Search

Evoked event-related oscillations (EROs) have been widely used to explore the mechanisms of brain activities for both normal people and neuropsychiatric disease patients. The selection of regions of evoked EROs tends to be subjectively based on the previous studies and the visual inspection of grand averaged time-frequency representations (TFRs) which causes some missing or redundant information. Meanwhile, the evoked EROs cannot be fully extracted via the conventional time-frequency analysis (TFA) method because they are sometimes overlapped with each other or with artifacts in time, frequency, and space domains to some extent. Hence, these shortcomings may pose some challenges to investigate the related neuronal processes. A data-driven approach was introduced to fill the gaps as below: extracting the temporal and spatial components of interest simultaneously by principal component analysis and Promax rotation and projecting them to the electrode field to correct their variance and polarity indeterminacy, calculating the TFRs of the back-projected components, and determining the regions of interest objectively using the edge detection algorithm. We performed this novel approach and the conventional TFA method in analyzing both a synthetic dataset and an actual ERP dataset in a two-factor simple gambling paradigm of waiting time (short/long) and feedback (loss/gain) separately. Synthetic dataset results indicated that N2-theta and P3-delta oscillations were detected using the proposed approach, but, by comparison, only one oscillation was obtained via the conventional TFA method. Furthermore, the actual ERP dataset results of P3-delta for our approach revealed that it was sensitive to the waiting time (which also was found in the previous reports) but not for that of the conventional TFA method. This study manifested that the proposed approach can objectively extract evoked EROs, which allows a better understanding of the modulations of the oscillatory responses.

Background: Music therapy improves neuronal activity and connectivity of healthy persons and patients with clinical symptoms of neurological diseases like Parkinson’s Disease, Alzheimer’s Disease, and Major Depression. Despite the plethora of publications that have reported the positive effects of music interventions, little is known about how music improves neuronal activity and connectivity in afflicted patients. In this three-part series of studies, each of the three neurological disorders – (1) Parkinson’s Disease, (2) Alzheimer’s Disease, and (3) Major Depression – will be treated individually in detail. Methods: For patients suffering from Parkinson’s Disease (PD), we propose a daily 25-minute music-based synchronous finger tapping (SFT) intervention for 8-weeks. Participants will be each split into two groups: an intervention group and a control arm. Assessment of finger tapping performances, the Unified Parkinson’s Disease Rating Scale (UPDRS), an n-back test, the Montreal Cognitive Assessment (MoCA), as well as oxygenated- (HbO 2 ), deoxygenated- hemoglobin (HbR), and total hemoglobin activation collected by functional near-infrared spectroscopy (fNIRS) will be measured at baseline, week 4 (during), week 8 (post), and week 12 (retention) of the study. Data collected from the two PD groups will be compared to baseline performances from healthy controls.Discussion: The trial study investigates the cortical neuronal activity and therapeutic effects associated with an auditory external cue used to induce automatic and implicit synchronous finger tapping in patients diagnosed with PD. The extent to which the intervention is effective may be dependent on the severity of the disease.

Recent continuous task studies, such as narrative speech comprehension, show that fluctuations in brain functional connectivity (FC) are altered and enhanced compared to the resting state. Here, we characterized the fluctuations in FC during comprehension of speech and time-reversed speech conditions. The correlations of Hilbert envelope of source-level EEG data were used to quantify FC between spatially separate brain regions. A symmetric multivariate leakage correction was applied to address the signal leakage issue before calculating FC. The dynamic FC was estimated based on a sliding time window. Then, principal component analysis (PCA) was performed on individually concatenated and temporally concatenated FC matrices to identify FC patterns. We observed that the mode of FC induced by speech comprehension can be characterized with a single principal component. The condition-specific FC demonstrated decreased correlations between frontal and parietal brain regions and increased correlations between frontal and temporal brain regions. The fluctuations of the condition-specific FC characterized by a shorter time demonstrated that dynamic FC also exhibited condition specificity over time. The FC is dynamically reorganized and FC dynamic pattern varies along a single mode of variation during speech comprehension. The proposed analysis framework seems valuable for studying the reorganization of brain networks during continuous task experiments.

A fiber optic array (FOA) can be used as an alternative or a supplement to the lens in a microscope due to its large magnification, high coupling efficiency and extremely low distortion. Based on our previous research, this paper first demonstrated the resolution and field-of-view (FOV) of the microscope based on the FOA. To further validate the FOA microscope&rsquo, s imaging capability, yeast activity and concentration were investigated by simple image processing. The results showed that the percentages of live and dead yeast cells correctly identified were 92.1% and 84.8%, except for the clusters, which agreed well with the manual counting methods. Then, the performances of the portable microscopes based on the FOA and lens were compared and the factors that affect the FOA microscope imaging performance were analyzed.

BackgroundNonnegative matrix factorization (NMF) has been successfully used for electroencephalography (EEG) spectral analysis. Since NMF was proposed in the 1990s, many adaptive algorithms have been developed. However, the performance of their use in EEG data analysis has not been fully compared. Here, we provide a comparison of four NMF algorithms in terms of accuracy of estimation, stability (repeatability of the results) and time complexity of algorithms with simulated data. In the practical application of NMF algorithms, stability plays an important role, which was an emphasis in the comparison. A Hierarchical clustering algorithm was implemented to evaluate the stability of NMF algorithms.ResultsIn simulation-based comprehensive analysis of fit, stability, accuracy of estimation and time complexity, hierarchical alternating least squares (HALS) low-rank NMF algorithm (lraNMF_HALS) outperformed the other three NMF algorithms. In the application of lraNMF_HALS for real resting-state EEG data analysis, stable and interpretable features were extracted.ConclusionBased on the results of assessment, our recommendation is to use lraNMF_HALS, providing the most accurate and robust estimation.

Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. Automatic sleep scoring is crucial and urgent to help address the increasing unmet needs for sleep research. Therefore, this paper aims to develop an automatic sleep scoring toolbox with the capability of multi-signal processing. The toolbox allows the user to choose signal types and the number of target classes. In addition, a user-friendly interface is provided to display sleep structures and related sleep parameters. The proposed approach employs several automatic processes including signal preprocessing, feature extraction and classification in order to save labor costs without compromising accuracy. For the phase of feature extraction, a huge number of features are considered including statistical characters, frequency characters, time-frequency characters, fractal characters, entropy characters and nonlinear characters. Their contribution to distinguishing between different sleep stages are compared in this article. The classifier we used for sleep stages discrimination is the random forest algorithm. The performance of the proposed approach is tested on the patients with sleep apnea by assessing accuracy, sensitivity and precision. The model achieves an accuracy of 82% to 86% for patients with varying degrees of sleep-disordered breathing, which indicates that sleep-disordered breathing does not significantly affect the performance of the proposed model. The proposed automatic scoring toolbox would alleviate the burden of the physicians, speed up sleep scoring, and expedite sleep research.

