Search

Motor imagery-based brain-computer interfaces (MI-BCIs) features are generally extracted from a wide fixed frequency band and time window of EEG signal. The performance suffers from individual differences in corresponding time to MI tasks. In order to solve the problem, in this study, we propose a novel method named Riemannian sparse optimization and Dempster-Shafer fusion of multi-time-frequency patterns (RSODSF) to enhance the decoding efficiency. First, we effectively combine the Riemannian geometry of the spatial covariance matrix with sparse optimization to extract more robust and distinct features. Second, the Dempster-Shafer theory is introduced and used to fuse each time window after sparse optimization of Riemannian features. Besides, the probabilistic values of the support vector machine (SVM) are obtained and transformed to effectively fuse multiple classifiers to leverage potential soft information of multiple trained SVM. The open-access BCI Competition IV dataset IIa and Competition III dataset IIIa are employed to evaluate the performance of the proposed RSODSF. It achieves higher average accuracy (89.7% and 96.8%) than state-of-the-art methods. The improvement over the common spatial patterns (SFBCSP) are respectively 9.9% and 12.4% (p < 0.01, paired t-test). These results show that our proposed RSODSF method is a promising candidate for the performance improvement of MI-BCI. [ABSTRACT FROM AUTHOR]

Though Electroencephalogram (EEG) could objectively reflect emotional states of our human beings, its weak, non-stationary, and low signal-to-noise properties easily cause the individual differences. To enhance the universality of affective brain-computer interface systems, transfer learning has been widely used to alleviate the data distribution discrepancies among subjects. However, most of existing approaches focused mainly on the domain-invariant feature learning, which is not unified together with the recognition process. In this paper, we propose a joint feature adaptation and graph adaptive label propagation model (JAGP) for cross-subject emotion recognition from EEG signals, which seamlessly unifies the three components of domain-invariant feature learning, emotional state estimation and optimal graph learning together into a single objective. We conduct extensive experiments on two benchmark SEED_IV and SEED_V data sets and the results reveal that 1) the recognition performance is greatly improved, indicating the effectiveness of the triple unification mode; 2) the emotion metric of EEG samples are gradually optimized during model training, showing the necessity of optimal graph learning, and 3) the projection matrix-induced feature importance is obtained based on which the critical frequency bands and brain regions corresponding to subject-invariant features can be automatically identified, demonstrating the superiority of the learned shared subspace. [ABSTRACT FROM AUTHOR]

Electroencephalogram(EEG) signals are generated from central nervous system which are difficult to disguise, leading to its popularity in emotion recognition. Recently,semi-supervisedlearning exhibits promisingemotion recognition performance by involving unlabeled EEG data into model training. However, if we first build a graph to characterize the sample similarities and then perform label propagation on this graph, these two steps cannotwell collaborate with each other. In this paper, we propose an OptimalGraph coupledSemi-Supervised Learning (OGSSL) model for EEG emotion recognition by unifying the adaptive graph learning and emotion recognition into a single objective. Besides, we improve the label indicator matrix of unlabeledsamples in order to directly obtain theiremotional states. Moreover, the key EEG frequency bands and brain regions in emotion expression are automatically recognized by the projectionmatrix of OGSSL. Experimental results on the SEED-IV data set demonstrate that 1) OGSSL achieves excellent average accuracies of 76.51%, 77.08% and 81.29% in three cross-sessionemotion recognition tasks, 2) OGSSL is competent for discriminative EEG feature selection in emotion recognition, and 3) the Gamma frequency band, the left/righttemporal, prefrontal,and (central) parietal lobes are identified to be more correlated with the occurrence of emotions. [ABSTRACT FROM AUTHOR]

