Decoding Motor Imagery Research Articles

Cross-Subject Motor Imagery Decoding by Transfer Learning of Tactile ERD.

For Brain-Computer Interface (BCI) based on motor imagery (MI), the MI task is abstract and spontaneous, presenting challenges in measurement and control and resulting in a lower signal-to-noise ratio. The quality of the collected MI data significantly impacts the cross-subject calibration results. To address this challenge, we introduce a novel cross-subject calibration method based on passive tactile afferent stimulation, in which data induced by tactile stimulation is utilized to calibrate transfer learning models for cross-subject decoding. During the experiments, tactile stimulation was applied to either the left or right hand, with subjects only required to sense tactile stimulation. Data from these tactile tasks were used to train or fine-tune models and subsequently applied to decode pure MI data. We evaluated BCI performance using both the classical Common Spatial Pattern (CSP) combined with the Linear Discriminant Analysis (LDA) algorithm and a state-of-the-art deep transfer learning model. The results demonstrate that the proposed calibration method achieved decoding performance at an equivalent level to traditional MI calibration, with the added benefit of outperforming traditional MI calibration with fewer trials. The simplicity and effectiveness of the proposed cross-subject tactile calibration method make it valuable for practical applications of BCI, especially in clinical settings.

Recognition of motor imagery electroencephalogram based on flicker noise spectroscopy and weighted filter bank common spatial pattern

Due to the high complexity and subject variability of motor imagery electroencephalogram, its decoding is limited by the inadequate accuracy of traditional recognition models. To resolve this problem, a recognition model for motor imagery electroencephalogram based on flicker noise spectrum (FNS) and weighted filter bank common spatial pattern ( wFBCSP) was proposed. First, the FNS method was used to analyze the motor imagery electroencephalogram. Using the second derivative moment as structure function, the ensued precursor time series were generated by using a sliding window strategy, so that hidden dynamic information of transition phase could be captured. Then, based on the characteristic of signal frequency band, the feature of the transition phase precursor time series and reaction phase series were extracted by wFBCSP, generating features representing relevant transition and reaction phase. To make the selected features adapt to subject variability and realize better generalization, algorithm of minimum redundancy maximum relevance was further used to select features. Finally, support vector machine as the classifier was used for the classification. In the motor imagery electroencephalogram recognition, the method proposed in this study yielded an average accuracy of 86.34%, which is higher than the comparison methods. Thus, our proposed method provides a new idea for decoding motor imagery electroencephalogram.

A multiscale feature fusion network based on attention mechanism for motor imagery EEG decoding

The decoding of motor imagery (MI) electroencephalogram (EEG) is an essential component of the brain–computer interface (BCI), which can help patients with motor impairment communicate directly with the outside world through assistive devices. The key to motor imagery electroencephalogram (MI-EEG) classification is to extract multiple temporal, spatial, and spectral features, to obtain more comprehensive and representative information. However, current deep learning methods must fully consider the depth of temporal features and multi-spectral knowledge in EEG and often ignore the temporal or spectrum dependence in MI-EEG. In addition, the lack of effective feature fusion methods can lead to information redundancy, which affects decoding performance. To solve the above problems, this paper proposes a novel MI-EEG decoding method, named multi-scale feature fusion network based on attention mechanism (MSFF-SENet). Firstly, the multi-scale spatio-temporal module (MS-STM) and the multi-scale temporal module (MSTM) extract spatial and high-dimensional temporal features from the original signal. Then, the power spectral density estimation (PSD) convolution module (PSD-Conv module) acquires the multi-spectral features of the MI-EEG signal. Secondly, the feature fusion module fuses spatio-temporal and multi-spectral features to generate integrated feature mappings and establish the dependencies between different features. Finally, we conducted a visual analysis of the results, explaining the neural activity patterns of various motor imagery tasks in different frequency ranges and revealing the potential relationship between body movement and changes related to brain activity. The experimental results show that the classification accuracy of this model in BCI Competition IV 2a (BCI IV 2a) and High Gamma (HGD) datasets is 85.37% and 96.60%, respectively, which is superior to the most advanced methods.