Canonical polyadic decomposition (CPD) of multi-subject complex-valued fMRI data can be used to provide spatially and temporally shared components among groups with both magnitude and phase information. However, the CPD model is not well formulated due to the large subject variability in the spatial and temporal modalities, as well as the high noise level in complex-valued fMRI data. Considering that the shift-invariant CPD can model temporal variability across subjects, we propose to further impose a phase sparsity constraint on the shared spatial maps to denoise the complex-valued components and to model the inter-subject spatial variability as well. More precisely, subject-specific time delays are first estimated for the complex-valued shared time courses in the framework of real-valued shift-invariant CPD. Source phase sparsity is then imposed on the complex-valued shared spatial maps. A smoothed $\ell _{\mathbf {{0}}}$ norm is specifically used to reduce voxels with large phase values after phase de-ambiguity based on the small phase characteristic of BOLD-related voxels. The results from both the simulated and experimental fMRI data demonstrate improvements of the proposed method over three complex-valued algorithms, namely, tensor-based spatial ICA, shift-invariant CPD and CPD without spatiotemporal constraints. When comparing with a real-valued algorithm combining shift-invariant CPD and ICA, the proposed method detects 178.7% more contiguous task-related activations. peerReviewed

Background Ongoing EEG data are recorded as mixtures of stimulus-elicited EEG, spontaneous EEG and noises, which require advanced signal processing techniques for separation and analysis. Existing methods cannot simultaneously consider common and individual characteristics among/within subjects when extracting stimulus-elicited brain activities from ongoing EEG elicited by 512-s long modern tango music. New method Aiming to discover the commonly music-elicited brain activities among subjects, we provide a comprehensive framework based on fast double-coupled nonnegative tensor decomposition (FDC-NTD) algorithm. The proposed algorithm with a generalized model is capable of simultaneously decomposing EEG tensors into common and individual components. Results With the proposed framework, the brain activities can be effectively extracted and sorted into the clusters of interest. The proposed algorithm based on the generalized model achieved higher fittings and stronger robustness. In addition to the distribution of centro-parietal and occipito-parietal regions with theta and alpha oscillations, the music-elicited brain activities were also located in the frontal region and distributed in the 4∼11 Hz band. Comparison with existing method(s) The present study, by providing a solution of how to separate common stimulus-elicited brain activities using coupled tensor decomposition, has shed new light on the processing and analysis of ongoing EEG data in multi-subject level. It can also reveal more links between brain responses and the continuous musical stimulus. Conclusions The proposed framework based on coupled tensor decomposition can be successfully applied to group analysis of ongoing EEG data, as it can be reliably inferred that those brain activities we obtained are associated with musical stimulus.

Statistical shape models (SSMs) are widely used in medical image segmentation. However, traditional SSM methods suffer from the High-Dimension-Low-Sample-Size (HDLSS) problem in modelling. In this work, we extend the state-of-the-art multi-resolution SSM approach from two dimension (2D) to three dimension (3D) and from single organ to multiple organs. Then we proposed a multi-resolution multi-organ 3D SSM method that uses a downsampling-and-interpolation strategy to overcome HDLSS problem. We also use an inter-surface-point distance thresholding scheme to achieve multi-resolution modelling effect. Our method is tested on the modelling of multiple mouse abdominal organs from mouse micro-CT images in three different resolution levels, including global level, single organ level and local organ level. The minimum specificity error and generalization error of this method are less than 0.3 mm, which are close to the pixel resolution of mouse micro-CT images (0.2 mm) and better than the modelling results of traditional principal component analysis (PCA) method.

Sustained attention encompasses a cascade of fundamental functions. The human ability to implement a sustained attention task is supported by brain networks that dynamically formed and dissolved through oscillatory synchronization. The decrement of vigilance induced by prolonged task engagement affects sustained attention. However, little is known about which stage or combinations are affected by vigilance decrement. Here, we applied an analysis framework composed of weighted phase lag index (wPLI) and tensor component analysis (TCA) to an EEG dataset collected during 80 min sustained attention task to examine the electrophysiological basis of such effect. We aimed to characterize the phase-coupling networks to untangle different phases involved in sustained attention and study how they are modulated by vigilance decrement. We computed the time–frequency domain wPLI from each block and subject and constructed a fourth-order tensor, containing the time, frequency, functional connectivity (FC), and blocks × subjects. This tensor was subjected to the TCA to identify the interacted and low-dimensional components representing the frequency-specific dynamic FC (fdFC). We extracted four types of neuromakers during a sustained attention task, namely the pre-stimulus alpha right-lateralized parieto-occipital FC, the post-stimulus theta fronto-parieto-occipital FC, delta fronto-parieto-occipital FC, and beta right/left sensorimotor FCs. All these fdFCs were impaired by vigilance decrement. These fdFCs, except for the beta left sensorimotor network, were restored by rewards, although the restoration by reward in the beta right sensorimotor network was transient. These findings provide implications for dissociable effects of vigilance decrement on sustained attention by utilizing the tensor-based framework. Electronic supplementary material The online version of this article (10.1007/s10548-020-00795-0) contains supplementary material, which is available to authorized users.

Functional connectivity (FC) patterns in human brain are dynamic in a task-specific condition, and identifying the dynamic changes is important to reveal the information processing processes and network reconfiguration in cognitive tasks. In this study, we proposed a comprehensive framework based on high-order singular value decomposition (HOSVD) to detect the stable change points of FC using electroencephalogram (EEG). First, phase lag index (PLI) method was applied to calculate FC for each time point, constructing a 3-way tensor, i.e., connectivity \( \times \) connectivity \( \times \) time. Then a stepwise HOSVD (SHOSVD) algorithm was proposed to detect the change points of FC, and the stability of change points were analyzed considering the different dissimilarity between different FC patterns. The transmission of seven FC patterns were identified in a task condition. We applied our methods to EEG data, and the results verified by prior knowledge demonstrated that our proposed algorithm can reliably capture the dynamic changes of FC.