It is difficult to identify optimal cut-off frequencies for filters used with the common spatial pattern (CSP) method in motor imagery (MI)-based brain-computer interfaces (BCIs). Most current studies choose filter cut-frequencies based on experience or intuition, resulting in sub-optimal use of MI-related spectral information in the electroencephalography (EEG). To improve information utilization, we propose a SincNet-based hybrid neural network (SHNN) for MI-based BCIs. First, raw EEG is segmented into different time windows and mapped into the CSP feature space. Then, SincNets are used as filter bank band-pass filters to automatically filter the data. Next, we used squeeze-and-excitation modules to learn a sparse representation of the filtered data. The resulting sparse data were fed into convolutional neural networks to learn deep feature representations. Finally, these deep features were fed into a gated recurrent unit module to seek sequential relations, and a fully connected layer was used for classification. We used the BCI competition IV datasets 2a and 2b to verify the effectiveness of our SHNN method. The mean classification accuracies (kappa values) of our SHNN method are 0.7426 (0.6648) on dataset 2a and 0.8349 (0.6697) on dataset 2b, respectively. The statistical test results demonstrate that our SHNN can significantly outperform other state-of-the-art methods on these datasets. [ABSTRACT FROM AUTHOR]

Schizophrenia seriously affects the quality of life. To date, both simple (e.g., linear discriminant analysis) and complex (e.g., deep neural network) machine-learning methods have been utilized to identify schizophrenia based on functional connectivity features. The existing simple methods need two separate steps (i.e., feature extraction and classification) to achieve the identification, which disables simultaneous tuning for the best feature extraction and classifier training. The complex methods integrate two steps and can be simultaneously tuned to achieve optimal performance, but these methods require a much larger amount of data for model training. To overcome the aforementioned drawbacks, we proposed a multikernel capsule network (MKCapsnet), which was developed by considering the brain anatomical structure. Kernels were set to match partition sizes of the brain anatomical structure in order to capture interregional connectivities at the varying scales. With the inspiration of the widely used dropout strategy in deep learning, we developed capsule dropout in the capsule layer to prevent overfitting of the model. The comparison results showed that the proposed method outperformed the state-of-the-art methods. Besides, we compared performances using different parameters and illustrated the routing process to reveal characteristics of the proposed method. MKCapsnet is promising for schizophrenia identification. Our study first utilized the capsule neural network for analyzing functional connectivity of magnetic resonance imaging (MRI) and proposed a novel multikernel capsule structure with the consideration of brain anatomical parcellation, which could be a new way to reveal brain mechanisms. In addition, we provided useful information in the parameter setting, which is informative for further studies using a capsule network for other neurophysiological signal classification. [ABSTRACT FROM AUTHOR]

The motor imagery (MI) based brain-computer interfaces (BCIs) have been proposed as a potential physical rehabilitation technology. However, the low classification accuracy achievable with MI tasks is still a challenge when building effective BCI systems. We propose a novel MI classification model based on measurement of functional connectivity between brain regions and graph theory. Specifically, motifs describing local network structures in the brain are extracted from functional connectivity graphs. A graph embedding model called Ego-CNNs is then used to build a classifier, which can convert the graph from a structural representation to a fixed-dimensional vector for detecting critical structure in the graph. We validate our proposed method on four datasets, and the results show that our proposed method produces high classification accuracies in two-class classification tasks (92.8% for dataset 1, 93.4% for dataset 2, 96.5% for dataset 3, and 80.2% for dataset 4) and multiclass classification tasks (90.33% for dataset 1). Our proposed method achieves a mean Kappa value of 0.88 across nine participants, which is superior to other methods we compared it to. These results indicate that there is a local structural difference in functional connectivity graphs extracted under different motor imagery tasks. Our proposed method has great potential for motor imagery classification in future studies. [ABSTRACT FROM AUTHOR]

The common spatial patterns (CSP) algorithm is the most popular spatial filtering method applied to extract electroencephalogram (EEG) features for motor imagery (MI) based brain-computer interface (BCI) systems. The effectiveness of the CSP algorithm depends on optimal selection of the frequency band and time window from the EEG. Many algorithms have been designed to optimize frequency band selection for CSP, while few algorithms seek to optimize the time window. This study proposes a novel framework, termed common time-frequency-spatial patterns (CTFSP), to extract sparse CSP features from multi-band filtered EEG data in multiple time windows. Specifically, the whole MI period is first segmented into multiple subseries using a sliding time window approach. Then, sparse CSP features are extracted from multiple frequency bands in each time window. Finally, multiple support vector machine (SVM) classifiers with the Radial Basis Function (RBF) kernel are trained to identify the MI tasks and the voting result of these classifiers determines the final output of the BCI. This study applies the proposed CTFSP algorithm to three public EEG datasets (BCI competition III dataset IVa, BCI competition III dataset IIIa, and BCI competition IV dataset 1) to validate its effectiveness, compared against several other state-of-the-art methods. The experimental results demonstrate that the proposed algorithm is a promising candidate for improving the performance of MI-BCI systems. [ABSTRACT FROM AUTHOR]

