A novel DRL-guided sparse voxel decoding model for reconstructing perceived images from brain activity.

BACKGROUND: Due to the sparse encoding character of the human visual cortex and the scarcity of paired training samples for {images, fMRIs}, voxel selection is an effective means of reconstructing perceived images from fMRI. However, the existing data-driven voxel selection methods have not achieved satisfactory results. NEW METHOD: Here, a novel deep reinforcement learning-guided sparse voxel (DRL-SV) decoding model is proposed to reconstruct perceived images from fMRI. We innovatively describe voxel selection as a Markov decision process (MDP), training agents to select voxels that are highly involved in specific visual encoding. RESULTS: Experimental results on two public datasets verify the effectiveness of the proposed DRL-SV, which can accurately select voxels highly involved in neural encoding, thereby improving the quality of visual image reconstruction. COMPARISON WITH EXISTING METHODS: We qualitatively and quantitatively compared our results with the state-of-the-art (SOTA) methods, getting better reconstruction results. We compared the proposed DRL-SV with traditional data-driven baseline methods, obtaining sparser voxel selection results, but better reconstruction performance. CONCLUSIONS: DRL-SV can accurately select voxels involved in visual encoding on few-shot, compared to data-driven voxel selection methods. The proposed decoding model provides a new avenue to improving the image reconstruction quality of the primary visual cortex.

OxcarNet: sinc convolutional network with temporal and channel attention for prediction of oxcarbazepine monotherapy responses in patients with newly diagnosed epilepsy.

Objective.Monotherapy with antiepileptic drugs (AEDs) is the preferred strategy for the initial treatment of epilepsy. However, an inadequate response to the initially prescribed AED is a significant indicator of a poor long-term prognosis, emphasizing the importance of precise prediction of treatment outcomes with the initial AED regimen in patients with epilepsy.Approach. We introduce OxcarNet, an end-to-end neural network framework developed to predict treatment outcomes in patients undergoing oxcarbazepine monotherapy. The proposed predictive model adopts a Sinc Module in its initial layers for adaptive identification of discriminative frequency bands. The derived feature maps are then processed through a Spatial Module, which characterizes the scalp distribution patterns of the electroencephalography (EEG) signals. Subsequently, these features are fed into an attention-enhanced Temporal Module to capture temporal dynamics and discrepancies. A channel module with an attention mechanism is employed to reveal inter-channel dependencies within the output of the Temporal Module, ultimately achieving response prediction. OxcarNet was rigorously evaluated using a proprietary dataset of retrospectively collected EEG data from newly diagnosed epilepsy patients at Nanjing Drum Tower Hospital. This dataset included patients who underwent long-term EEG monitoring in a clinical inpatient setting.Main results.OxcarNet demonstrated exceptional accuracy in predicting treatment outcomes for patients undergoing Oxcarbazepine monotherapy. In the ten-fold cross-validation, the model achieved an accuracy of 97.27%, and in the validation involving unseen patient data, it maintained an accuracy of 89.17%, outperforming six conventional machine learning methods and three generic neural decoding networks. These findings underscore the model's effectiveness in accurately predicting the treatment responses in patients with newly diagnosed epilepsy. The analysis of features extracted by the Sinc filters revealed a predominant concentration of predictive frequencies in the high-frequency range of the gamma band.Significance. The findings of our study offer substantial support and new insights into tailoring early AED selection, enhancing the prediction accuracy for the responses of AEDs.

Lightweight Source-Free Domain Adaptation based on Adaptive Euclidean Alignment for Brain-Computer Interfaces.

