Search

Autism spectrum disorder (ASD) is a pervasive developmental disorder of the central nervous system, which occurs most frequently in childhood and is characterized by unusual and repetitive ritualistic behaviors. Currently, diagnostic methods primarily rely on questionnaire surveys and behavioral observation, which may lead to misdiagnoses due to the subjective evaluation and measurement used in these traditional methods. With the advancement in medical imaging, MR imaging-based diagnosis has become an alternative and more objective approach. In this paper, we propose a Hybrid neural Network model for ASD identification, termded ASD-HNet, to hierarchically extract features on the functional brain networks based on resting-state functional magnetic resonance imaging data. This hierarchical method can better extract brain representations, improve the diagnostic accuracy, and help us better locate brain regions related to ASD. Specifically, features are extracted from three scales: local regions of interest (ROIs) scale, community-clustering scale, and the whole-communities scale. For the ROI scale, graph convolution is used to transfer features between ROIs. At the community cluster scale, functional gradients are introduced, the clustering algorithm K-Means is used to automatically cluster ROIs with similar functional gradients into several communities, and features of ROIs belonging to the same community are extracted to characterize these communities. At global information integration scale, we extract global features from community-scale brain networks to characterize the whole brain networks. We validate the effectiveness of our method using the public dataset of Autism Brain Imaging Data Exchange I (ABIDE I), and elucidate the interpretability of the method. Experimental results demonstrate that the proposed ASD-HNet can yield superior performance than compared methods.

Graph Neural Networks (GNNs) have received considerable attention since its introduction. It has been widely applied in various fields due to its ability to represent graph structured data. However, the application of GNNs is constrained by two main issues. Firstly, the "over-smoothing" problem restricts the use of deeper network structures. Secondly, GNNs' applicability is greatly limited when nodes and edges are not clearly defined and expressed, as is the case with EEG data.In this study, we proposed an innovative approach that harnesses the distinctive properties of the graph structure's Markov Chain to optimize the sampling depth of deep graph convolution networks. We introduced a tailored method for constructing graph structures specifically designed for analyzing EEG data, alongside the development of a vertex-level GNN classification model for precise detection of mental disorders. In order to verify the method's performance, we conduct experiments on two disease datasets using a subject-independent experiment scenario. For the Schizophrenia (SZ) data, our method achieves an average accuracy of 100% using only the first 300 seconds of data from each subject. Similarly, for Major Depressive Disorder (MDD) data, the method yields average accuracies of over 99%. These experiments demonstrate the method's ability to effectively distinguish between healthy control (HC) subjects and patients with mental disorders. We believe this method shows great promise for clinical diagnosis., Comment: 5 figures, 4 tables

In this work, we investigate a simple and must-known conditional generative framework based on Vector Quantised-Variational AutoEncoder (VQ-VAE) and Generative Pre-trained Transformer (GPT) for human motion generation from textural descriptions. We show that a simple CNN-based VQ-VAE with commonly used training recipes (EMA and Code Reset) allows us to obtain high-quality discrete representations. For GPT, we incorporate a simple corruption strategy during the training to alleviate training-testing discrepancy. Despite its simplicity, our T2M-GPT shows better performance than competitive approaches, including recent diffusion-based approaches. For example, on HumanML3D, which is currently the largest dataset, we achieve comparable performance on the consistency between text and generated motion (R-Precision), but with FID 0.116 largely outperforming MotionDiffuse of 0.630. Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach. Our work suggests that VQ-VAE still remains a competitive approach for human motion generation., Comment: Accepted to CVPR 2023. Project page: https://mael-zys.github.io/T2M-GPT/

Steady-state visual evoked potentials (SSVEPs) based brain-computer interface (BCI) has received considerable attention due to its high information transfer rate (ITR) and available quantity of targets. However, the performance of frequency identification methods heavily hinges on the amount of user calibration data and data length, which hinders the deployment in real-world applications. Recently, generative adversarial networks (GANs)-based data generation methods have been widely adopted to create synthetic electroencephalography (EEG) data, holds promise to address these issues. In this paper, we proposed a GAN-based end-to-end signal transformation network for Time-window length Extension, termed as TEGAN. TEGAN transforms short-length SSVEP signals into long-length artificial SSVEP signals. By incorporating a novel U-Net generator architecture and an auxiliary classifier into the network architecture, the TEGAN could produce conditioned features in the synthetic data. Additionally, we introduced a two-stage training strategy and the LeCam-divergence regularization term to regularize the training process of GAN during the network implementation. The proposed TEGAN was evaluated on two public SSVEP datasets (a 4-class dataset and a 12-class dataset). With the assistance of TEGAN, the performance of traditional frequency recognition methods and deep learning-based methods have been significantly improved under limited calibration data. And the classification performance gap of various frequency recognition methods has been narrowed. This study substantiates the feasibility of the proposed method to extend the data length for short-time SSVEP signals for developing a high-performance BCI system. The proposed GAN-based methods have the great potential of shortening the calibration time and cutting down the budget for various real-world BCI-based applications., Comment: 16 pages, 9 figures, 4 tables