Cauchy non-convex sparse feature selection method for the high-dimensional small-sample problem in motor imagery EEG decoding.

The time, frequency, and space information of electroencephalogram (EEG) signals is crucial for motor imagery decoding. However, these temporal-frequency-spatial features are high-dimensional small-sample data, which poses significant challenges for motor imagery decoding. Sparse regularization is an effective method for addressing this issue. However, the most commonly employed sparse regularization models in motor imagery decoding, such as the least absolute shrinkage and selection operator (LASSO), is a biased estimation method and leads to the loss of target feature information. In this paper, we propose a non-convex sparse regularization model that employs the Cauchy function. By designing a proximal gradient algorithm, our proposed model achieves closer-to-unbiased estimation than existing sparse models. Therefore, it can learn more accurate, discriminative, and effective feature information. Additionally, the proposed method can perform feature selection and classification simultaneously, without requiring additional classifiers. We conducted experiments on two publicly available motor imagery EEG datasets. The proposed method achieved an average classification accuracy of 82.98% and 64.45% in subject-dependent and subject-independent decoding assessment methods, respectively. The experimental results show that the proposed method can significantly improve the performance of motor imagery decoding, with better classification performance than existing feature selection and deep learning methods. Furthermore, the proposed model shows better generalization capability, with parameter consistency over different datasets and robust classification across different training sample sizes. Compared with existing sparse regularization methods, the proposed method converges faster, and with shorter model training time.

Dynamic Convolution With Multilevel Attention for EEG-Based Motor Imagery Decoding

Brain-computer interface (BCI) is an innovative technology that utilizes artificial intelligence (AI) and wearable electroencephalography (EEG) sensors to decode brain signals and enhance the quality of life. EEG-based motor imagery (MI) brain signal is used in many BCI applications including smart healthcare, smart homes, and robotics control. However, the restricted ability to decode brain signals is a major factor preventing BCI technology from expanding significantly. In this study, we introduce a dynamic attention temporal convolutional network (D-ATCNet) for decoding EEG-based motor imagery signals. The D-ATCNet model uses dynamic convolution and multilevel attention to enhance the performance of MI classification with a relatively small number of parameters. D-ATCNet has two main blocks: dynamic and temporal convolution. Dynamic convolution uses multilevel attention to encode low-level MI-EEG information and temporal convolution uses shifted window with self-attention to extract high-level temporal information from the encoded signal. The proposed model performs better than the existing methods with an accuracy of 71.3% for subject-independent and 87.08% for subject-dependent using the BCI Competition IV-2a dataset.

Improvement of motor imagery electroencephalogram decoding by iterative weighted Sparse-Group Lasso

Discriminative feature selection is vital for enhancing motor imagery decoding performance in electroencephalogram (EEG) signals. However, existing feature optimization methods have not sufficiently explored the intrinsic attribute distribution of features and their associations with the target class, which could result in spurious correlations between optimized features and class labels, yielding suboptimal performance. Therefore, this study proposed an iterative Weighted Sparse-Group Lasso (iWSGL) model for optimizing Common Spatial Pattern (CSP)-based high-dimensional features, thus further enhancing the decoding accuracy of motor imagery. Specifically, the affinity propagation (AP) clustering algorithm was utilized to adaptively partition the high-dimensional features into multiple groups based on the underlying relationships among them. To evaluate the significance of individual feature within each group and the overall significance of the groups themselves, a weight calculation method was proposed based on conditional entropy. With the weights and feature structural information, a weighted sparse regression model was devised within the iterative Sparse-Group Lasso (iSGL) framework to jointly optimize the CSP-based high-dimensional features. The performance of the proposed method was validated on three datasets using the support vector machine (SVM). The experimental results exhibited the exceptional superiority of the proposed method over the current CSP and its variants, demonstrating its remarkable performance. These findings imply that the proposed model can offer a novel optimization strategy for enhancing pattern recognition of brain intentions in Brain-Computer Interface (BCI) applications.