Deep learning for the automated detection of epileptic seizures has received much attention during recent years. In this work, one dimensional convolutional neural network (1D-CNN) and two dimensional convolutional neural network (2D-CNN) are simultaneously used on electroencephalogram (EEG) data for seizure detection. Firstly, using sliding windows without overlap on raw EEG to obtain the definite one-dimension time EEG segments (1D-T), and continuous wavelet transform (CWT) for 1D-T signals to obtain the two-dimension time-frequency representations (2D-TF). Then, 1D-CNN and 2D-CNN model architectures are used on 1D-T and 2D-TF signals for automatic classification, respectively. Finally, the classification results from 1D-CNN and 2D-CNN are showed. In the two-classification and three-classification problems of seizure detection, the highest accuracy can reach 99.92% and 99.55%, respectively. It shows that the proposed method for a benchmark clinical dataset can achieve good performance in terms of seizure detection. peerReviewed

Recent studies show that the dynamics of electrophysiological functional connectivity is attracting more and more interest since it is considered as a better representation of functional brain networks than static network analysis. It is believed that the dynamic electrophysiological brain networks with specific frequency modes, transiently form and dissolve to support ongoing cognitive function during continuous task performance. Here, we propose a novel method based on tensor component analysis (TCA), to characterize the spatial, temporal, and spectral signatures of dynamic electrophysiological brain networks in electroencephalography (EEG) data recorded during free music-listening. A three-way tensor containing time-frequency phase-coupling between pairs of parcellated brain regions is constructed. Nonnegative CANDECOMP/PARAFAC (CP) decomposition is then applied to extract three interconnected, low-dimensional descriptions of data including temporal, spectral, and spatial connection factors. Musical features are also extracted from stimuli using acoustic feature extraction. Correlation analysis is then conducted between temporal courses of musical features and TCA components to examine the modulation of brain patterns. We derive several brain networks with distinct spectral modes (described by TCA components) significantly modulated by musical features, including higher-order cognitive, sensorimotor, and auditory networks. The results demonstrate that brain networks during music listening in EEG are well characterized by TCA components, with spatial patterns of oscillatory phase-synchronization in specific spectral modes. The proposed method provides evidence for the time-frequency dynamics of brain networks during free music listening through TCA, which allows us to better understand the reorganization of electrophysiological networks.

Clustering is a promising tool for grouping the sequence of similar time-points aimed to identify the attention blocks in spatiotemporal event-related potentials (ERPs) analysis. It is most likely to elicit the appropriate time window for ERP of interest if a suitable clustering method is applied to spatiotemporal ERP. However, how to reliably estimate a proper time window from entire individual subjects’ data is still challenging. In this study, we developed a novel multiset consensus clustering method in which several clustering results of multiple subjects were combined to retrieve the best fitted clustering for all the subjects within a group. Then, the obtained clustering was processed by a newly proposed time-window detection method to determine the most suitable time window for identifying the ERP of interest in each condition/group. Applying the proposed method to the simulated ERP data and real data indicated that the brain responses from the individual subjects can be collected to determine a reliable time window for different conditions/groups. Our results revealed more precise time windows to identify N2 and P3 components in the simulated data compared to the state-of-the-art methods. Additionally, our proposed method achieved more robust performance and outperformed statistical analysis results in the real data for N300 and prospective positivity components. To conclude, the proposed method successfully estimates the time window for ERP of interest by processing the individual data, offering new venues for spatiotemporal ERP processing.

Background There has been growing interest towards naturalistic neuroimaging experiments, which deepen our understanding of how human brain processes and integrates incoming streams of multifaceted sensory information, as commonly occurs in real world. Music is a good example of such complex continuous phenomenon. In a few recent fMRI studies examining neural correlates of music in continuous listening settings, multiple perceptual attributes of music stimulus were represented by a set of high-level features, produced as the linear combination of the acoustic descriptors computationally extracted from the stimulus audio. New method fMRI data from naturalistic music listening experiment were employed here. Kernel principal component analysis (KPCA) was applied to acoustic descriptors extracted from the stimulus audio to generate a set of nonlinear stimulus features. Subsequently, perceptual and neural correlates of the generated high-level features were examined. Results The generated features captured musical percepts that were hidden from the linear PCA features, namely Rhythmic Complexity and Event Synchronicity. Neural correlates of the new features revealed activations associated to processing of complex rhythms, including auditory, motor, and frontal areas. Comparison with existing method Results were compared with the findings in the previously published study, which analyzed the same fMRI data but applied linear PCA for generating stimulus features. To enable comparison of the results, methodology for finding stimulus-driven functional maps was adopted from the previous study. Conclusions Exploiting nonlinear relationships among acoustic descriptors can lead to the novel high-level stimulus features, which can in turn reveal new brain structures involved in music processing.

Independent component analysis (ICA) on group-level voxel-based morphometry (VBM) produces the coefficient matrix and the component matrix. The former contains variability among multiple subjects for further statistical analysis, and the latter reveals spatial maps common for all subjects. ICA algorithms converge to local optimization points in practice and the mostly applied stability investigation approach examines the stability of the extracted components. We found that the practically stable components do not guarantee to produce the practically stable coefficients of ICA decomposition for the further statistical analysis. Consequently, we proposed a novel approach including two steps: (1), the stability index for the coefficient matrix and the stability index for the component matrix were examined, respectively; (2) the two indices were multiplied to analyze the stability of ICA decomposition. The proposed approach was used to study the sMRI data of Type II diabetes mellitus group and the healthy control group (HC). Group differences in VBM were found in the superior temporal gyrus. Besides, it was revealed that the VBMs of the region of the HC group were significantly correlated with Montreal Cognitive Assessment (MoCA) describing the level of cognitive disorder. In contrast to the widely applied approach to investigating the stability of the extracted components for ICA decomposition, we proposed to examine the stability of ICA decomposition by fusion the stability of both coefficient matrix and the component matrix. Therefore, the proposed approach can examine the stability of ICA decomposition sufficiently.

Zebrafish eggs are widely used in biological experiments to study the environmental and genetic influence on embryo development. Due to the high throughput of microscopic imaging, automated analysis of zebrafish egg microscopic images is highly demanded. However, machine learning algorithms for zebrafish egg image analysis suffer from the problems of small imbalanced training dataset and subtle inter-class differences. In this study, we developed an automated zebrafish egg microscopic image analysis algorithm based on deep convolutional neural network (CNN). To tackle the problem of insufficient training data, the strategies of transfer learning and data augmentation were used. We also adopted the global averaged pooling technique to overcome the subtle phenotype differences between the fertilized and unfertilized eggs. Experimental results of a five-fold cross-validation test showed that the proposed method yielded a mean classification accuracy of 95.0% and a maximum accuracy of 98.8%. The network also demonstrated higher classification accuracy and better convergence performance than conventional CNN methods. This study extends the deep learning technique to zebrafish egg phenotype classification and paves the way for automatic bright-field microscopic image analysis.