Steady-state visual evoked potential (SSVEP) is one of the most commonly used control signal in the brain-computer interface (BCI) systems. However, the conventional spatial filtering methods for SSVEP classification highly depend on the subject-specific calibration data. The need for the methods that can alleviate the demand for the calibration data become urgent. In recent years, developing the methods that can work in inter-subject classification scenario has become a promising new direction. As the popular deep learning model nowadays, Transformer has excellent performance and has been used in EEG signal classification tasks. Therefore, in this study, we propose a deep learning model for SSVEP classification based on Transformer structure in inter-subject classification scenario, termed as SSVEPformer, which is the first application of the transformer to the classification of SSVEP. Inspired by previous studies, the model adopts the frequency spectrum of SSVEP data as input, and explores the spectral and spatial domain information for classification. Furthermore, to fully utilize the harmonic information, an extended SSVEPformer based on the filter bank technology (FB-SSVEPformer) is proposed to further improve the classification performance. Experiments were conducted using two open datasets (Dataset 1: 10 subjects, 12-class task; Dataset 2: 35 subjects, 40-class task) in the inter-subject classification scenario. The experimental results show that the proposed models could achieve better results in terms of classification accuracy and information transfer rate, compared with other baseline methods. The proposed model validates the feasibility of deep learning models based on Transformer structure for SSVEP classification task, and could serve as a potential model to alleviate the calibration procedure in the practical application of SSVEP-based BCI systems.

In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions. To address MTDA, we propose a self-training strategy that employs pseudo-labels to induce cooperation among multiple domain-specific classifiers. We employ feature stylization as an efficient way to generate image views that forms an integral part of self-training. Additionally, to prevent the network from overfitting to noisy pseudo-labels, we devise a rectification strategy that leverages the predictions from different classifiers to estimate the quality of pseudo-labels. Our extensive experiments on numerous settings, based on four different semantic segmentation datasets, validate the effectiveness of the proposed self-training strategy and show that our method outperforms state-of-the-art MTDA approaches. Code available at: https://github.com/Mael-zys/CoaST, Comment: Accepted at WACV 2023

Schizophrenia (SZ) is a serious mental disorder that could seriously affect the patient's quality of life. In recent years, detection of SZ based on deep learning (DL) using electroencephalogram (EEG) has received increasing attention. In this paper, we proposed an end-to-end recurrent auto-encoder (RAE) model to detect SZ. In the RAE model, the raw data was input into one auto-encoder block, and the reconstructed data were recurrently input into the same block. The extracted code by auto-encoder block was simultaneously served as an input of a classifier block to discriminate SZ patients from healthy controls (HC). Evaluated on the dataset containing 14 SZ patients and 14 HC subjects, and the proposed method achieved an average classification accuracy of 81.81% in subject-independent experiment scenario. This study demonstrated that the structure of RAE is able to capture the differential features between SZ patients and HC subjects.

In recent years, emotion recognition based on electroencephalography (EEG) has received growing interests in the brain-computer interaction (BCI) field. The neuroscience researches indicate that the left and right brain hemispheres demonstrate activity differences under different emotional activities, which could be an important principle for designing deep learning (DL) model for emotion recognition. Besides, owing to the nonstationarity of EEG signals, using convolution kernels of a single size may not sufficiently extract the abundant features for EEG classification tasks. Based on these two angles, we proposed a model termed Multi-Scales Bi-hemispheric Asymmetric Model (MSBAM) based on convolutional neural network (CNN) structure. Evaluated on the public DEAP and DREAMER datasets, MSBAM achieved over 99% accuracy for the two-class classification of low-level and high-level states in each of four emotional dimensions, i.e., arousal, valence, dominance and liking, respectively. This study further demonstrated the promising potential to design the DL model from the multi-scale characteristics of the EEG data and the neural mechanisms of the emotion cognition.