In electroencephalography (EEG)-based affective brain–computer interfaces (aBCIs), there is a consensus that EEG features extracted from different frequency bands and channels have different abilities in emotion expression. Besides, EEG is so weak and non-stationary that easily causes distribution discrepancies for EEG data collected at different times; therefore, it is necessary to explore the affective activation patterns in cross-session emotion recognition. To address these two problems, we propose a self-weighted semi-supervised classification (SWSC) model in this article for joint EEG-based cross-session emotion recognition and affective activation patterns mining, whose merits include: 1) using both the labeled and unlabeled samples from different sessions for better capturing data characteristics; 2) introducing a self-weighted variable to learn the importance of EEG features adaptively and quantitatively; and 3) mining the activation patterns including the critical EEG frequency bands and channels automatically based on the learned self-weighted variable. Extensive experiments are conducted on the benchmark SEED_IV emotional dataset and SWSC obtained excellent average accuracies of 77.40%, 79.55%, and 81.52% in three cross-session emotion recognition tasks. Moreover, SWSC identifies that the Gamma frequency band contributes the most and the EEG channels in prefrontal, left/right temporal, and (central) parietal lobes are more important for cross-session emotion recognition. [ABSTRACT FROM AUTHOR]

Structured Tucker tensor decomposition models complete or incomplete multiway data sets (tensors), where the core tensor and the factor matrices can obey different constraints. The model includes block-term decomposition or canonical polyadic decomposition as special cases. We propose a very flexible optimization method for the structured Tucker decomposition problem, based on the second-order Levenberg-Marquardt optimization, using an approximation of the Hessian matrix by the Krylov subspace method. An algorithm with limited sensitivity of the decomposition is included. The proposed algorithm is shown to perform well in comparison to existing tensor decomposition methods. [ABSTRACT FROM AUTHOR]

Optimal rank selection is an important issue in tensor decomposition problems, especially for Tensor Train (TT) and Tensor Ring (TR) (also known as Tensor Chain) decompositions. In this paper, a new rank selection method for TR decomposition has been proposed for automatically finding near-optimal TR ranks, which result in a lower storage cost, especially for tensors with inexact TT or TR structures. In many of the existing approaches, TR ranks are determined in advance or by using truncated Singular Value Decomposition (t-SVD). There are also other approaches for selecting TR ranks adaptively. In our approach, the TR ranks are not determined in advance, but are increased gradually in each iteration until the model achieves a desired approximation accuracy. For this purpose, in each iteration, the sensitivity of the approximation error to each of the core tensors is measured and the core tensors with the highest sensitivity measures are selected and their sizes are increased. Simulation results confirmed that the proposed approach reduces the storage cost considerably and allows us to find optimal model in TR format, while preserving the desired accuracy of the approximation. [ABSTRACT FROM AUTHOR]

The performance of motor imagery (MI) based Brain-computer interfacing (BCI) is easily affected by noise and redundant information that exists in the multi-channel electroencephalogram (EEG). To solve this problem, many temporal and spatial feature based channel selection methods have been proposed. However, temporal and spatial features do not accurately reflect changes in the power of the oscillatory EEG. Thus, spectral features of MI-related EEG signals may be useful for channel selection. Bispectrum analysis is a technique developed for extracting non-linear and non-Gaussian information from non-linear and non-Gaussian signals. The features extracted from bispectrum analysis can provide frequency domain information about the EEG. Therefore, in this study, we propose a bispectrum-based channel selection (BCS) method for MI-based BCI. The proposed method uses the sum of logarithmic amplitudes (SLA) and the first order spectral moment (FOSM) features extracted from bispectrum analysis to select EEG channels without redundant information. Three public BCI competition datasets (BCI competition IV dataset 1, BCI competition III dataset IVa and BCI competition III dataset IIIa) were used to validate the effectiveness of our proposed method. The results indicate that our BCS method outperforms use of all channels (83.8% vs 69.4%, 86.3% vs 82.9% and 77.8% vs 68.2%, respectively). Furthermore, compared to the other state-of-the-art methods, our BCS method also can achieve significantly better classification accuracies for MI-based BCI (Wilcoxon signed test, p < 0.05). [ABSTRACT FROM AUTHOR]