Spectral representation of EEG data using learned graphs with application to motor imagery decoding

Electroencephalography (EEG) data entail a complex spatiotemporal structure that reflects ongoing organization of brain activity. Characterization of the spatial patterns is an indispensable step in numerous EEG processing pipelines. We present a novel method for transforming EEG data into a spectral representation. First, we learn subject-specific graphs from each subject’s EEG data. Second, by eigendecomposition of the normalized Laplacian matrix of each subject’s graph, an orthonormal basis is obtained using which any given EEG map of the subject can be decomposed, providing a spectral representation of the data. We show that energy of EEG maps is strongly associated with low frequency components of the learned basis, reflecting the smooth topography of EEG maps. As a proof-of-concept for this alternative view of EEG data, we consider the task of decoding two-class motor imagery (MI) data. To this aim, the spectral representations are first mapped into a discriminative subspace for differentiating two-class data using a projection matrix obtained by the Fukunaga–Koontz transform (FKT). An SVM classifier is then trained and tested on the resulting features to differentiate MI classes. The method is benchmarked against features extracted from a subject-specific functional connectivity matrix as well as four alternative MI-decoding methods on Dataset IVa of BCI Competition III. Experimental results show the superiority of the proposed method over alternative approaches in differentiating MI classes, reflecting the added benefit of (i) decomposing EEG data using data-driven, subject-specific harmonic bases, and (ii) accounting for class-specific temporal variations in spectral profiles.

Decoding motor imagery based on dipole feature imaging and a hybrid CNN with embedded squeeze-and-excitation block

Motor imagery (MI) decoding is the core of an intelligent rehabilitation system in brain computer interface, and it has a potential advantage by using source signals, which have higher spatial resolution and the same time resolution compared to scalp electroencephalography (EEG). However, how to delve and utilize the personalized frequency characteristic of dipoles for improving decoding performance has not been paid sufficient attention. In this paper, a novel dipole feature imaging (DFI) and a hybrid convolutional neural network (HCNN) with an embedded squeeze-and-excitation block (SEB), denoted as DFI-HCNN, are proposed for decoding MI tasks. EEG source imaging technique is used for brain source estimation, and each sub-band spectrum powers of all dipoles are calculated through frequency analysis and band division. Then, the 3D space information of dipoles is retrieved, and by using azimuthal equidistant projection algorithm it is transformed to a 2D plane, which is combined with nearest neighbor interpolation to generate multi sub-band dipole feature images. Furthermore, a HCNN is designed and applied to the ensemble of sub-band dipole feature images, from which the importance of sub-bands is acquired to adjust the corresponding attentions adaptively by SEB. Ten-fold cross-validation experiments on two public datasets achieve the comparatively higher decoding accuracies of 84.23% and 92.62%, respectively. The experiment results show that DFI is an effective feature representation, and HCNN with an embedded SEB can enhance the useful frequency information of dipoles for improving MI decoding.

Real-Time Classification of Motor Imagery Using Dynamic Window-Level Granger Causality Analysis of fMRI Data.

This article presents a method for extracting neural signal features to identify the imagination of left- and right-hand grasping movements. A functional magnetic resonance imaging (fMRI) experiment is employed to identify four brain regions with significant activations during motor imagery (MI) and the effective connections between these regions of interest (ROIs) were calculated using Dynamic Window-level Granger Causality (DWGC). Then, a real-time fMRI (rt-fMRI) classification system for left- and right-hand MI is developed using the Open-NFT platform. We conducted data acquisition and processing on three subjects, and all of whom were recruited from a local college. As a result, the maximum accuracy of using Support Vector Machine (SVM) classifier on real-time three-class classification (rest, left hand, and right hand) with effective connections is 69.3%. And it is 3% higher than that of traditional multivoxel pattern classification analysis on average. Moreover, it significantly improves classification accuracy during the initial stage of MI tasks while reducing the latency effects in real-time decoding. The study suggests that the effective connections obtained through the DWGC method serve as valuable features for real-time decoding of MI using fMRI. Moreover, they exhibit higher sensitivity to changes in brain states. This research offers theoretical support and technical guidance for extracting neural signal features in the context of fMRI-based studies.