Brain neural networks characterize various information propagation patterns for different emotional states. However, the statistical features based on traditional graph theory may ignore the spacial network difference. To reveal these inherent spatial features and increase the stability of emotional recognition, we proposed a hierarchical framework that can perform the multiple emotion recognitions with the multiple emotion-related spatial network topology patterns (MESNP) by combining a supervised learning with ensemble co-decision strategy. To evaluate the performance of our proposed MESNP approach, we conduct both off-line and simulated on-line experiments with two public datasets i.e., MAHNOB and DEAP. The experiment results demonstrated that MESNP can significantly enhance the classification performance for the multiple emotions. The highest accuracies of off-line experiments for MAHNOB-HCI and DEAP achieved 99.93% (3 classes) and 83.66% (4 classes), respectively. For simulated on-line experiments, we also obtained the best classification accuracies with 100% (3 classes) for MAHNOB and 99.22% (4 classes) for DEAP by proposed MESNP. These results further proved the efficiency of MESNP for structured feature extraction in mult-classification emotional task.

Steady-state visual evoked potentials (SSVEP) brain-computer interface (BCI) provides reliable responses leading to high accuracy and information throughput. But achieving high accuracy typically requires a relatively long time window of one second or more. Various methods were proposed to improve sub-second response accuracy through subject-specific training and calibration. Substantial performance improvements were achieved with tedious calibration and subject-specific training; resulting in the user's discomfort. So, we propose a training-free method by combining spatial-filtering and temporal alignment (CSTA) to recognize SSVEP responses in sub-second response time. CSTA exploits linear correlation and non-linear similarity between steady-state responses and stimulus templates with complementary fusion to achieve desirable performance improvements. We evaluated the performance of CSTA in terms of accuracy and Information Transfer Rate (ITR) in comparison with both training-based and training-free methods using two SSVEP data-sets. We observed that CSTA achieves the maximum mean accuracy of 97.43$\pm$2.26 % and 85.71$\pm$13.41 % with four-class and forty-class SSVEP data-sets respectively in sub-second response time in offline analysis. CSTA yields significantly higher mean performance (p<0.001) than the training-free method on both data-sets. Compared with training-based methods, CSTA shows 29.33$\pm$19.65 % higher mean accuracy with statistically significant differences in time window less than 0.5 s. In longer time windows, CSTA exhibits either better or comparable performance though not statistically significantly better than training-based methods. We show that the proposed method brings advantages of subject-independent SSVEP classification without requiring training while enabling high target recognition performance in sub-second response time., Comment: Further improvements or modifications required to algorithm design

Effective frequency recognition algorithms are critical in steady-state visual evoked potential (SSVEP) based brain-computer interfaces (BCIs). In this study, we present a hierarchical feature fusion framework which can be used to design high-performance frequency recognition methods. The proposed framework includes two primary technique for fusing features: spatial dimension fusion (SD) and frequency dimension fusion (FD). Both SD and FD fusions are obtained using a weighted strategy with a nonlinear function. To assess our novel methods, we used the correlated component analysis (CORRCA) method to investigate the efficiency and effectiveness of the proposed framework. Experimental results were obtained from a benchmark dataset of thirty-five subjects and indicate that the extended CORRCA method used within the framework significantly outperforms the original CORCCA method. Accordingly, the proposed framework holds promise to enhance the performance of frequency recognition methods in SSVEP-based BCIs., Comment: 25 pages, 9 figures

The oddball paradigm is widely applied to the investigation of multiple cognitive functions. Prior studies have explored the cortical oscillation and power spectral differing from the resting-state conduction to oddball paradigm, but whether brain networks existing the significant difference is still unclear. Our study addressed how the brain reconfigures its architecture from a resting-state condition (i.e., baseline) to P300 stimulus task in the visual oddball paradigm. In this study, electroencephalogram (EEG) datasets were collected from 24 postgraduate students, who were required to only mentally count the number of target stimulus; afterwards the functional EEG networks constructed in different frequency bands were compared between baseline and oddball task conditions to evaluate the reconfiguration of functional network in the brain. Compared to the baseline, our results showed the significantly (p < 0.05) enhanced delta/theta EEG connectivity and decreased alpha default mode network in the progress of brain reconfiguration to the P300 task. Furthermore, the reconfigured coupling strengths were demonstrated to relate to P300 amplitudes, which were then regarded as input features to train a classifier to differentiate the high and low P300 amplitudes groups with an accuracy of 77.78%. The findings of our study help us to understand the changes of functional brain connectivity from resting-state to oddball stimulus task, and the reconfigured network pattern has the potential for the selection of good subjects for P300-based brain- computer interface., Comment: This manuscript is submitting to IEEE Transactions on Cognitive and Developmental Systems

