Brain-computer Interface Competition Research Articles

A Synergy of Convolutional Neural Networks for Sensor-Based EEG Brain–Computer Interfaces to Enhance Motor Imagery Classification

Enhancing motor disability assessment and its imagery classification is a significant concern in contemporary medical practice, necessitating reliable solutions to improve patient outcomes. One promising avenue is the use of brain–computer interfaces (BCIs), which establish a direct communication pathway between users and machines. This technology holds the potential to revolutionize human–machine interaction, especially for individuals diagnosed with motor disabilities. Despite this promise, extracting reliable control signals from noisy brain data remains a critical challenge. In this paper, we introduce a novel approach leveraging the collaborative synergy of five convolutional neural network (CNN) models to improve the classification accuracy of motor imagery tasks, which are essential components of BCI systems. Our method demonstrates exceptional performance, achieving an accuracy of 79.44% on the BCI Competition IV 2a dataset, surpassing existing state-of-the-art techniques in using multiple CNN models. This advancement offers significant promise for enhancing the efficacy and versatility of BCIs in a wide range of real-world applications, from assistive technologies to neurorehabilitation, thereby providing robust solutions for individuals with motor disabilities.

Developing Innovative Feature Extraction Techniques from the Emotion Recognition Field on Motor Imagery Using Brain–Computer Interface EEG Signals

Research on brain–computer interfaces (BCIs) advances the way scientists understand how the human brain functions. The BCI system, which is based on the use of electroencephalography (EEG) signals to detect motor imagery (MI) tasks, enables opportunities for various applications in stroke rehabilitation, neuroprosthetic devices, and communication tools. BCIs can also be used in emotion recognition (ER) research to depict the sophistication of human emotions by improving mental health monitoring, human–computer interactions, and neuromarketing. To address the low accuracy of MI-BCI, which is a key issue faced by researchers, this study employs a new approach that has been proven to have the potential to enhance motor imagery classification accuracy. The basic idea behind the approach is to apply feature extraction methods from the field of emotion recognition to the field of motor imagery. Six feature sets and four classifiers were explored using four MI classes (left and right hands, both feet, and tongue) from the BCI Competition IV 2a dataset. Statistical, wavelet analysis, Hjorth parameters, higher-order spectra, fractal dimensions (Katz, Higuchi, and Petrosian), and a five-dimensional combination of all five feature sets were implemented. GSVM, CART, LinearSVM, and SVM with polynomial kernel classifiers were considered. Our findings show that 3D fractal dimensions predominantly outperform all other feature sets, specifically during LinearSVM classification, accomplishing nearly 79.1% mean accuracy, superior to the state-of-the-art results obtained from the referenced MI paper, where CSP reached 73.7% and Riemannian methods reached 75.5%. It even performs as well as the latest TWSB method, which also reached approximately 79.1%. These outcomes emphasize that the new hybrid approach in the motor imagery/emotion recognition field improves classification accuracy when applied to motor imagery EEG signals, thus enhancing MI-BCI performance.

Pre-movement pattern decoding from motor evoked potentials for reducing interaction delay

Brain-computer interfaces (BCIs) represent one of the most successful integrations of neuroscience and artificial intelligence, and have been applied in intelligent healthcare. However, the high complexity and low signal-to-noise ratio of electroencephalogram (EEG) signals make them susceptible to external interference and noise, leading to low decoding rates and high latency. To effectively enhance the performance of pre-movement pattern decoding from motor evoked potentials, this study proposed a robust method. We employed the filter bank common spatial patterns (FBCSP) to extract and identify event-related desynchronization (ERD) features from motor evoked potentials, and used FBCSP to investigate the ERD bands associated with actual movements. Feature vectors were classified using Cubic-SVM. The results indicated that extracting ERD features in sub-frequency bands yields more discriminative information. Approximately 530 ms before actual movement, distinct ERD patterns were observed for two movement tasks at electrode sites C3 and C4. Furthermore, frequency band selection revealed that ERD features in motor evoked potentials predominantly exist in the 17–29 Hz range. The robustness and effectiveness of the method were validated, achieving an average accuracy of 93.4 %, an average AUC of 0.954, and an average MSE of 0.195 on the self-collected hand fisting experiment dataset, and an average accuracy of 95.8 % on the BCI Competition II dataset, representing a 4.7 % improvement over the current highest classification accuracy. Overall, this study offered a promising approach for decoding pre-movement patterns from motor evoked potentials, which was crucial for enhancing the operational efficiency of brain-computer interfaces.