For privacy protection of subjects in electroencephalogram (EEG)-based brain-computer interfaces (BCIs), using source-free domain adaptation (SFDA) for cross-subject recognition has proven to be highly effective. However, updating and storing a model trained on source subjects for each new subject can be inconvenient. This paper extends Euclidean alignment (EA) to propose adaptive Euclidean alignment (AEA), which learns a projection matrix to align the distribution of the target subject with the source subjects, thus eliminating domain drift issues and improving model classification performance of subject-independent BCIs. Combining the proposed AEA with various existing SFDA methods, such as SHOT, GSFDA, and NRC, this paper presents three new methods: AEA-SHOT, AEA-GSFDA, and AEA-NRC. In our experimental studies, these AEA-based SFDA methods were applied to four well-known deep learning models (i.e., EEGNet, Shallow ConvNet, Deep ConvNet, and MSFBCNN) on two motor imagery (MI) datasets, one event-related potential (ERP) dataset and one steady-state visual evoked potentials (SSVEP) dataset. The advanced cross-subject EEG classification performance demonstrates the efficacy of our proposed methods. For example, AEA-SHOT achieved the best average accuracy of 81.4% on the PhysioNet dataset.

The Role of EEG microstates in predicting oxcarbazepine treatment outcomes in patients with newly-diagnosed focal epilepsy.

PURPOSE: Microstates represent the global and topographical distribution of electrical brain activity from scalp-recorded EEG. This study aims to explore EEG microstates of patients with focal epilepsy prior to medication, and employ extracted microstate metrics for predicting treatment outcomes with Oxcarbazepine monotherapy. METHODS: This study involved 25 newly-diagnosed focal epilepsy patients (13 females), aged 12 to 68, with various etiologies. Patients were categorized into Non-Seizure-Free (NSF) and Seizure-Free (SF) groups according to their first follow-up outcomes. From pre-medication EEGs, four representative microstates were identified by using clustering. The temporal parameters and transition probabilities of microstates were extracted and analyzed to discern group differences. With generating sample method, Support Vector Machine (SVM), Logistic Regression (LR), and Naïve Bayes (NB) classifiers were employed for predicting treatment outcomes. RESULTS: In the NSF group, Microstate 1 (MS1) exhibited a significantly higher duration (mean±std. = 0.092±0.008 vs. 0.085±0.008, p = 0.047), occurrence (mean±std. = 2.587±0.334 vs. 2.260±0.278, p = 0.014), and coverage (mean±std. = 0.240±0.046 vs. 0.194±0.040, p = 0.014) compared to the SF group. Additionally, the transition probabilities from Microstate 2 (MS2) and Microstate 3 (MS3) to MS1 were increased. In MS2, the NSF group displayed a stronger correlation (mean±std. = 0.618±0.025 vs. 0.571±0.034, p < 0.001) and a higher global explained variance (mean±std. = 0.083±0.035 vs. 0.055±0.023, p = 0.027) than the SF group. Conversely, Microstate 4 (MS4) in the SF group demonstrated significantly greater coverage (mean±std. = 0.388±0.074 vs. 0.334±0.052, p = 0.046) and more frequent transitions from MS2 to MS4, indicating a distinct pattern. Temporal parameters contribute major predictive role in predicting treatment outcomes of Oxcarbazepine, with area under curves (AUCs) of 0.95, 0.70, and 0.86, achieved by LR, NB and SVM, respectively. CONCLUSION: This study underscores the potential of EEG microstates as predictive biomarkers for Oxcarbazepine treatment responses in newly-diagnosed focal epilepsy patients.

Brain connectivity patterns derived from aging-related alterations in dynamic brain functional networks and their potential as features for brain age classification.

Objective.Recent studies have demonstrated that the analysis of brain functional networks (BFNs) is a powerful tool for exploring brain aging and age-related neurodegenerative diseases. However, investigating the mechanism of brain aging associated with dynamic BFN is still limited. The purpose of this study is to develop a novel scheme to explore brain aging patterns by constructing dynamic BFN using resting-state functional magnetic resonance imaging data.Approach.A dynamic sliding-windowed non-negative block-diagonal representation (dNBDR) method is proposed for constructing dynamic BFN, based on which a collection of dynamic BFN measures are suggested for examining age-related differences at the group level and used as features for brain age classification at the individual level.Results.The experimental results reveal that the dNBDR method is superior to the sliding time window with Pearson correlation method in terms of dynamic network structure quality. Additionally, significant alterations in dynamic BFN structures exist across the human lifespan. Specifically, average node flexibility and integration coefficient increase with age, while the recruitment coefficient shows a decreased trend. The proposed feature extraction scheme based on dynamic BFN achieved the highest accuracy of 78.7% in classifying three brain age groups.Significance. These findings suggest that dynamic BFN measures, dynamic community structure metrics in particular, play an important role in quantitatively assessing brain aging.