Previous studies made progress in the early diagnosis of Alzheimer’s disease (AD) using electroencephalography (EEG) without considering EEG connectivity. To fill this gap, we explored significant differences between early AD patients and controls based on frequency domain and spatial properties using functional connectivity in mild cognitive impairment (MCI) and mild AD datasets. Four global metrics, network resilience, connection-level metrics and node versatility were used to distinguish between controls and patients. The results show that the main frequency bands that are different between MCI patients and controls are the $\theta $ and low $\alpha $ bands, and the differently affected brain areas are the frontal, left temporal and parietal areas. Compared to MCI patients, in patients with mild AD, the main frequency bands that are different are the low and high $\alpha $ bands, and the main differently affected brain region is a larger right temporal area. Four LOFC bands were used as input to train the ResNet-18 model. For the MCI dataset, the average accuracy of 20 runs was 93.42% and the best accuracy was 98.33%, while for the mild AD dataset, the average accuracy was 98.54% and the best accuracy was 100%. To determine the timing of early treatment and discovering the susceptible patients, and to slow the progression of the disease, we assume that the occurrence of MCI and mild AD and their progression to more serious AD and dementia could be inferred by analyzing the topological structure of the brain network generated by EEG. Our findings provide a novel solution for connectome-based biomarker analysis to improve personalized medicine. [ABSTRACT FROM AUTHOR]

P300-based brain-computer interfaces (BCIs) provide an additional communication channel for individuals with communication disabilities. In general, P300-based BCIs need to be trained, offline, for a considerable period of time, which causes users to become fatigued. This reduces the efficiency and performance of the system. In order to shorten calibration time and improve system performance, we introduce the concept of a generic model set. We used ERP data from 116 participants to train the generic model set. The resulting set consists of ten models, which are trained by weighted linear discriminant analysis (WLDA). Twelve new participants were then invited to test the validity of the generic model set. The results demonstrated that all new participants matched the best generic model. The resulting mean classification accuracy equaled 80% after online training, an accuracy that was broadly equivalent to the typical training model method. Moreover, the calibration time was shortened by 70.7% of the calibration time of the typical model method. In other words, the best matching model method only took 81s to calibrate, while the typical model method took 276s. There were also significant differences in both accuracy and raw bit rate between the best and the worst matching model methods. We conclude that the strategy of combining the generic models with online training is easily accepted and achieves higher levels of user satisfaction (as measured by subjective reports). Thus, we provide a valuable new strategy for improving the performance of P300-based BCI. [ABSTRACT FROM AUTHOR]

Canonical polyadic (CP) tensor decomposition is an important task in many applications. Many times, the true tensor rank is not known, or noise is present, and in such situations, different existing CP decomposition algorithms provide very different results. In this letter, we introduce a notion of sensitivity of CP decomposition and suggest to use it as a side criterion (besides the fitting error) to evaluate different CP decomposition results. Next, we propose a novel variant of a Krylov-Levenberg-Marquardt CP decomposition algorithm which may serve for CP decomposition with a constraint on the sensitivity. In simulations, we decompose order-4 tensors that come from convolutional neural networks. We show that it is useful to combine the CP decomposition algorithms with an error-preserving correction. [ABSTRACT FROM AUTHOR]

Common spatial pattern (CSP)-based spatial filtering has been most popularly applied to electroencephalogram (EEG) feature extraction for motor imagery (MI) classification in brain–computer interface (BCI) application. The effectiveness of CSP is highly affected by the frequency band and time window of EEG segments. Although numerous algorithms have been designed to optimize the spectral bands of CSP, most of them selected the time window in a heuristic way. This is likely to result in a suboptimal feature extraction since the time period when the brain responses to the mental tasks occurs may not be accurately detected. In this paper, we propose a novel algorithm, namely temporally constrained sparse group spatial pattern (TSGSP), for the simultaneous optimization of filter bands and time window within CSP to further boost classification accuracy of MI EEG. Specifically, spectrum-specific signals are first derived by bandpass filtering from raw EEG data at a set of overlapping filter bands. Each of the spectrum-specific signals is further segmented into multiple subseries using sliding window approach. We then devise a joint sparse optimization of filter bands and time windows with temporal smoothness constraint to extract robust CSP features under a multitask learning framework. A linear support vector machine classifier is trained on the optimized EEG features to accurately identify the MI tasks. An experimental study is implemented on three public EEG datasets (BCI Competition III dataset IIIa, BCI Competition IV datasets IIa, and BCI Competition IV dataset IIb) to validate the effectiveness of TSGSP in comparison to several other competing methods. Superior classification performance (averaged accuracies are 88.5%, 83.3%, and 84.3% for the three datasets, respectively) based on the experimental results confirms that the proposed algorithm is a promising candidate for performance improvement of MI-based BCIs. [ABSTRACT FROM AUTHOR]