MACNet: A Multidimensional Attention-Based Convolutional Neural Network for Lower-Limb Motor Imagery Classification.

Decoding lower-limb motor imagery (MI) is highly important in brain-computer interfaces (BCIs) and rehabilitation engineering. However, it is challenging to classify lower-limb MI from electroencephalogram (EEG) signals, because lower-limb motions (LLMs) including MI are excessively close to physiological representations in the human brain and generate low-quality EEG signals. To address this challenge, this paper proposes a multidimensional attention-based convolutional neural network (CNN), termed MACNet, which is specifically designed for lower-limb MI classification. MACNet integrates a temporal refining module and an attention-enhanced convolutional module by leveraging the local and global feature representation abilities of CNNs and attention mechanisms. The temporal refining module adaptively investigates critical information from each electrode channel to refine EEG signals along the temporal dimension. The attention-enhanced convolutional module extracts temporal and spatial features while refining the feature maps across the channel and spatial dimensions. Owing to the scarcity of public datasets available for lower-limb MI, a specified lower-limb MI dataset involving four routine LLMs is built, consisting of 10 subjects over 20 sessions. Comparison experiments and ablation studies are conducted on this dataset and a public BCI Competition IV 2a EEG dataset. The experimental results show that MACNet achieves state-of-the-art performance and outperforms alternative models for the subject-specific mode. Visualization analysis reveals the excellent feature learning capabilities of MACNet and the potential relationship between lower-limb MI and brain activity. The effectiveness and generalizability of MACNet are verified.

Spatialspectral-Backdoor: Realizing backdoor attack for deep neural networks in brain–computer interface via EEG characteristics

In recent years, electroencephalogram (EEG) based on the brain–computer interface (BCI) systems have become increasingly advanced, with researcher using deep neural networks as tools to enhance performance. BCI systems heavily rely on EEG signals for effective human–computer interactions, and deep neural networks show excellent performance in processing and classifying these signals. Nevertheless, the vulnerability to backdoor attack is still a major problem. Backdoor attack is the injection of specially designed triggers into the model training process, which can lead to significant security issues. Therefore, in order to simulate the negative impact of backdoor attack and bridge the research gap in the field of BCI, this paper proposes a new backdoor attack method to call researcher attention to the security issues of BCI. In this paper, Spatialspectral-Backdoor is proposed to effectively attack the BCI system. The method is carefully designed to target the spectral active backdoor attack of the BCI system and includes a multi-channel preference method to select the electrode channels sensitive to the target task. Ultimately, the effectiveness of the comparison and ablation experiments is validated on the publicly available BCI competition datasets. The results show that the average attack success rate and clean sample accuracy of Spatialspectral-Backdoor in the BCI scenario are 97.12% and 85.16%, respectively, compared with other backdoor attack methods. Furthermore, by observing the infection ratio of backdoor triggers and visualization of the feature space, the proposed Spatialspectral-Backdoor outperforms other backdoor attack methods.

Spatiotemporal feature extraction method combining common spatial pattern and hybrid spatial‐temporal attention‐Net in motor imagery–brain‐computer interface system

AbstractIn recent years, motor imagery (MI) based on brain‐computer interface (BCI) has gained the attention of researchers and been widely used in many fields, such as medical rehabilitation and entertainment. The temporal and spatial features of electroencephalography (EEG) are very important for MI‐BCI classification. This study proposed a better spatiotemporal feature extraction method by combining the common spatial pattern (CSP) with a hybrid spatiotemporal attention convolutional neural network (HSTA‐Net) model. The method first intercepts the MI‐EEG into multiple time windows and projects them into the feature space and feeds into the HSTA‐Net in parallel. Subsequently, the scaled dot product attention module and multi‐head attention module are used to extract spatial feature attention. Finally, the features in multiple time windows obtained through HSTA‐Net are integrated and used for classification. The proposed method achieves a classification accuracy of 77.3% on the BCI Competition IV2a dataset. The experimental results show that the proposed model has better classification performance. The CSP‐HSTA‐Net model can quickly adapt to the distribution of MI‐EEG data during the training process, which increases the interclass distance of the extracted features and decreases its intraclass distance; it can better accomplish the MI‐BCI classification task.