Reliable and fast automatic artifact rejection of Long-Term EEG recordings based on Isolation Forest.

Long-term electroencephalogram (Long-Term EEG) has the capacity to monitor over a long period, making it a valuable tool in medical institutions. However, due to the large volume of patient data, selecting clean data segments from raw Long-Term EEG for further analysis is an extremely time-consuming and labor-intensive task. Furthermore, the various actions of patients during recording make it difficult to use algorithms to denoise part of the EEG data, and thus lead to the rejection of these data. Therefore, tools for the quick rejection of heavily corrupted epochs in Long-Term EEG records are highly beneficial. In this paper, a new reliable and fast automatic artifact rejection method for Long-Term EEG based on Isolation Forest (IF) is proposed. Specifically, the IF algorithm is repetitively applied to detect outliers in the EEG data, and the boundary of inliers is promptly adjusted by using a statistical indicator to make the algorithm proceed in an iterative manner. The iteration is terminated when the distance metric between clean epochs and artifact-corrupted epochs remains unchanged. Six statistical indicators (i.e., min, max, median, mean, kurtosis, and skewness) are evaluated by setting them as centroid to adjust the boundary during iteration, and the proposed method is compared with several state-of-the-art methods on a retrospectively collected dataset. The experimental results indicate that utilizing the min value of data as the centroid yields the most optimal performance, and the proposed method is highly efficacious and reliable in the automatic artifact rejection of Long-Term EEG, as it significantly improves the overall data quality. Furthermore, the proposed method surpasses compared methods on most data segments with poor data quality, demonstrating its superior capacity to enhance the data quality of the heavily corrupted data. Besides, owing to the linear time complexity of IF, the proposed method is much faster than other methods, thus providing an advantage when dealing with extensive datasets.

Motor Imagery EEG Classification Based on a Weighted Multi-Branch Structure Suitable for Multisubject Data.

OBJECTIVE: Electroencephalogram (EEG) signal recognition based on deep learning technology requires the support of sufficient data. However, training data scarcity usually occurs in subject-specific motor imagery tasks unless multisubject data can be used to enlarge training data. Unfortunately, because of the large discrepancies between data distributions from different subjects, model performance could only be improved marginally or even worsened by simply training on multisubject data. METHOD: This article proposes a novel weighted multi-branch (WMB) structure for handling multisubject data to solve the problem, in which each branch is responsible for fitting a pair of source-target subject data and adaptive weights are used to integrate all branches or select branches with the largest weights to make the final decision. The proposed WMB structure was applied to six well-known deep learning models (EEGNet, Shallow ConvNet, Deep ConvNet, ResNet, MSFBCNN, and EEG_TCNet) and comprehensive experiments were conducted on EEG datasets BCICIV-2a, BCICIV-2b, high gamma dataset (HGD) and two supplementary datasets. RESULT: Superior results against the state-of-the-art models have demonstrated the efficacy of the proposed method in subject-specific motor imagery EEG classification. For example, the proposed WMB_EEGNet achieved classification accuracies of 84.14%, 90.23%, and 97.81% on BCICIV-2a, BCICIV-2b and HGD, respectively. CONCLUSION: It is clear that the proposed WMB structure is capable to make good use of multisubject data with large distribution discrepancies for subject-specific EEG classification.

Block Distributed Joint Temporal-Frequency-Phase Modulation for Steady-State Visual Evoked Potential Based Brain-Computer Interface With a Limited Number of Frequencies.