Background and objective It is challenging to conduct real-time identification of myocardial infarction (MI) due to artifact corruption and high dimensionality of multi-lead electrocardiogram (ECG). In the present study, we proposed an automated single-beat MI detection and localization system using dual-Q tunable Q-factor wavelet transformation (Dual-Q TQWT) denoising algorithm. Methods After denoising and segmentation of ECG, a fourth-order wavelet tensor (leads × subbands × samples × beats) was constructed based on the discrete wavelet packet transform (DWPT), to represent the features considering the information of inter-beat, intra-beat, inter-frequency, and inter-lead. To reduce the tensor dimension and preserve the intrinsic information, the multilinear principal component analysis (MPCA) was employed. Afterward, 84 discriminate features were fed into a classifier of bootstrap-aggregated decision trees (Treebagger). A total of 78 healthy and 328 MI (6 types) records including 57557 beats were chosen from PTB diagnostic ECG database for evaluation. Results The validation results demonstrated that our proposed MI detection and localization system embedded with Dual-Q TQWT and wavelet packet tensor decomposition outperformed commonly used discrete wavelet transform (DWT), empirical mode decomposition (EMD) denoising methods and vector-based PCA method. With the Treebagger classifier, we obtained an accuracy of 99.98% in beat level and an accuracy of 97.46% in record level training/testing for MI detection. We also achieved an accuracy of 99.87% in beat level and an accuracy of 90.39% in record level for MI localization. Conclusion Altogether, the automated system brings potential improvement in automated detection and localization of MI in clinical practice.

Electrocardiography (ECG) signal analysis is an effective method for diagnosis of heart disease. However, the quality of ECG, corrupted by artifacts, limits the automatic ECG classification. In order to extract good quality ECG, we proposed a new ECG enhancement method based on tunable Q-factor wavelet transform (TQWT). In the proposed method, the original ECG signal was decomposed into high Q-factor component and low Q-factor component with dual-Q TQWT. According to the morphological of P, QRS, T waves in ECG, low Q-factor component was chosen for the representation of ECG. The proposed method was tested on 52 healthy volunteers and 52 myocardial infarction patients from the openly dataset of PTB diagnostic ECG. A total of 288 features, covering time, frequency, nonlinear, and entropy domains, were extracted from R-R interval and ECG (in a window of 5s) across 12 leads. The features were selected by Relief method, and 22 discriminative features were fed into five different classifiers. The classification accuracy for dual-Q TQWT was 86.3%, which was 4.7% higher than the filtered data based on k-nearest neighbors (KNN) algorithm. The comparison results verified that the proposed dual-Q TQWT method provides good feasibility for ECG de-noising.

The characterization of dynamic electrophysiological brain activity, which form and dissolve in order to support ongoing cognitive function, is one of the most important goals in neuroscience. Here, we introduce a method with tensor decomposition for measuring the task-induced oscillations in the human brain using electroencephalography (EEG). The time frequency representation of source-reconstructed singletrail EEG data constructed a third-order tensor with three factors of time ∗ trails, frequency and source points. We then used a non-negative Canonical Polyadic decomposition (NCPD) to identify the temporal, spectral and spatial changes in electrophysiological brain activity. We validate this method using both simulation EEG data and real EEG data recorded during a task of irony comprehension. The results demonstrated that proposed method can track dynamics of the temporal-spectral modes of the rhythm in the brain on a timescale commensurate to the task they are undertaking. peerReviewed

Background Stability of spatial components is frequently used as a post-hoc selection criteria for choosing the dimensionality of an independent component analysis (ICA) of functional magnetic resonance imaging (fMRI) data. Although the stability of the ICA temporal courses differs from that of spatial components, temporal stability has not been considered during dimensionality decisions. New method The current study aims to (1) develop an algorithm to incorporate temporal course stability into dimensionality selection and (2) test the impact of temporal course on the stability of the ICA decomposition of fMRI data via tensor clustering. Resting state fMRI data were analyzed with two popular ICA algorithms, InfomaxICA and FastICA, using our new method and results were compared with model order selection based on spatial or temporal criteria alone. Results Hierarchical clustering indicated that the stability of the ICA decomposition incorporating spatiotemporal tensor information performed similarly when compared to current best practice. However, we found that component spatiotemporal stability and convergence of the model varied significantly with model order. Considering both may lead to methodological improvements for determining ICA model order. Selected components were also significantly associated with relevant behavioral variables. Comparison with Existing Method: The Kullback–Leibler information criterion algorithm suggests the optimal model order for group ICA is 40, compared to the proposed method with an optimal model order of 20. Conclusion The current study sheds new light on the importance of temporal course variability in ICA of fMRI data.

Embodiment theories argue that language comprehension involves activating specific sensory-motor systems in the brain. Previous research performed in English and other Indo-European languages suggests that, when compared to compatible sentences referring to the same actions performed sequentially (e.g. 'After cleaning the wound he unrolled the bandage'), incompatible sentences describing two manual actions performed simultaneously by an agent (e.g. 'While cleaning the wound he unrolled the bandage') were worse understood and increased the event-related potentials (ERPs) component N400. The present ERP research aims to further investigate brain response to motor compatibility in native Mandarin speakers. The Chinese experimental sentences described two manual actions either in incongruent conditions marked by the Chinese parallel structure … … ('yibian…yibian…'/'while… while…') or congruent conditions marked by the sequential structure … … ('xian…ranhou…'/'firstly… then…'). The last action clause elicited larger fronto-central N400 in the incongruent condition, which reveals that there are semantic embodiment effects on the comprehension of Mandarin manual action language.

