared components in ACMTF and propose an approach to maximize the correlation between the shared components of EEG and fMRI in the common mode, while removing the smearing effect of hemodynamic response function on fMRI data. This method is called Correlated Coupled Matrix Tensor Factorization (CCMTF). ResultsTwo simulation scenarios with different noise levels are performed to evaluate the performance of the proposed CCMTF method. The simulation results show 30.1% and 23.38% average improvement of Match Scores over ACMTF and N-way Partial Least Square (N-PLS) methods, respectively. The proposed method is also applied to a real dataset of an auditory oddball paradigm. The results of real data analysis show that the proposed CCMTF method estimates the unknown number of shared components between EEG and fMRI data, with p-value less than 0.007. Conclusion and SignificanceIn addition to the improvement of match score, the simulation results demonstrate that CCMTF has higher performance than ACMTF for fusion of EEG and fMRI datasets in case of extracting the dissimilarities in modalities, and it provides more convenient interpretation of the results, in comparison to N-PLS method.

Removing the Effect of Hemodynamic Response Function in Joint Factorization of EEG and fMRI Datasets

Purpose: One of the most well-known multimodality techniques is the integration of EEG and fMRI datasets. Convolution of EEG signals with hemodynamic response function is one of the most important methods to consider the effect of HRF in the fusion of EEG and fMRI data. However, the latencies and amplitudes of ERPs and fMRI spatial components are affected by the low pass filtering effect of HRF in each trial. Materials and Methods: In this paper, we have proposed a new method based on Advanced Coupled Matrix Tensor Factorization model to jointly factorize the EEG tensor and fMRI matrix while we simultaneously remove the effect of HRF through decomposition of fMRI dataset. Results: Applying the proposed method to an auditory oddball paradigm of simultaneous EEG-fMRI recording, the well-known ERP of oddball paradigm and the corresponding fMRI spatial maps are estimated. Conclusion: The results demonstrate that our proposed approach is strongly capable of extracting the ERPs and their corresponding fMRI spatial components, while simultaneously estimates the trial to trial variations of these factors with accurate amplitude and latency in each trial.

Bayesian tensor factorization for multi-way analysis of multi-dimensional EEG

Abstract Factorization-based analysis of multi-dimensional EEG (Electroencephalography) has become increasingly important in neuroscience research and practices with the capability of extracting latent multi-way features. However, how to sift the most informative factors of routinely noisy EEG remains unclear especially under the circumstance of no a priori knowledge. This study proposes a Bayesian tensor factorization (BTF) model as a “one-stop” solution to the challenges. BTF assumes non-informative priori on potential distribution of factors and noise derived from exponential family distribution. A high-dimensional variational Bayesian inference method is designed to iteratively estimate the posterior distribution of potential factors. The factor vectors whose elements are “small” values can then be identified as redundancy and filtered out afterwards. Finally, the study enables a generic factorization-based method for multi-way analysis of brain states. Results from experiments on synthesized tensors indicate that (1) BTF excels in processing EEG tensor mixed with intensive white noises in comparison with the traditional counterparts; and (2) the non-informative components in factors can be filtered out effectively (rank reduction). Two case studies of factorization-based multi-way analysis assisted by a Multi-Layer Perception (MLP) network have been performed on two real EEG datasets, and (1) seizure detection and (2) sleep stage classification can be achieved with averaged accuracy up to 99.52% and 90.81% respectively.

Multi-level Explanations in Neuroscience II: EEG Spectral Fingerprints and Tensor Decompositions for Understanding Brain Activity --- Initial Results

Multi-level Explanations in Neuroscience II: EEG Spectral Fingerprints and Tensor Decompositions for Understanding Brain Activity --- Initial Results

Disrupted Gamma Synchrony after Mild Traumatic Brain Injury and Its Correlation with White Matter Abnormality.