How to encode as many targets as possible with limited frequency resources is a grave problem that restricts the application of steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs). In the current study, we propose a novel block-distributed joint temporal-frequency-phase modulation method for a virtual speller based on SSVEP-based BCI. A 48-target speller keyboard array is virtually divided into eight blocks and each block contains six targets. The coding cycle consists of two sessions: in the first session, each block flashes at different frequencies while all the targets in the same block flicker at the same frequency; in the second session, all the targets in the same block flash at different frequencies. Using this method, 48 targets can be coded with only eight frequencies, which greatly reduces the frequency resources required, and average accuracies of 86.81  ± 9.41% and 91.36  ± 6.41% were obtained for both the offline and online experiments. This study provides a new coding approach for a large number of targets with a small number of frequencies, which can further expand the application potential of SSVEP-based BCI.

Recognition of unilateral lower limb movement based on EEG signals with ERP-PCA analysis.

It has been confirmed that motor imagery (MI) and motor execution (ME) share a subset of mechanisms underlying motor cognition. In contrast to the well-studied laterality of upper limb movement, the laterality hypothesis of lower limb movement also exists, but it needs to be characterized by further investigation. This study used electroencephalographic (EEG) recordings of 27 subjects to compare the effects of bilateral lower limb movement in the MI and ME paradigms. Event-related potential (ERP) recorded was decomposed into meaningful and useful representatives of the electrophysiological components, such as N100 and P300. Principal components analysis (PCA) was used to trace the characteristics of ERP components temporally and spatially, respectively. The hypothesis of this study is that the functional opposition of unilateral lower limbs of MI and ME should be reflected in the different alterations of the spatial distribution of lateralized activity. Meanwhile, the significant ERP-PCA components of the EEG signals as identifiable feature sets were applied with support vector machine to identify left and right lower limb movement tasks. The average classification accuracy over all subjects is up to 61.85% for MI and 62.94% for ME. The proportion of subjects with significant results are 51.85% for MI and 59.26% for ME, respectively. Therefore, a potential new classification model for lower limb movement can be applied on brain computer interface (BCI) systems in the future.

Early neural markers for individual difference in mathematical achievement determined from rational number processing.

The neural markers for individual differences in mathematical achievement have been studied extensively using magnetic resonance imaging; however, high temporal resolution electrophysiological evidence for individual differences in mathematical achievement require further elucidation. This study evaluated the event-related potential (ERP) when 48 college students with high or low mathematical achievement (HA vs. LA) matched non-symbolic and symbolic rational numbers. Behavioral results indicated that HA students had better performance in the discretized non-symbolic matching, although the two groups showed similar performances in the continuous matching. ERP data revealed that even before non-symbolic stimulus presentation, HA students had greater Bereitschaftspotential (BP) amplitudes over posterior central electrodes. After the presentation of non-symbolic numbers, HA students had larger N1 amplitudes at 160 ms post-stimulus, over left-lateralized parieto-occipital electrodes. After the presentation of symbolic numbers, HA students displayed more profound P1 amplitudes at 100 ms post-stimulus, over left parietal electrodes. Furthermore, larger BP and N1 amplitudes were associated with the shorter reaction times, and larger P1 amplitudes corresponded to lower error rates. The BP effect could indicate preparation processing, and early left-lateralized N1 and P1 effects could reflect the non-symbolic and symbolic number processing along the dorsal neural pathways. These results suggest that the left-lateralized P1 and N1 components elicited by matching non-symbolic and symbolic rational numbers can be considered as neurocognitive markers for individual differences in mathematical achievement.

Capped L21-norm-based common spatial patterns for EEG signals classification applicable to BCI systems.