Cross-dataset transfer learning for motor imagery signal classification via multi-task learning and pre-training

Objective. Deep learning (DL) models have been proven to be effective in decoding motor imagery (MI) signals in Electroencephalogram (EEG) data. However, DL models’ success relies heavily on large amounts of training data, whereas EEG data collection is laborious and time-consuming. Recently, cross-dataset transfer learning has emerged as a promising approach to meet the data requirements of DL models. Nevertheless, transferring knowledge across datasets involving different MI tasks remains a significant challenge in cross-dataset transfer learning, limiting the full utilization of valuable data resources. Approach: This study proposes a pre-training-based cross-dataset transfer learning method inspired by Hard Parameter Sharing in multi-task learning. Different datasets with distinct MI paradigms are considered as different tasks, classified with shared feature extraction layers and individual task-specific layers to allow cross-dataset classification with one unified model. Then, Pre-training and fine-tuning are employed to transfer knowledge across datasets. We also designed four fine-tuning schemes and conducted extensive experiments on them. Main results: The results showed that compared to models without pre-training, models with pre-training achieved a maximum increase in accuracy of 7.76%. Moreover, when limited training data were available, the pre-training method significantly improved DL model’s accuracy by 27.34% at most. The experiments also revealed that pre-trained models exhibit faster convergence and remarkable robustness. The training time per subject could be reduced by up to 102.83 s, and the variance of classification accuracy decreased by 75.22% at best. Significance: This study represents the first comprehensive investigation of the cross-dataset transfer learning method between two datasets with different MI tasks. The proposed pre-training method requires only minimal fine-tuning data when applying DL models to new MI paradigms, making MI-Brain–computer interface more practical and user-friendly.

Decoding Algorithm of Motor Imagery Electroencephalogram Signal Based on CLRNet Network Model.

EEG decoding based on motor imagery is an important part of brain-computer interface technology and is an important indicator that determines the overall performance of the brain-computer interface. Due to the complexity of motor imagery EEG feature analysis, traditional classification models rely heavily on the signal preprocessing and feature design stages. End-to-end neural networks in deep learning have been applied to the classification task processing of motor imagery EEG and have shown good results. This study uses a combination of a convolutional neural network (CNN) and a long short-term memory (LSTM) network to obtain spatial information and temporal correlation from EEG signals. The use of cross-layer connectivity reduces the network gradient dispersion problem and enhances the overall network model stability. The effectiveness of this network model is demonstrated on the BCI Competition IV dataset 2a by integrating CNN, BiLSTM and ResNet (called CLRNet in this study) to decode motor imagery EEG. The network model combining CNN and BiLSTM achieved 87.0% accuracy in classifying motor imagery patterns in four classes. The network stability is enhanced by adding ResNet for cross-layer connectivity, which further improved the accuracy by 2.0% to achieve 89.0% classification accuracy. The experimental results show that CLRNet has good performance in decoding the motor imagery EEG dataset. This study provides a better solution for motor imagery EEG decoding in brain-computer interface technology research.