Recently, exploring brain activity based on functional networks during naturalistic stimuli especially music and video represents an attractive challenge because of the low signal-to-noise ratio in collected brain data. Although most efforts focusing on exploring the listening brain have been made through functional magnetic resonance imaging (fMRI), sensor-level electro- or magnetoencephalography (EEG/MEG) technique, little is known about how neural rhythms are involved in the brain network activity under naturalistic stimuli. This study exploited cortical oscillations through analysis of ongoing EEG and musical feature during free-listening to music. We used a data-driven method that combined music information retrieval with spatial Independent Components Analysis (ICA) to probe the interplay between the spatial profiles and the spectral patterns. We projected the sensor data into cortical space using a minimum-norm estimate and applied the Short Time Fourier Transform (STFT) to obtain frequency information. Then, spatial ICA was made to extract spatial-spectral-temporal information of brain activity in source space and five long-term musical features were computationally extracted from the naturalistic stimuli. The spatial profiles of the components whose temporal courses were significantly correlated with musical feature time series were clustered to identify reproducible brain networks across the participants. Using the proposed approach, we found brain networks of musical feature processing are frequency-dependent and three plausible frequency-dependent networks were identified; the proposed method seems valuable for characterizing the large-scale frequency-dependent brain activity engaged in musical feature processing.

Real-world data exhibiting high order/dimensionality and various couplings are linked to each other since they share some common characteristics. Coupled tensor decomposition has become a popular technique for group analysis in recent years, especially for simultaneous analysis of multi-block tensor data with common information. To address the multiblock tensor data, we propose a fast double-coupled nonnegative Canonical Polyadic Decomposition (FDC-NCPD) algorithm in this study, based on the linked CP tensor decomposition (LCPTD) model and fast Hierarchical Alternating Least Squares (Fast-HALS) algorithm. The proposed FDCNCPD algorithm enables simultaneous extraction of common components, individual components and core tensors from tensor blocks. Moreover, time consumption is greatly reduced without compromising the decomposition quality when handling large-scale tensor blocks. Simulation experiments of synthetic and real-world data are conducted to demonstrate the superior performance of the proposed algorithm. peerReviewed

Tensor decomposition is a powerful tool for analyzing multiway data. Nowadays, with the fast development of multisensor technology, more and more data appear in higherorder (order > 4) and nonnegative form. However, the decomposition of higher-order nonnegative tensor suffers from poor convergence and low speed. In this study, we propose a new nonnegative CANDECOM/PARAFAC (NCP) model using proximal algorithm. The block principal pivoting method in alternating nonnegative least squares (ANLS) framework is employed to minimize the objective function. Our method can guarantee the convergence and accelerate the computation. The results of experiments on both synthetic and real data demonstrate the efficiency and superiority of our method. peerReviewed

Real-world data are often linked with each other since they share some common characteristics. The mutual linking can be seen as a core driving force of group analysis. This study proposes a generalized linked canonical polyadic tensor decomposition (GLCPTD) model that is well suited to exploiting the linking nature in multi-block tensor analysis. To address GLCPTD model, an efficient algorithm based on hierarchical alternating least squa res (HALS) method is proposed, termed as GLCPTD-HALS algorithm. The proposed algorithm enables the simultaneous extraction of common components, individual components and core tensors from tensor blocks. Simulation experiments of synthetic EEG data analysis and image reconstruction and denoising were conducted to demonstrate the superior performance of the proposed generalized model and its realization. peerReviewed

Sleep scoring is a fundamental but time-consuming process in any sleep laboratory. To speed up the process of sleep scoring without compromising accuracy, this paper develops an automatic sleep scoring toolbox with the capability of multi-signal processing. It allows the user to choose signal types and the number of target classes. Then, an automatic process containing signal pre-processing, feature extraction, classifier training (or prediction) and result correction will be performed. Finally, the application interface displays predicted sleep structure, related sleep parameters and the sleep quality index for reference. To improve the identification accuracy of minority stages, a layer-wise classification strategy is proposed according to the signal characteristics of sleep stages. The context of the current stage is taken into consideration in the correction phase by employing a Hidden Markov Model to study the transition rules of sleep stages in the training dataset. These transition rules will be used for logic classification results. The performance of proposed toolbox has been tested on 100 subjects with an average accuracy of 85.76%. The proposed automatic scoring toolbox would alleviate the burden of the physicians, speed up sleep scoring, and expedite sleep research. peerReviewed

Deep learning has contributed greatly to functional magnetic resonance imaging (fMRI) analysis, however, spatial maps derived from fMRI data by independent component analysis (ICA), as promising biomarkers, have rarely been directly used to perform individualized diagnosis. As such, this study proposes a novel framework combining ICA and convolutional neural network (CNN) for classifying schizophrenia patients (SZs) and healthy controls (HCs). ICA is first used to obtain components of interest which have been previously implicated in schizophrenia. Functionally informative slices of these components are then selected and labelled. CNN is finally employed to learn hierarchical diagnostic features from the slices and classify SZs and HCs. We use complex-valued fMRI data instead of magnitude fMRI data, in order to obtain more contiguous spatial activations. Spatial maps estimated by ICA with multiple model orders are employed for data argumentation to enhance the training process. Evaluations are performed using 82 resting-state complex-valued fMRI datasets including 42 SZs and 40 HCs. The proposed method shows an average accuracy of 72.65% in the default mode network and 78.34% in the auditory cortex for slice-level classification. When performing subject-level classification based on majority voting, the result shows 91.32% and 98.75% average accuracy, highlighting the potential of the proposed method for diagnosis of schizophrenia and other neurological diseases.

Blind source separation algorithms have been widely used in the EEG signal processing. This chapter introduces the EEG model basis of blind source separation and details of three mainstream algorithms, i.e., principal component analysis (PCA), independent component analysis (ICA), and tensor decomposition, to provide a comprehensive review on this growing topic. The main focus will be on basic principles of applying ICA on continuous EEG data to remove artifacts, PCA, and tensor decomposition on ERP data to conduct group analysis. The introduction of current softwares specialized in PCA and ICA on EEG signal processing will also be covered.