The common spatial patterns (CSP) technique is an effective strategy for the classification of multichannel electroencephalogram (EEG) signals. However, the objective function expression of the conventional CSP algorithm is based on the L2-norm, which makes the performance of the method easily affected by outliers and noise. In this paper, we consider a new extension to CSP, which is termed capped L21-norm-based common spatial patterns (CCSP-L21), by using the capped L21-norm rather than the L2-norm for robust modeling. L21-norm considers the L1-norm sum which largely alleviates the influence of outliers and noise for the sake of robustness. The capped norm is further used to mitigate the effects of extreme outliers whose signal amplitude is much higher than that of the normal signal. Moreover, a non-greedy iterative procedure is derived to solve the proposed objective function. The experimental results show that the proposed method achieves the highest average recognition rates on the three real data sets of BCI competitions, which are 91.67%, 85.07%, and 82.04%, respectively. Capped L21-norm-based common spatial patterns-a robust model for EEG signals classification.

Effective Connectivity Analysis and Classification of Action Observation From Different Perspectives: An fMRI Study.

OBJECTIVE: Analyzing the effective connectivity characteristics of brain networks in the process of action observation is helpful for understanding the neurodynamic mechanisms during action observation. METHOD: In this study, functional magnetic resonance imaging (fMRI) images were obtained from 20 participants who performed hand-object interaction observation tasks from the first-person perspective (1PP) and third-person perspective (3PP). On the basis of a meta-analysis, 11 key brain regions were extracted as nodes to build an action observation network. The weighted and directional connections between all of the nodes were investigated using partial directional coherence (PDC) analysis in five narrow frequency bands. RESULTS: The statistical analysis indicated that the ultra-low frequency band ( ≤ 0.04 Hz) exhibited significant activation compared with other frequency bands for both 1PP and 3PP. In addition, it was found that 3PP induced significantly stronger brain activation than 1PP in the ultra-low frequency band. Moreover, this study attempted to classify fMRI data corresponding to different perspectives using brain network features. A comparative analysis revealed that the weighted and binary PDC matrix methods achieved classification accuracies of 86.3% and 80.8%, respectively. SIGNIFICANCE: The weighted PDC analysis exhibits a more comprehensive understanding of neural mechanisms during action observation in different visual perspectives. It also has potential applications value in human-computer interaction in the future.

Chiral Assembly and Recognition of Seven Copper (II) Coordination Polymers from Tartaric Acid Derivative Ligands.

A pair of enantiomeric ligands, (2R,3R)-dibenzyl-2,3-bis(isonicotinoyloxy)succinate ((R,R)-L) and (2S,3S)-dibenzyl-2,3-bis(isonicotinoyloxy)succinate ((S,S)-L), are designed and synthesized. Seven copper (II) coordination polymers {[Cu((R,R)-L)Br2 (THF)] ⋅ CH3 CN} n (1 a) and {[Cu((S,S)-L)Br2 (THF)] ⋅ CH3 CN}n (1 b), {[Cu((R,R)-L)Cl2 (THF)] ⋅ CH3 CN}n (2 a) and {[Cu((S,S)-L)Cl2 (THF)] ⋅ CH3 CN}n (2 b), {[Cu((R,R)-L)(NO3 )2 (CH3 CN)]}n (3 a) and {[Cu((S,S)-L)(NO3 )2 (CH3 CN)]}n (3 b), {[Cu((R,R)-L)2 (CH3 CN)2 ](ClO4 )2 ⋅ 3CH3 CN}n (4) were obtained through the assemblies with CuBr2 , CuCl2 ⋅ 2H2 O, Cu(NO3 )2 ⋅ 3H2 O, Cu(ClO4 )2 ⋅ 6H2 O, respectively. Single-crystal X-ray diffraction and circular dichroism analysis demonstrate that 1 a-3 a, 1 b-3 b have a mono chiral one-dimensional (1D) chain-like spiral structure, while 4 have 1D chain-like structure whose metal centers have chiral propeller coordination environment. Ligand structure, anions and solvent systems have a regulatory effect on the formation of chiral helical structure. Further investigation has proved that 1 a can be used as circular dichroism spectrum probe for monitoring L-/D-cysteine and L-/D-penicillamine configuration and concentration in aqueous media based on ligand interchange mechanism.