Dynamic Weighted Filter Bank Domain Adaptation for Motor Imagery Brain–Computer Interfaces

A motor imagery (MI)-based brain–computer interface (BCI) is a promising system that can help neuromuscular injury patients recover or replace their motor abilities. Currently, before one uses MI-BCI, we need to collect a large amount of training data to train the decoding model, and this process is time consuming. When trained with a small amount of data, existing decoding methods generally do not perform well in MI decoding tasks. Therefore, it is important to improve the decoding performance with short calibration data. In this study, we propose a dynamic weighted filter bank domain adaptation framework that uses data from an existing subject to reduce the requirement of data from the new subject. A filter bank is used to explore information from different frequency subbands. A feature extractor with two 1-D convolutional layers is designed to extract EEG features. The class-specific Wasserstein generative adversarial network (WGAN)-based domain adaptation network aligns the distribution of each class between the data from the new subject and the data from the existing subject. Additionally, we apply an attention network to dynamically allocate different weights for different frequency bands. We evaluate our method on a public MI dataset and a self-collected dataset. The experimental results show that the proposed method achieves the best decoding accuracy among the compared methods with different amounts of training data. On the public dataset, our method achieves 8.88% and 7.16% higher decoding accuracy than the best comparing method with on block of training data on the two sessions, respectively. This indicates that our method can enhance MI decoding accuracy with a small amount of training data.

A novel scheme based on information theory and transfer learning for multi classes motor imagery decoding

AbstractThe most important challenges of classifying Motor Imagery tasks based on the EEG signal are low signal‐to‐noise ratio, non‐stationarity, and the high subject dependence of the EEG signal. In this study, a framework for multi‐class decoding of Motor Imagery signals is presented. This framework is based on information theory and hybrid deep learning along with transfer learning. In this study, the OVR‐FBDiv method, which is based on the symmetric Kullback—Leibler divergence, is used to differentiate between features of different classes and highlight them. Then, the mRMR algorithm is used to select the most distinctive features obtained from the filters of symmetric KL divergence. Finally, a hybrid deep neural network consisting of CNN and LSTM is used to learn the spatial and temporal features of the EEG signal along with the transfer learning technique to overcome the problem of subject dependence in EEG signals. The average value of Kappa for the classification of 4‐class Motor Imagery data on BCI competition IV dataset 2a by the proposed method is 0.84. Also, the proposed method is compared with other state‐of‐the‐art methods.

Filter bank sinc-convolutional network with channel self-attention for high performance motor imagery decoding

Objective. Motor Imagery Brain-Computer Interface (MI-BCI) is an active Brain-Computer Interface (BCI) paradigm focusing on the identification of motor intention, which is one of the most important non-invasive BCI paradigms. In MI-BCI studies, deep learning-based methods (especially lightweight networks) have attracted more attention in recent years, but the decoding performance still needs further improving. Approach. To solve this problem, we designed a filter bank structure with sinc-convolutional layers for spatio-temporal feature extraction of MI-electroencephalography in four motor rhythms. The Channel Self-Attention method was introduced for feature selection based on both global and local information, so as to build a model called Filter Bank Sinc-convolutional Network with Channel Self-Attention for high performance MI-decoding. Also, we proposed a data augmentation method based on multivariate empirical mode decomposition to improve the generalization capability of the model. Main results. We performed an intra-subject evaluation experiment on unseen data of three open MI datasets. The proposed method achieved mean accuracy of 78.20% (4-class scenario) on BCI Competition IV IIa, 87.34% (2-class scenario) on BCI Competition IV IIb, and 72.03% (2-class scenario) on Open Brain Machine Interface (OpenBMI) dataset, which are significantly higher than those of compared deep learning-based methods by at least 3.05% ( = 0.0469), 3.18% ( = 0.0371), and 2.27% ( = 0.0024) respectively. Significance. This work provides a new option for deep learning-based MI decoding, which can be employed for building BCI systems for motor rehabilitation.

Real-Time Navigation in Google Street View® Using a Motor Imagery-Based BCI.