Background: Sleep scoring is an essential but time-consuming process, and therefore automatic sleep scoring is crucial and urgent to help address the growing unmet needs for sleep research. This paper aims to develop a versatile deep-learning architecture to automate sleep scoring using raw polysomnography recordings. Method: The model adopts a linear function to address different numbers of inputs, thereby extending model applications. Two-dimensional convolution neural networks are used to learn features from multi-modality polysomnographic signals, a “squeeze and excitation” block to recalibrate channel-wise features, together with a long short-term memory module to exploit long-range contextual relation. The learnt features are finally fed to the decision layer to generate predictions for sleep stages. Result: Model performance is evaluated on three public datasets. For all tasks with different available channels, our model achieves outstanding performance not only on healthy subjects but even on patients with sleep disorders (SHHS: Acc-0.87, K-0.81; ISRUC: Acc-0.86, K-0.82; Sleep-EDF: Acc-0.86, K-0.81). The highest classification accuracy is achieved by a fusion of multiple polysomnographic signals. Comparison: Compared to state-of-the-art methods that use the same dataset, the proposed model achieves a comparable or better performance, and exhibits low computational cost. Conclusions: The model demonstrates its transferability among different datasets, without changing model architecture or hyper-parameters across tasks. Good model transferability promotes the application of transfer learning on small group studies with mismatched channels. Due to demonstrated availability and versatility, the proposed method can be integrated with diverse polysomnography systems, thereby facilitating sleep monitoring in clinical or routine care. peerReviewed

Objective Manual sleep staging on overnight polysomnography (PSG) is time-consuming and laborious. This study aims to develop an end-to-end automatic sleep staging method in single-channel electroencephalogram (EEG) signals from PSG recordings. Methods A convolutional neural network called CCN-SE is proposed to address sleep staging tasks. The proposed method was efficiently constructed by stacking a collection of consecutive convolutional micro-networks (CCNs) and squeeze-excitation (SE) block. The designed model took multi-epoch (3 epochs) raw EEG signals as its input and relabeled the input. We trained and tested this model on different single-channel EEG (C4-A1 and Fpz-Cz) signals from two open datasets and then explored the model’s generalization ability and the channel mismatch problem using clinical PSG files. Results Results of the five-fold cross-validation show that our model achieved the good overall accuracies in SHHS1 (88.1%) and Sleep-EDFx (85.3%) datasets. Furthermore, the observed scores on 10 healthy clinical sleep recordings using the single EEG channel (C4-M1) based on two trained weights were 72.3% and 81.9%. Conclusion The obtained performance on two sleep datasets reveals the efficiency and generalization capability of the proposed method in sleep staging in EEG. Furthermore, the results on the clinical PSG recordings suggest that the proposed model can alleviate the problem of channel mismatch to some extent. Significance This study proposes a novel method for automatic sleep staging that can be easily utilized in portable sleep monitoring devices and draws attention to the channel mismatch in sleep staging.

To examine the electrophysiological underpinnings of the functional networks involved in music listening, previous approaches based on spatial independent component analysis (ICA) have recently been used to ongoing electroencephalography (EEG) and magnetoencephalography (MEG). However, those studies focused on healthy subjects, and failed to examine the group-level comparisons during music listening. Here, we combined group-level spatial Fourier ICA with acoustic feature extraction, to enable group comparisons in frequency-specific brain networks of musical feature processing. It was then applied to healthy subjects and subjects with major depressive disorder (MDD). The music-induced oscillatory brain patterns were determined by permutation correlation analysis between individual time courses of Fourier-ICA components and musical features. We found that (1) three components, including a beta sensorimotor network, a beta auditory network and an alpha medial visual network, were involved in music processing among most healthy subjects; and that (2) one alpha lateral component located in the left angular gyrus was engaged in music perception in most individuals with MDD. The proposed method allowed the statistical group comparison, and we found that: (1) the alpha lateral component was activated more strongly in healthy subjects than in the MDD individuals, and that (2) the derived frequency-dependent networks of musical feature processing seemed to be altered in MDD participants compared to healthy subjects. The proposed pipeline appears to be valuable for studying disrupted brain oscillations in psychiatric disorders during naturalistic paradigms.

Canonical polyadic decomposition (CPD) may face a local optimal problem when analyzing multi-subject fMRI data with inter-subject variability. Beckmann and Smith proposed a tensor PICA approach that incorporated an independence constraint to the spatial modality by combining CPD with ICA, and alleviated the problem of inter-subject spatial map (SM) variability.This study extends tensor PICA to incorporate additional inter-subject time course (TC) variability and to connect CPD and ICA in a new way. Assuming multiple subjects share common TCs but with different time delays, we accommodate subject-dependent TC delays into the CP model based on the idea of shift-invariant CP (SCP). We use ICA as an initialization step to provide the aggregating mixing matrix for shift-invariant CPD to estimate shared TCs with subject-dependent delays and intensities. We then estimate shared SMs using a least-squares fit post shift-invariant CPD.Using simulated fMRI data as well as actual fMRI data we demonstrate that the proposed approach improves the estimates of the shared SMs and TCs, and the subject-dependent TC delays and intensities. The default mode component illustrates larger TC delays than the task-related component.The proposed approach shows improvements over tensor PICA in particular when TC delays are large, and also outperforms SCP with SM orthogonality constraint and SCP with ICA-based SM initialization.TCs with subject-dependent delays conform to the true situation of multi-subject fMRI data. The proposed approach is suitable for decomposing multi-subject fMRI data with large inter-subject temporal and spatial variability.

Fatigue may cause a decrease in mental and physical performance capacity, which is a serious safety risk for the drivers in the transportation system. Recently, various studies have demonstrated the deviations of electroencephalogram (EEG) indicators from normal vigilant state during fatigue in time and frequency domains. However, when considering spatial information, these feature descriptors are not satisfying the demand for reliable detection due to the well-known challenge of signal mixing. In this paper, we propose a novel approach based on clustering on brain networks (CBNs) to alleviate the problem to improve the performance of driver fatigue detection. The clustering algorithm was employed to extract the spatial nodes with distinct connectivity attributes throughout the EEG-based brain networks. Then, the temporal features of wavelet entropy from the extracted nodes were transformed to spatio-temporal images so that the image edge detection method (pulse-coupled neural networks) to distinguish different stages of fatigue can be used. The experimental results demonstrated the temporal features from the extracted nodes reduced signal mixing and showed clearer deviations. The detected fatigue based on the imaging method was to an extent consistent with self-reported subjective feelings and most of the critical fatigue was detected before the subjective feelings of fatigue. For all the subjects, 21 of 29 accidents happened after detected fatigue in the simulated driving task. Therefore, the proposed method owns potential value for early warning and avoidance of traffic accidents caused by driver fatigue.

Classification of different zebrafish larvae phenotypes is useful for studying the environmental influence on embryo development. However, the scarcity of well-annotated training images and fuzzy inter-phenotype differences hamper the application of machine-learning methods in phenotype classification. This study develops a deep-learning approach to address these challenging problems. A convolutional network model with compressed separable convolution kernels is adopted to address the overfitting issue caused by insufficient training data. A two-tier classification pipeline is designed to improve the classification accuracy based on fuzzy phenotype features. Our method achieved an averaged accuracy of 91% for all the phenotypes and maximum accuracy of 100% for some phenotypes (e.g., dead and chorion). We also compared our method with the state-of-the-art methods based on the same dataset. Our method obtained dramatic accuracy improvement up to 22% against the existing method. This study offers an effective deep-learning solution for classifying difficult zebrafish larvae phenotypes based on very limited training data.

