Tensor-based dynamic brain functional network for motor imagery classification

Partial prior transfer learning based on self-attention CNN for EEG decoding in stroke patients

The utilization of motor imagery-based brain-computer interfaces (MI-BCI) has been shown to assist stroke patients activate motor regions in the brain. In particular, the brain regions activated by unilateral upper limb multi-task are more extensive, which is more beneficial for rehabilitation, but it also increases the difficulty of decoding. In this paper, self-attention convolutional neural network based partial prior transfer learning (SACNN-PPTL) is proposed to improve the classification performance of patients' MI multi-task. The backbone network of the algorithm is SACNN, which accords with the inherent features of electroencephalogram (EEG) and contains the temporal feature module, the spatial feature module and the feature generalization module. In addition, PPTL is introduced to transfer part of the target domain while preserving the generalization of the base model while improving the specificity of the target domain. In the experiment, five backbone networks and three training modes are selected as comparison algorithms. The experimental results show that SACNN-PPTL had a classification accuracy of 55.4%±0.17 in four types of MI tasks for 22 patients, which is significantly higher than comparison algorithms (P < 0.05). SACNN-PPTL effectively improves the decoding performance of MI tasks and promotes the development of BCI-based rehabilitation for unilateral upper limb.

Motor imagery decoding using source optimized transfer learning based on multi-loss fusion CNN

Transfer learning is increasingly used to decode multi-class motor imagery tasks. Previous transfer learning ignored the optimizability of the source model, weakened the adaptability to the target domain and limited the performance. This paper first proposes the multi-loss fusion convolutional neural network (MF-CNN) to make an optimizable source model. Then we propose a novel source optimized transfer learning (SOTL), which optimizes the source model to make it more in line with the target domain's features to improve the target model's performance. We transfer the model trained from 16 healthy subjects to 16 stroke patients. The average classification accuracy achieves 51.2 ± 0.17% in the four types of unilateral upper limb motor imagery tasks, which is significantly higher than the classification accuracy of deep learning (p < 0.001) and transfer learning (p < 0.05). In this paper, an MI model from the data of healthy subjects can be used for the classification of stroke patients and can demonstrate good classification results, which provides experiential support for the study of transfer learning and the modeling of stroke rehabilitation training.

Spatio-Temporal Graph Hubness Propagation Model for Dynamic Brain Network Classification

Dynamic brain network has the advantage over static brain network in characterizing the variation pattern of functional brain connectivity, and it has attracted increasing attention in brain disease diagnosis. However, most of the existing dynamic brain networks analysis methods rely on extracting features from independent brain networks divided by sliding windows, making them hard to reveal the high-order dynamic evolution laws of functional brain networks. Additionally, they cannot effectively extract the spatio-temporal topology features in dynamic brain networks. In this paper, we propose to use optimal transport (OT) theory to capture the topology evolution of the dynamic brain networks, and develop a multi-channel spatio-temporal graph convolutional network that collaboratively extracts the temporal and spatial features from the evolution networks. Specifically, we first adaptively evaluate the graph hubness of brain regions in the brain network of each time window, which comprehensively models information transmission among multiple brain regions. Second, the hubness propagation information across adjacent time windows is captured by optimal transport, describing high-order topology evolution of dynamic brain networks. Moreover, we develop a spatio-temporal graph convolutional network with attention mechanism to collaboratively extract the intrinsic temporal and spatial topology information from the above networks. Finally, the multi-layer perceptron is adopted for classifying the dynamic brain network. The extensive experiment on the collected epilepsy dataset and the public ADNI dataset show that our proposed method not only outperforms several state-of-the-art methods in brain disease diagnosis, but also reveals the key dynamic alterations of brain connectivities between patients and healthy controls.

Efficient Feature Learning Model of Motor Imagery EEG Signals with L1-Norm and Weighted Fusion

Brain-computer interface (BCI) for motor imagery is an advanced technology used in the field of medical rehabilitation. However, due to the poor accuracy of electroencephalogram feature classification, BCI systems often misrecognize user commands. Although many state-of-the-art feature selection methods aim to enhance classification accuracy, they usually overlook the interrelationships between individual features, indirectly impacting the accuracy of feature classification. To overcome this issue, we propose an adaptive feature learning model that employs a Riemannian geometric approach to generate a feature matrix from electroencephalogram signals, serving as the model's input. By integrating the enhanced adaptive L1 penalty and weighted fusion penalty into the sparse learning model, we select the most informative features from the matrix. Specifically, we measure the importance of features using mutual information and introduce an adaptive weight construction strategy to penalize regression coefficients corresponding to each variable adaptively. Moreover, the weighted fusion penalty balances weight differences among correlated variables, reducing the model's overreliance on specific variables and enhancing accuracy. The performance of the proposed method was validated on BCI Competition IV datasets IIa and IIb using the support vector machine. Experimental results demonstrate the effectiveness and superiority of the proposed model compared to the existing models.

Recruiting neural field theory for data augmentation in a motor imagery brain-computer interface

We introduce a novel approach to training data augmentation in brain-computer interfaces (BCIs) using neural field theory (NFT) applied to EEG data from motor imagery tasks. BCIs often suffer from limited accuracy due to a limited amount of training data. To address this, we leveraged a corticothalamic NFT model to generate artificial EEG time series as supplemental training data. We employed the BCI competition IV '2a' dataset to evaluate this augmentation technique. For each individual, we fitted the model to common spatial patterns of each motor imagery class, jittered the fitted parameters, and generated time series for data augmentation. Our method led to significant accuracy improvements of over 2% in classifying the "total power" feature, but not in the case of the "Higuchi fractal dimension" feature. This suggests that the fit NFT model may more favorably represent one feature than the other. These findings pave the way for further exploration of NFT-based data augmentation, highlighting the benefits of biophysically accurate artificial data.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

A sequential learning model with GNN for EEG-EMG-based stroke rehabilitation BCI

Introduction

Brain-computer interfaces (BCIs) have the potential in providing neurofeedback for stroke patients to improve motor rehabilitation. However, current BCIs often only detect general motor intentions and lack the precise information needed for complex movement execution, mainly due to insufficient movement execution features in EEG signals.

Methods

This paper presents a sequential learning model incorporating a Graph Isomorphic Network (GIN) that processes a sequence of graph-structured data derived from EEG and EMG signals. Movement data are divided into sub-actions and predicted separately by the model, generating a sequential motor encoding that reflects the sequential features of the movements. Through time-based ensemble learning, the proposed method achieves more accurate prediction results and execution quality scores for each movement.

Results

A classification accuracy of 88.89% is achieved on an EEG-EMG synchronized dataset for push and pull movements, significantly outperforming the benchmark method's performance of 73.23%.

Discussion

This approach can be used to develop a hybrid EEG-EMG brain-computer interface to provide patients with more accurate neural feedback to aid their recovery.