Domain generalization through latent distribution exploration for motor imagery EEG classification

Electroencephalography (EEG)-based Motor Imagery (MI) brain-computer interface (BCI) systems play essential roles in motor function rehabilitation for patients with post-stroke. Existing neural networks for decoding MI EEG face challenges due to nonstationary characteristics and subject-specific variations of EEG data. To address these challenges and improve generalization performance, this study proposes a domain generalization (DG) model that eliminates the need for user-specific calibration in real-life applications. Specifically, the proposed model comprises two branches: the first branch applies several independent decision-making networks to decode and classify subjects’ motor intentions, while the second branch adaptively assigns weights to classification results and fuses them into a comprehensive decision. Both branches utilize EEGNet and ShallowConvNet to extract time-frequency-spatial features. By implementing multiple classification networks, the model can learn a broad range of data distributions from source subjects, which contributes to improved generalization performance on target subjects. The proposed EEG-DG framework was evaluated on BCI Competition IV Dataset 2a, 2b and PhysioNet. Results show that the proposed framework significantly enhances the classification performance of MI EEG, outperforming several state-of-the-art models on all three datasets, underlining its superior efficacy in real-world scenarios and exceptional generalization performance. The source code can be accessed at https://github.com/DrugLover/Multibranch-DG-EEG.

Compact convolutional transformer for subject-independent motor imagery EEG-based BCIs

Motor imagery electroencephalography (EEG) analysis is crucial for the development of effective brain-computer interfaces (BCIs), yet it presents considerable challenges due to the complexity of the data and inter-subject variability. This paper introduces EEGCCT, an application of compact convolutional transformers designed specifically to improve the analysis of motor imagery tasks in EEG. Unlike traditional approaches, EEGCCT model significantly enhances generalization from limited data, effectively addressing a common limitation in EEG datasets. We validate and test our models using the open-source BCI Competition IV datasets 2a and 2b, employing a Leave-One-Subject-Out (LOSO) strategy to ensure subject-independent performance. Our findings demonstrate that EEGCCT not only outperforms conventional models like EEGNet in standard evaluations but also achieves better performance compared to other advanced models such as Conformer, Hybrid s-CViT, and Hybrid t-CViT, while utilizing fewer parameters and achieving an accuracy of 70.12%. Additionally, the paper presents a comprehensive ablation study that includes targeted data augmentation, hyperparameter optimization, and architectural improvements.

Efficient one-step multi-trial electroencephalograph spectral clustering via unsupervised covariance-based representations

As an important research branch of artificial intelligence, decoding motor imagery electroencephalograph (MI-EEG) is notoriously famous in engineering of constructing noninvasive brain-computer interfaces (BCIs). Clustering becomes a crucial manner in decoding MI-EEG due to lack of effective labels. However, recently clustering methods for EEG rely on modeling time-series characteristics with high dimensions, as well as classical clustering frameworks, which requires a large iterative consumption. To address these challenges, we proposed a novel Efficient one-step EEG spectral clustering (EosEEGsc) method for multi-trial scenarios. Firstly, two forms of covariance-base representations are constructed for the multi-trial MI-EEG samples using unsupervised manner. Subsequently, the similarity graphs are constructed according to such representation, and a weighting strategy between similarity graphs and spectral embedding is progressively iterated using a one-step spectral clustering manner. Comparative experiments were conducted on ten MI-EEG datasets from BCI Competitions. The EosEEGsc achieved better clustering performance with lower time complexity quickly converged to local optima during the one-step framework. Ablation studies have demonstrated the necessity of two key components of EosEEGsc, and parameter sensitivities have validated the robustness. Our method offers a novel option for online MI-BCIs. When labels for MI tasks cannot be quickly annotated, employing the EosEEGsc method enables rapid cluster acquisition, thereby guiding precise control instructions for MI-BCIs output.

Transforming Motor Imagery Analysis: A Novel EEG Classification Framework Using AtSiftNet Method