The framework of embodied cognition has challenged the modular view of a language-cognition divide by suggesting that meaning-retrieval critically involves the sensory-motor system. Despite extensive research into the neural mechanisms underlying language-motor coupling, it remains unclear how the motor system might be differentially engaged by different levels of linguistic abstraction and language proficiency. To address this issue, we used fMRI to quantify neural activations in brain regions underlying motor and language processing in Chinese-English speakers’ processing of literal, metaphorical, and abstract language in their L1 and L2. Results overall revealed a response in motor ROIs gradually attenuating in intensity from literal to abstract via metaphorical language in both L1 and L2. Furthermore, contrast analyses between L1 and L2 showed overall greater activations of motor ROIs in the L2. We conclude that motor involvement in language processing is graded rather than all-or-none and that the motor system has a dual-functional role. peerReviewed

Highlights • NMF-based method to identify abnormal connectivity patterns of ASD brains. • ASD children were characterized by interhemispheric under-connectivity. • Long-range connections modulated by slower rhythm; local-range by faster frequency. • Alpha-band interhemispheric pattern play pivotal role in ASD neurodevelopment., Autism spectrum disorder (ASD) is associated with altered patterns of over- and under-connectivity of neural circuits. Age-related changes in neural connectivities remain unclear for autistic children as compared with normal children. In this study, a parts-based network-decomposition technique, known as non-negative matrix factorization (NMF), was applied to identify a set of possible abnormal connectivity patterns in brains affected by ASD, using resting-state electroencephalographic (EEG) data. Age-related changes in connectivities in both inter- and intra-hemispheric areas were studied in a total of 256 children (3–6 years old), both with and without ASD. The findings included the following: (1) the brains of children affected by ASD were characterized by a general trend toward long-range under-connectivity, particularly in interhemispheric connections, combined with short-range over-connectivity; (2) long-range connections were often associated with slower rhythms (δ and θ), whereas synchronization of short-range networks tended to be associated with faster frequencies (α and β); and (3) the α-band specific patterns of interhemispheric connections in ASD could be the most prominent during early childhood neurodevelopment. Therefore, NMF would be useful for further exploring the early childhood developmental functional connectivity of children aged 3–6 with ASD as well as with typical development. Additionally, long-range interhemispheric alterations in connectivity may represent a potential biomarker for the identification of ASD.

The majority of optical microscopes rely heavily on the lens group because of the low cost and ease of use. However, this type of microscope is limited by the relative long working distance, large chromatic aberration and complex structure. As an alternative to the lens, fiber optic array (FOA) can overcome the above limitations and achieve better results in the same magnification scale. This paper demonstrated that the microscope based on the FOA had a comparable resolution (3 μm) with the traditional lens group microscope, while the field-of-view (FOV) of FOA was almost four times larger than the latter. Without any manual focus, the volume and distortion of our FOA microscope were obviously smaller than that of the lens group microscope. To obtain a better microscopy imaging performance based on the FOA, the coupling efficiency and signal-to-noise ratio (SNR) of the FOA microscope were analyzed and some related measures for improvement were proposed.

Dynamic representation of functional brain networks involved in the sequence analysis of functional connectivity graphs of the brain (FCGB) gains advances in uncovering evolved interaction mechanisms. However, most of the networks, even the event-related ones, are highly heterogeneous due to spurious interactions, which bring challenges to revealing the change patterns of interactive information in the complex dynamic process. In this paper, we propose a network entropy (NE) method to measure connectivity uncertainty of FCGB sequences to alleviate the spurious interaction problem in dynamic network analysis to realize associations with different events during a complex cognitive task. The proposed dynamic analysis approach calculated the adjacency matrices from ongoing electroencephalpgram (EEG) in a sliding time-window to form the FCGB sequences. The probability distribution of Shannon entropy was replaced by the connection sequence distribution to measure the uncertainty of FCGB constituting NE. Without averaging, we used time frequency transform of the NE of FCGB sequences to analyze the event-related changes in oscillatory activity in the single-trial traces during the complex cognitive process of driving. Finally, the results of a verification experiment showed that the NE of the FCGB sequences has a certain time-locked performance for different events related to driver fatigue in a prolonged driving task. The time errors between the extracted time of high-power NE and the recorded time of event occurrence were distributed within the range [−30 s, 30 s] and 90.1% of the time errors were distributed within the range [−10 s, 10 s]. The high correlation (r = 0.99997, p < 0.001) between the timing characteristics of the two types of signals indicates that the NE can reflect the actual dynamic interaction states of brain. Thus, the method may have potential implications for cognitive studies and for the detection of physiological states.

Background: Preprocessed Event-related potential (ERP) data are usually organized in multi-way tensor, in which tensor decomposition serves as a powerful tool for data processing. Due to the limitation of computation burden for multi-way data and the low algorithm performance of stability and efficiency, multi-way ERP data are conventionally reorganized into low-order tensor or matrix before further analysis. However, the reorganization may hamper mode specification and spoil the interaction information among different modes. New Method: In this study, we applied a fifth-order tensor decomposition to a set of fifth-order ERP data collected by exerting proprioceptive stimulus on left and right hand. One of the latest nonnegative CANDECOMP/PARAFAC (NCP) decomposition methods implemented by alternating proximal gradient (APG) was employed. We also proposed an improved DIFFIT method to select the optimal component number for the fifth-order tensor decomposition. Results: By the fifth-order NCP model with a proper component number, the ERP data were fully decomposed into spatial, spectral, temporal, subject and condition factors in each component. The results showed more pairs of components with symmetric activation region in left and right hemisphere elicited by contralateral stimuli on hand. Comparison with Existing Method(s): In our experiment, more interesting components and coherent brain activities were extracted, compared with previous studies. Conclusions: The discovered activities elicited by proprioceptive stimulus are in line with those in relevant cognitive neuroscience studies. Our proposed method has proved to be appropriate and viable for processing high-order EEG data with well-preserved interaction information among all modes.