Navigation in virtual worlds is ubiquitous in games and other virtual reality (VR) applications and mainly relies on external controllers. As brain-computer interfaces (BCI)s rely on mental control, bypassing traditional neural pathways, they provide to paralyzed users an alternative way to navigate. However, the majority of BCI-based navigation studies adopt cue-based visual paradigms, and the evoked brain responses are encoded into navigation commands. Although robust and accurate, these paradigms are less intuitive and comfortable for navigation compared to imagining limb movements (motor imagery, MI). However, decoding motor imagery from EEG activity is notoriously challenging. Typically, wet electrodes are used to improve EEG signal quality, including a large number of them to discriminate between movements of different limbs, and a cuedbased paradigm is used instead of a self-paced one to maximize decoding performance. Motor BCI applications primarily focus on typing applications or on navigating a wheelchair-the latter raises safety concerns-thereby calling for sensors scanning the environment for obstacles and potentially hazardous scenarios. With the help of new technologies such as virtual reality (VR), vivid graphics can be rendered, providing the user with a safe and immersive experience; and they could be used for navigation purposes, a topic that has yet to be fully explored in the BCI community. In this study, we propose a novel MI-BCI application based on an 8-dry-electrode EEG setup, with which users can explore and navigate in Google Street View®. We pay attention to system design to address the lower performance of the MI decoder due to the dry electrodes' lower signal quality and the small number of electrodes. Specifically, we restricted the number of navigation commands by using a novel middle-level control scheme and avoided decoder mistakes by introducing eye blinks as a control signal in different navigation stages. Both offline and online experiments were conducted with 20 healthy subjects. The results showed acceptable performance, even given the limitations of the EEG set-up, which we attribute to the design of the BCI application. The study suggests the use of MI-BCI in future games and VR applications for consumers and patients temporarily or permanently devoid of muscle control.

A Multi-Source Transfer Joint Matching Method for Inter-Subject Motor Imagery Decoding.

Individual differences among different subjects pose a great challenge to motor imagery (MI) decoding. Multi-source transfer learning (MSTL) is one of the most promising ways to reduce individual differences, which can utilize rich information and align the data distribution among different subjects. However, most MSTL methods in MI-BCI combine all data in the source subjects into a single mixed domain, which will ignore the effect of important samples and the large differences in multiple source subjects. To address these issues, we introduce transfer joint matching and improve it to multi-source transfer joint matching (MSTJM) and weighted MSTJM (wMSTJM). Different from previous MSTL methods in MI, our methods align the data distribution for each pair of subjects, and then integrate the results by decision fusion. Besides that, we design an inter-subject MI decoding framework to verify the effectiveness of these two MSTL algorithms. It mainly consists of three modules: covariance matrix centroid alignment in the Riemannian space, source selection in the Euclidean space after tangent space mapping to reduce negative transfer and computation overhead, and further distribution alignment by MSTJM or wMSTJM. The superiority of this framework is verified on two common public MI datasets from BCI competition IV. The average classification accuracy of the MSTJM and wMSTJ methods outperformed other state-of-the-art methods by at least 4.24% and 2.62% respectively. It's promising to advance the practical applications of MI-BCI.

IFNet: An Interactive Frequency Convolutional Neural Network for Enhancing Motor Imagery Decoding From EEG.

The key principle of motor imagery (MI) decoding for electroencephalogram (EEG)-based Brain-Computer Interface (BCI) is to extract task-discriminative features from spectral, spatial, and temporal domains jointly and efficiently, whereas limited, noisy, and non-stationary EEG samples challenge the advanced design of decoding algorithms. Inspired by the concept of cross-frequency coupling and its correlation with different behavioral tasks, this paper proposes a lightweight Interactive Frequency Convolutional Neural Network (IFNet) to explore cross-frequency interactions for enhancing representation of MI characteristics. IFNet first extracts spectro-spatial features in low and high-frequency bands, respectively. Then the interplay between the two bands is learned using an element-wise addition operation followed by temporal average pooling. Combined with repeated trial augmentation as a regularizer, IFNet yields spectro-spatio-temporally robust features for the final MI classification. We conduct extensive experiments on two benchmark datasets: the BCI competition IV 2a (BCIC-IV-2a) dataset and the OpenBMI dataset. Compared with state-of-the-art MI decoding algorithms, IFNet achieves significantly superior classification performance on both datasets while improving the winner's result in BCIC-IV-2a by 11%. Moreover, by conducting sensitivity analysis on decision windows, we show IFNet attains the best trade-off between decoding speed and accuracy. Detailed analysis and visualization verify IFNet can capture the coupling across frequency bands along with the known MI signatures. We demonstrate the effectiveness and superiority of the proposed IFNet for MI decoding. This study suggests IFNet holds promise for rapid response and accurate control in MI-BCI applications.