Reconfiguration of Brain Network Dynamics in Autism Spectrum Disorder Based on Hidden Markov Model.

Autism spectrum disorder (ASD) is a group of complex neurodevelopment disorders characterized by altered brain connectivity. However, the majority of neuroimaging studies for ASD focus on the static pattern of brain function and largely neglect brain activity dynamics, which might provide deeper insight into the underlying mechanism of brain functions for ASD. Therefore, we proposed a framework with Hidden Markov Model (HMM) analysis for resting-state functional MRI (fMRI) from a large multicenter dataset of 507 male subjects. Specifically, the 507 subjects included 209 subjects with ASD and 298 well-matched health controls across 14 sites from the Autism Brain Imaging Data Exchange (ABIDE). Based on the HMM, we can identify the recurring brain function networks over time across ASD and healthy controls (HCs). Then we assessed the dynamical configuration of the whole-brain networks and further analyzed the community structure of transitions across the brain states. Based on the 19 HMM states, we found that the global temporal statistics of the specific HMM states (including fractional occupancies and lifetimes) were significantly altered in ASD compared to HCs. These specific HMM states were characterized by the activation pattern of default mode network (DMN), sensory processing networks [including visual network, auditory network, and sensory and motor network (SMN)]. Meanwhile, we also find that the specific modules of transitions between states were closely related to ASD. Our findings indicate the temporal reconfiguration of the brain network in ASD and provide novel insights into the dynamics of the whole-brain networks for ASD.

Biomarkers Derived from Alterations in Overlapping Community Structure of Resting-state Brain Functional Networks for Detecting Alzheimer's Disease.

Recent studies show that overlapping community structure is an important feature of the brain functional network. However, alterations in such overlapping community structure in Alzheimer's disease (AD) patients have not been examined yet. In this study, we investigate the overlapping community structure in AD by using resting-state functional magnetic resonance imaging (rs-fMRI) data. The collective sparse symmetric non-negative matrix factorization (cssNMF) is adopted to detect the overlapping community structure. Experimental results on 28 AD patients and 32 normal controls (NCs) from the ADNI2 dataset show that the two groups have remarkable differences in terms of the optimal number of communities, the hierarchy of communities detected at different scales, network functional segregation, and nodal functional diversity. In particular, the frontal-parietal and basal ganglia networks exhibit significant differences between the two groups. A machine learning framework proposed in this paper for AD detection achieved an accuracy of 76.7% when using the detected community strengths of the frontal-parietal and basal ganglia networks only as input features. These findings provide novel insights into the understanding of pathological changes in the brain functional network organization of AD and show the potential of the community structure-related features for AD detection.

Euler common spatial patterns for EEG classification.

The technique of common spatial patterns (CSP) is a widely used method in the field of feature extraction of electroencephalogram (EEG) signals. Motivated by the fact that a cosine distance can enlarge the distance between samples of different classes, we propose the Euler CSP (e-CSP) for the feature extraction of EEG signals, and it is then used for EEG classification. The e-CSP is essentially the conventional CSP with the Euler representation. It includes the following two stages: each sample value is first mapped into a complex space by using the Euler representation, and then the conventional CSP is performed in the Euler space. Thus, the e-CSP is equivalent to applying the Euler representation as a kernel function to the input of the CSP. It is computationally as straightforward as the CSP. However, it extracts more discriminative features from the EEG signals. Extensive experimental results illustrate the discrimination ability of the e-CSP.

Action Intention Understanding EEG Signal Classification Based on Improved Discriminative Spatial Patterns.