Motor experience plays an important role in the ability to anticipate action outcomes, but little is known about the brain processes through which it modulates the preparation for unexpected events. To address this issue, EEG was employed while table tennis players and novices observed videos of serves in order to predict the expected ball direction based on the kinematics of a model's movement. Furthermore, we manipulated the congruency between the model's body kinematics and the subsequent ball trajectory while assessing the cerebral cortical activity of novices and experts to understand how experts respond to unexpected outcomes. Experts were more accurate in predicting the ball trajectories than novices and were further differentiated from novices in the cortical dynamics just prior to ball contact and during the period of observation of the ball trajectories. Consistent with the predicted response-outcome model, experts exhibited elevated theta oscillations during the incongruent relative to the congruent trajectories, while no such differences were observed in the novices. Source estimation for theta activity revealed stronger activation in the middle frontal gyrus for the experts in response to the incongruent trajectories. Collectively, the observed differences in cortical dynamics between the groups suggest that motor experience promotes central neural system adaptations that facilitate preparation for anticipated outcomes and contributes to adaptive cognitive-motor responses in the face of uncertainty.

Background Component splitting at higher model orders is a widely accepted finding for independent component analysis (ICA) of functional magnetic resonance imaging (fMRI) data. However, our recent study found that intact components occurred with subcomponents at higher model orders. New method This study investigated model order effects on ICA of resting-state complex-valued fMRI data from 82 subjects, which included 40 healthy controls (HCs) and 42 schizophrenia patients. In addition, we explored underlying causes for distinct component splitting between complex-valued data and magnitude-only data by examining model order effects on ICA of phase fMRI data. A best run selection method was proposed to combine subject averaging and a one-sample t-test. We selected the default mode network (DMN)-, visual-, and sensorimotor-related components from the best run of ICA at varying model orders from 10 to 140. Results Results show that component integration occurred in complex-valued and phase analyses, whereas component splitting emerged in magnitude-only analysis with increasing model order. Incorporation of phase data appears to play a complementary role in preserving integrity of brain networks. Comparison with existing method(s) When compared with magnitude-only analysis, the intact DMN component obtained in complex-valued analysis at higher model orders exhibited highly significant subject-level differences between HCs and patients with schizophrenia. We detected significantly higher activity and variation in anterior areas for HCs and in posterior areas for patients with schizophrenia. Conclusions These results demonstrate the potential of complex-valued fMRI data to contribute generally and specifically to brain network analysis in identification of schizophrenia-related changes.

Tensor decomposition has been widely employed for EEG signal processing in recent years. Constrained and regularized tensor decomposition often attains more meaningful and interpretable results. In this study, we applied sparse nonnegative CANDECOMP/PARAFAC tensor decomposition to ongoing EEG data under naturalistic music stimulus. Interesting temporal, spectral and spatial components highly related with music features were extracted. We explored the ongoing EEG decomposition results and properties in a wide range of sparsity levels, and proposed a paradigm to select reasonable sparsity regularization parameters. The stability of interesting components extraction from fourteen subjects’ data was deeply analyzed. Our results demonstrate that appropriate sparsity regularization can increase the stability of interesting components significantly and remove weak components at the same time. peerReviewed

In recent decades, event-related potentials have been used for the clinical electrophysiological assessment of patients with disorders of consciousness (DOCs). In this paper, an oddball paradigm with two types of frequencydeviant stimulus (standard stimuli were pure tones of 1000 Hz; small deviant stimuli were pure tones of 1050 Hz; large deviant stimuli were pure tones of 1200 Hz) was applied to elicit mismatch negativity (MMN) in 30 patients with DOCs diagnosed using the JFK Coma Recovery ScaleRevised (CRS-R). The results showed that the peak amplitudes of MMN elicited by both large and small deviant stimuli were significantly different from baseline. In terms of the spatial properties of MMN, a significant interaction effect between conditions (small and large deviant stimuli) and electrode nodes was centered at the frontocentral area. Furthermore, correlation coefficients were calculated between MMN amplitudes and CRS-R scores for each electrode among all participants to generate topographic maps. Meanwhile, a significant negative correlation between the MMN amplitudes elicited by large deviant stimuli and the CRS-R scores was also found at the frontocentral area. In consequence, our results combine the above spatial properties of MMN in patients with DOCs, and provide a more precise location (frontocentral area) at which to evaluate the correlation between clinical electrophysiological assessment and the level of consciousness. peerReviewed

Electroencephalography (EEG) is one fundamental tool for functional brain imaging. EEG signals tend to be represented by a vector or a matrix to facilitate data processing and analysis with generally understood methodologies like time-series analysis, spectral analysis and matrix decomposition. Indeed, EEG signals are often naturally born with more than two modes of time and space, and they can be denoted by a multi-way array called as tensor. This review summarizes the current progress of tensor decomposition of EEG signals with three aspects. The first is about the existing modes and tensors of EEG signals. Second, two fundamental tensor decomposition models, canonical polyadic decomposition (CPD, it is also called parallel factor analysis-PARAFAC) and Tucker decomposition, are introduced and compared. Moreover, the applications of the two models for EEG signals are addressed. Particularly, the determination of the number of components for each mode is discussed. Finally, the N-way partial least square and higherorder partial least square are described for a potential trend to process and analyze brain signals of two modalities simultaneously peerReviewed

Emotional faces can serve as distractors for visual working memory (VWM) tasks. An event-related potential called contralateral delay activity (CDA) can measure the filtering efficiency of face distractors. Previous studies have investigated the influence of VWM capacity on filtering efficiency of simple neutral distractors but not of face distractors. We measured the CDA indicative of emotional face filtering during a VWM task related to facial identity. VWM capacity was measured in a separate colour change detection task, and participants were divided to high- and low-capacity groups. The high-capacity group was able to filter out distractors similarly irrespective of its facial emotion. In contrast, the low-capacity group failed in filtering the neutral and angry face distractors, while the filtering was efficient for the happy face distractors. The results indicate that potentially threatening faces are particularly difficult to filter if VWM capacity is limited. peerReviewed

Driving mental fatigue is a contributing factor that causes thousands of traffic accidents. Functional brain networks are supposed to reflect the interaction dynamics between different brain regions. To investigate the interactions among distributed brain regions of drivers, we constructed binary brain networks from EEG data of the mental fatigue induced by the simulated driving task. Clustering coefficient, characteristic path length and global efficiency served as statistical network characteristics. Based on the network characteristic analysis, a calculation method of fatigue index was proposed. The results showed that the number of the brain network links decreases with the accumulation of the fatigue. The fatigue index embodied the risk of driving fatigue.