A Spiking Neural Network with Adaptive Graph Convolution and LSTM for EEG-Based Brain-Computer Interfaces.

Electroencephalography (EEG) signals classification is essential for the brain-computer interface (BCI). Recently, energy-efficient spiking neural networks (SNNs) have shown great potential in EEG analysis due to their ability to capture the complex dynamic properties of biological neurons while also processing stimulus information through precisely timed spike trains. However, most existing methods do not effectively mine the specific spatial topology of EEG channels and temporal dependencies of the encoded EEG spikes. Moreover, most are designed for specific BCI tasks and lack some generality. Hence, this study presents a novel SNN model with the customized spike-based adaptive graph convolution and long short-term memory (LSTM), termed SGLNet, for EEG-based BCIs. Specifically, we first adopt a learnable spike encoder to convert the raw EEG signals into spike trains. Then, we tailor the concepts of the multi-head adaptive graph convolution to SNN so that it can make good use of the intrinsic spatial topology information among distinct EEG channels. Finally, we design the spike-based LSTM units to further capture the temporal dependencies of the spikes. We evaluate our proposed model on two publicly available datasets from two representative fields of BCI, notably emotion recognition, and motor imagery decoding. The empirical evaluations demonstrate that SGLNet consistently outperforms existing state-of-the-art EEG classification algorithms. This work provides a new perspective for exploring high-performance SNNs for future BCIs with rich spatiotemporal dynamics.

Front-End Replication Dynamic Window (FRDW) for Online Motor Imagery Classification.

Motor imagery (MI) is a classical paradigm in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Online accurate and fast decoding is very important to its successful applications. This paper proposes a simple yet effective front-end replication dynamic window (FRDW) algorithm for this purpose. Dynamic windows enable the classification based on a test EEG trial shorter than those used in training, improving the decision speed; front-end replication fills a short test EEG trial to the length used in training, improving the classification accuracy. Within-subject and cross-subject online MI classification experiments on three public datasets, with three different classifiers and three different data augmentation approaches, demonstrated that FRDW can significantly increase the information transfer rate in MI decoding. Additionally, FR can also be used in training data augmentation. FRDW helped win national champion of the China BCI Competition in 2022.

A Model Combining Multi Branch Spectral-Temporal CNN, Efficient Channel Attention, and LightGBM For MI-BCI Classification.

Accurately decoding motor imagery (MI) brain-computer interface (BCI) tasks has remained a challenge for both neuroscience research and clinical diagnosis. Unfortunately, less subject information and low signal-to-noise ratio of MI electroencephalography (EEG) signals make it difficult to decode the movement intentions of users. In this study, we proposed an end-to-end deep learning model, a multi-branch spectral-temporal convolutional neural network with channel attention and LightGBM model (MBSTCNN-ECA-LightGBM), to decode MI-EEG tasks. We first constructed a multi branch CNN module to learn spectral-temporal domain features. Subsequently, we added an efficient channel attention mechanism module to obtain more discriminative features. Finally, LightGBM was applied to decode the MI multi-classification tasks. The within-subject cross-session training strategy was used to validate classification results. The experimental results showed that the model achieved an average accuracy of 86% on the two-class MI-BCI data and an average accuracy of 74% on the four-class MI-BCI data, which outperformed current state-of-the-art methods. The proposed MBSTCNN-ECA-LightGBM can efficiently decode the spectral and temporal domain information of EEG, improving the performance of MI-based BCIs.