Canonical correlation analysis (CCA) is a state-of-the-art method for frequency recognition in steady-state visual evoked potential (SSVEP)-based brain-computer interface (BCI) systems. Various extended methods have been developed, and among such methods, a combination method of CCA and individual-template-based CCA (IT-CCA) has achieved excellent performance. However, CCA requires the canonical vectors to be orthogonal, which may not be a reasonable assumption for EEG analysis. In the current study, we propose using the correlated component analysis (CORRCA) rather than CCA to implement frequency recognition. CORRCA can relax the constraint of canonical vectors in CCA, and generate the same projection vector for two multichannel EEG signals. Furthermore, we propose a two-stage method based on the basic CORRCA method (termed TSCORRCA). Evaluated on a benchmark dataset of thirty-five subjects, the experimental results demonstrate that CORRCA significantly outperformed CCA, and TSCORRCA obtained the best performance among the compared methods. This study demonstrates that CORRCA-based methods have great potential for implementing high-performance SSVEP-based BCI systems., Comment: 10 pages, 10 figures, submitted to IEEE TNSRE

Our mysterious brain is believed to operate near a non-equilibrium point and generate critical self-organized avalanches in neuronal activity. Recent experimental evidence has revealed significant heterogeneity in both synaptic input and output connectivity, but whether the structural heterogeneity participates in the regulation of neuronal avalanches remains poorly understood. By computational modelling, we predict that different types of structural heterogeneity contribute distinct effects on avalanche neurodynamics. In particular, neuronal avalanches can be triggered at an intermediate level of input heterogeneity, but heterogeneous output connectivity cannot evoke avalanche dynamics. In the criticality region, the co-emergence of multi-scale cortical activities is observed, and both the avalanche dynamics and neuronal oscillations are modulated by the input heterogeneity. Remarkably, we show similar results can be reproduced in networks with various types of in- and out-degree distributions. Overall, these findings not only provide details on the underlying circuitry mechanisms of nonrandom synaptic connectivity in the regulation of neuronal avalanches, but also inspire testable hypotheses for future experimental studies., Comment: 37 pages, 9 figures, 1 table

Biological neurons receive multiple noisy oscillatory signals, and their dynamical response to the superposition of these signals is of fundamental importance for information processing in the brain. Here we study the response of neural systems to the weak envelope modulation signal, which is superimposed by two periodic signals with different frequencies. We show that stochastic resonance occurs at the beat frequency in neural systems at the single-neuron as well as the population level. The performance of this frequency-difference-dependent stochastic resonance is influenced by both the beat frequency and the two forcing frequencies. Compared to a single neuron, a population of neurons is more efficient in detecting the information carried by the weak envelope modulation signal at the beat frequency. Furthermore, an appropriate fine-tuning of the excitation-inhibition balance can further optimize the response of a neural ensemble to the superimposed signal. Our results thus introduce and provide insights into the generation and modulation mechanism of the frequency-difference-dependent stochastic resonance in neural systems., Comment: 6 two-column pages, 7 figures; accepted for publication in Physical Review E

The importance of self-feedback autaptic transmission in modulating spike-time irregularity is still poorly understood. By using a biophysical model that incorporates autaptic coupling, we here show that self-innervation of neurons participates in the modulation of irregular neuronal firing, primarily by regulating the occurrence frequency of burst firing. In particular, we find that both excitatory and electrical autapses increase the occurrence of burst firing, thus reducing neuronal firing regularity. In contrast, inhibitory autapses suppress burst firing and therefore tend to improve the regularity of neuronal firing. Importantly, we show that these findings are independent of the firing properties of individual neurons, and as such can be observed for neurons operating in different modes. Our results provide an insightful mechanistic understanding of how different types of autapses shape irregular firing at the single-neuron level, and they highlight the functional importance of autaptic self-innervation in taming and modulating neurodynamics., Comment: 27 pages, 8 figures