OBJECTIVE: Action intention understanding EEG signal classification is indispensable for investigating human-computer interactions and intention understanding mechanisms. Numerous investigations on classification tasks extract classification features by using graph theory metrics; however, the classification results are usually not good. METHOD: To effectively implement the task of action intention understanding EEG signal classification, we proposed a new feature extraction method by improving discriminative spatial patterns. RESULTS: The whole frequency band and fusion band achieved satisfactory classification accuracies. Compared with other authors' methods for action intention understanding EEG signal classification, the new method performs more satisfactorily in some aspects. CONCLUSIONS: The new feature extraction method not only effectively avoids complex values when solving the generalized eigenvalue problem but also perfectly realizes appreciable classification accuracies. Fusing the classification features of different frequency bands is a useful strategy for the classification task.

Neural Dissociations between Magnitude Processing of Fractions and Decimals.

Fraction and decimal magnitude processing are crucial for mathematic achievement. Previous neuroimaging results showed that fraction and decimal processing activated both overlapping and distinct neural substrates, but temporal dissociations between fraction and decimal processing remained unknown. This event-related potential (ERP) study explored differences in neural activities between magnitude processing of fractions and decimals, by examining the notation effect (fraction vs. decimal) and distance effect (far vs. close) on early components of P1/N1, P2 and N2. Results showed that decimals elicited larger N1 and smaller P1 than fractions at the parietal region. Fractions demonstrated the significant distance effect on fronto-central P2 while decimals showed the distance effect on left anterior N2. ERP results reflect distinct processing of identification and semantic access stages between fractions and decimals. Identification is located at the visual-related region with enhanced perception acuity and identification efficiency for decimals. Semantic access activates the fronto-central region associated with elaborative magnitude manipulation for fractions, while semantic access reflects automatic phonological retrieval for decimals. Our findings disintegrate the magnitude processing of fractions and decimals from identification to magnitude processing. It reveals that temporal discrepancies between fraction and decimal magnitude processing appear as early as post-stimulus 100 ms.

A novel index of functional connectivity: phase lag based on Wilcoxon signed rank test.

Phase synchronization has been an effective measurement of functional connectivity, detecting similar dynamics over time among distinct brain regions. However, traditional phase synchronization-based functional connectivity indices have been proved to have some drawbacks. For example, the phase locking value (PLV) index is sensitive to volume conduction, while the phase lag index (PLI) and the weighted phase lag index (wPLI) are easily affected by noise perturbations. In addition, thresholds need to be applied to these indices to obtain the binary adjacency matrix that determines the connections. However, the selection of the thresholds is generally arbitrary. To address these issues, in this paper we propose a novel index of functional connectivity, named the phase lag based on the Wilcoxon signed-rank test (PLWT). Specifically, it characterizes the functional connectivity based on the phase lag with a weighting procedure to reduce the influence of volume conduction and noise. Besides, it automatically identifies the important connections without relying on thresholds, by taking advantage of the framework of the Wilcoxon signed-rank test. The performance of the proposed PLWT index is evaluated on simulated electroencephalograph (EEG) datasets, as well as on two resting-state EEG datasets. The experimental results on the simulated EEG data show that the PLWT index is robust to volume conduction and noise. Furthermore, the brain functional networks derived by PLWT on the real EEG data exhibit a reasonable scale-free characteristic and high test-retest (TRT) reliability of graph measures. We believe that the proposed PLWT index provides a useful and reliable tool to identify the underlying neural interactions, while effectively diminishing the influence of volume conduction and noise.

Multilinear Discriminative Spatial Patterns for Movement-Related Cortical Potential Based on EEG Classification with Tensor Representation.

The discriminative spatial patterns (DSP) algorithm is a classical and effective feature extraction technique for decoding of voluntary finger premovements from electroencephalography (EEG). As a purely data-driven subspace learning algorithm, DSP essentially is a spatial-domain filter and does not make full use of the information in frequency domain. The paper presents multilinear discriminative spatial patterns (MDSP) to derive multiple interrelated lower dimensional discriminative subspaces of low frequency movement-related cortical potential (MRCP). Experimental results on two finger movement tasks' EEG datasets demonstrate the effectiveness of the proposed MDSP method.