In CANDECOMP/PARAFAC tensor decomposition, degeneracy often occurs in some difficult scenarios, especially, when the rank exceeds the tensor dimension, or when the loading components are highly collinear in several or all modes, or when CPD does not have an optimal solution. In such cases, norms of some rank-1 tensors become significantly large and cancel each other. This makes algorithms getting stuck in local minima while running a huge number of iterations does not improve the decomposition. In this paper, we propose an error preservation correction method to deal with such problem. Our aim is to seek an alternative tensor, which preserves the approximation error, but norms of rank-1 tensor components of the new tensor are minimized. Alternating and all-at-once correction algorithms have been developed for the problem. In addition, we propose a novel CPD with a bound constraint on the norm of the rank-one tensors. The method can be useful for decomposing tensors that cannot be performed by traditional algorithms. Finally, we demonstrate an application of the proposed method in image denoising and decomposition of the weight tensors in convolutional neural networks. [ABSTRACT FROM AUTHOR]

In this paper, we present a multimodal emotion recognition framework called EmotionMeter that combines brain waves and eye movements. To increase the feasibility and wearability of EmotionMeter in real-world applications, we design a six-electrode placement above the ears to collect electroencephalography (EEG) signals. We combine EEG and eye movements for integrating the internal cognitive states and external subconscious behaviors of users to improve the recognition accuracy of EmotionMeter. The experimental results demonstrate that modality fusion with multimodal deep neural networks can significantly enhance the performance compared with a single modality, and the best mean accuracy of 85.11% is achieved for four emotions (happy, sad, fear, and neutral). We explore the complementary characteristics of EEG and eye movements for their representational capacities and identify that EEG has the advantage of classifying happy emotion, whereas eye movements outperform EEG in recognizing fear emotion. To investigate the stability of EmotionMeter over time, each subject performs the experiments three times on different days. EmotionMeter obtains a mean recognition accuracy of 72.39% across sessions with the six-electrode EEG and eye movement features. These experimental results demonstrate the effectiveness of EmotionMeter within and between sessions. [ABSTRACT FROM AUTHOR]

A potential limitation of a motor imagery (MI) based brain-computer interface (BCI) is that it usually requires a relatively long time to record sufficient electroencephalogram (EEG) data for robust classifier training. The calibration burden during data acquisition phase will most probably cause a subject to be reluctant to use a BCI system. To alleviate this issue, we propose a novel sparse group representation model (SGRM) for improving the efficiency of MI-based BCI by exploiting the intersubject information. Specifically, preceded by feature extraction using common spatial pattern, a composite dictionary matrix is constructed with training samples from both the target subject and other subjects. By explicitly exploiting within-group sparse and group-wise sparse constraints, the most compact representation of a test sample of the target subject is then estimated as a linear combination of columns in the dictionary matrix. Classification is implemented by calculating the class-specific representation residual based on the significant training samples corresponding to the nonzero representation coefficients. Accordingly, the proposed SGRM method effectively reduces the required training samples from the target subject due to auxiliary data available from other subjects. With two public EEG data sets, extensive experimental comparisons are carried out between SGRM and other state-of-the-art approaches. Superior classification performance of our method using 40 trials of the target subject for model calibration (Averaged accuracy = 78.2%, Kappa = 0.57 and Averaged accuracy = 77.7%, Kappa = 0.55 for the two data sets, respectively) indicates its promising potential for improving the practicality of MI-based BCI. [ABSTRACT FROM AUTHOR]