Mild traumatic brain injury (mTBI) has been firmly associated with disrupted white matter integrity due to induced white matter damage and degeneration. However, comparatively less is known about the changes of the intrinsic functional connectivity mediated via neural synchronization in the brain after mTBI. Moreover, despite the presumed link between structural and functional connectivity, no existing studies in mTBI have demonstrated clear association between the structural abnormality of white matter axons and the disruption of neural synchronization. To investigate these questions, we recorded resting state EEG and diffusion tensor imaging (DTI) from a cohort of military service members. A newly developed synchronization measure, the weighted phase lag index was applied on the EEG data for estimating neural synchronization. Fractional anisotropy was computed from the DTI data for estimating white matter integrity. Fifteen service members with a history of mTBI within the past 3 years were compared to 22 demographically similar controls who reported no history of head injury. We observed that synchronization at low-gamma frequency band (25–40 Hz) across scalp regions was significantly decreased in mTBI cases compared with controls. The synchronization in theta (4–7 Hz), alpha (8–13 Hz), and beta (15–23 Hz) frequency bands were not significantly different between the two groups. In addition, we found that across mTBI cases, the disrupted synchronization at low-gamma frequency was significantly correlated with the white matter integrity of the inferior cerebellar peduncle, which was also significantly reduced in the mTBI group. These findings demonstrate an initial correlation between the impairment of white matter integrity and alterations in EEG synchronization in the brain after mTBI. The results also suggest that disruption of intrinsic neural synchronization at low-gamma frequency may be a characteristic functional pathology following mTBI and may prove useful for developing better methods of diagnosis and treatment.

A new approach for SSVEP detection using PARAFAC and canonical correlation analysis.

This paper presents a new way for automatic detection of SSVEPs through correlation analysis between tensor models. 3-way EEG tensor of channel × frequency × time is decomposed into constituting factor matrices using PARAFAC model. PARAFAC analysis of EEG tensor enables us to decompose multichannel EEG into constituting temporal, spectral and spatial signatures. SSVEPs characterized with localized spectral and spatial signatures are then detected exploiting a correlation analysis between extracted signatures of the EEG tensor and the corresponding simulated signatures of all target SSVEP signals. The SSVEP that has the highest correlation is selected as the intended target. Two flickers blinking at 8 and 13 Hz were used as visual stimuli and the detection was performed based on data packets of 1 second without overlapping. Five subjects participated in the experiments and the highest classification rate of 83.34% was achieved, leading to the Information Transfer Rate (ITR) of 21.01 bits/min.

Localization of brain activities using multiway analysis of EEG tensor via EMD and reassigned TF representation.

Electroencephalogram (EEG) is widely used for monitoring, diagnosis purposes and also for study of brain's physiological, mental and functional abnormalities. Processing of information by the brain is reflected in dynamical changes of the electrical activity in time, frequency, and space. EEG signal processing tends to describe and quantify these variations in such a way that they are localized in temporal, spectral and spatial domain. Here we use multi-way (Tensor) analysis for localizing the EEG events. We used EMD process for decomposing EEG into distinct oscillatory modes, which are then mapped to TF plane using the near optimal Reassigned Spectrogram. Temporal, Spatial and Spectral information of the Multichannel EEG are then used to generate a three-way Frequency-Time-Space EEG tensor. Exploiting EMD also enables us to detrend the EEG recordings. Simulation results on both synthetic and real EEG data show that tensor analysis greatly improve separation and localization of overlapping events in EEG and it could be effectively exploited for detecting and characterizing the evoked potentials.

L1-Regularized Multiway Canonical Correlation Analysis for SSVEP-Based BCI

Canonical correlation analysis (CCA) between recorded electroencephalogram (EEG) and designed reference signals of sine-cosine waves usually works well for steady-state visual evoked potential (SSVEP) recognition in brain-computer interface (BCI) application. However, using the reference signals of sine- cosine waves without subject-specific and inter-trial information can hardly give the optimal recognition accuracy, due to possible overfitting, especially within a short time window length. This paper introduces an L1-regularized multiway canonical correlation analysis (L1-MCCA) for reference signal optimization to improve the SSVEP recognition performance further. A multiway extension of the CCA, called MCCA, is first presented, in which collaborative CCAs are exploited to optimize the reference signals in correlation analysis for SSVEP recognition alternatingly from the channel-way and trial-way arrays of constructed EEG tensor. L1-regularization is subsequently imposed on the trial-way array optimization in the MCCA, and hence results in the more powerful L1-MCCA with function of effective trial selection. Both the proposed MCCA and L1-MCCA methods are validated for SSVEP recognition with EEG data from 10 healthy subjects, and compared to the ordinary CCA without reference signal optimization. Experimental results show that the MCCA significantly outperforms the CCA for SSVEP recognition. The L1-MCCA further improves the recognition accuracy which is significantly higher than that of the MCCA.