This paper presents an innovative approach for the Feature Extraction method using Self-Attention, incorporating various Feature Selection techniques known as the AtSiftNet method to enhance the classification performance of motor imaginary activities using electrophotography (EEG) signals. Initially, the EEG signals were sorted and then denoised using multiscale principal component analysis to obtain clean EEG signals. However, we also conducted a non-denoised experiment. Subsequently, the clean EEG signals underwent the Self-Attention feature extraction method to compute the features of each trial (i.e., 350×18). The best 1 or 15 features were then extracted through eight different feature selection techniques. Finally, five different machine learning and neural network classification models were employed to calculate the accuracy, sensitivity, and specificity of this approach. The BCI competition III dataset IV-a was utilized for all experiments, encompassing the datasets of five volunteers who participated in the competition. The experiment findings reveal that the average accuracy of classification is highest among ReliefF (i.e., 99.946%), Mutual Information (i.e., 98.902%), Independent Component Analysis (i.e., 99.62%), and Principal Component Analysis (i.e., 98.884%) for both 1 and 15 best-selected features from each trial. These accuracies were obtained for motor imagery using a Support Vector Machine (SVM) as a classifier. In addition, five-fold validation was performed in this paper to assess the fair performance estimation and robustness of the model. The average accuracy obtained through five-fold validation is 99.89%. The experiments’ findings indicate that the suggested framework provides a resilient biomarker with minimal computational complexity, making it a suitable choice for advancing Motor Imagery Brain–Computer Interfaces (BCI).

E-SAT: an extreme learning machine based self attention approach for decoding motor imagery EEG in subject-specific tasks

The advancements in Brain-Computer Interface (BCI) have substantially evolved people's lives by enabling direct communication between the human brain and external peripheral devices. In recent years, the integration of machine larning (ML) and deep learning (DL) models have considerably imrpoved the performances of BCIs for decoding the motor imagery (MI) tasks. However, there still exist several limitations, e.g., extensive training time and high sensitivity to noises or outliers with those existing models, which largely hinder the rapid developments of BCIs. To address such issues, this paper proposes a novel extreme learning machine (ELM) based self-attention (E-SAT) mechanism to enhance subject-specific classification performances. Specifically, for E-SAT, ELM is employed both to imrpove self-attention module generalization ability for feature extraction and to optimize the model's parameter initialization process. Meanwhile, the extracted features are also classified using ELM, and the end-to-end ELM based setup is used to evaluate E-SAT performances on different MI EEG signals. Extensive experiments with different datasets, such as BCI Competition III Dataset IV-a, IV-b and BCI Competition IV Datasets 1,2a,2b,3, are conducted to verify the effectiveness of proposed E-SAT strategy. Results show that E-SAT outperforms several state-of-the-art (SOTA) existing methods in subject-specific classification on all the datasets, with an average classification accuracy of 99.8%,99.1%,98.9%,75.8%, 90.8%, and 95.4%, being achieved for each datasets, respectively. The experimental results not only show outstanding performance of E-SAT in feature extractions, but also demonstrate that it helps achieves the best results among nine other robust ones. In addition, results in this study also demonstrate that E-SAT achieves exceptional performance in both binary and multi-class classification tasks, as well as for noisy and non-noisy datatsets.&#xD.

Classification of motor imagery EEG signals using wavelet scattering transform and Bi-directional long short-term memory networks

A brain-computer interface (BCI) is a technology that creates a communication path between the brain and external devices. Raw EEG data in BCI contain a large amount of complex information, but only some of it needs to be focused on in research. So Feature extraction and classification play an important role in BCI by reducing the data dimensionality and improving the accuracy of subsequent classification. Wavelet scattering transform is an emerging feature extraction method that generates time-shift invariant representations of EEG signals. We applied the wavelet scattering transform to extract features from motor imagery EEG signals, and utilized these features for classification purposes. To achieve this, we proposed a new method that combines wavelet scattering transform with a bidirectional long short-term memory (BiLSTM) network in a fusion deep learning network. Wavelet scattering transform can deeply mine the feature information in EEG signals. In the classification stage, multiple time window features obtained in the scattering transform are sent to the BiLSTM network for classification. The final result will be determined by a vote. In addition, for the processing of raw EEG data, we proposed a time-step based time window strategy that can better utilize the small dataset. This operation can obtain EEG data of multiple time steps. The proposed method was validated using BCI competition II dataset III and BCI competition IV dataset 2b. The results show that the proposed method in this paper can effectively improve the accuracy of motor imagery EEG and provide a new idea for the feature extraction and classification research of motor imagery brain-computer interface.

Cross-Channel Specific-Mutual Feature Transfer Learning for Motor Imagery EEG Signals Decoding.

In recent years, with the rapid development of deep learning, various deep learning frameworks have been widely used in brain-computer interface (BCI) research for decoding motor imagery (MI) electroencephalogram (EEG) signals to understand brain activity accurately. The electrodes, however, record the mixed activities of neurons. If different features are directly embedded in the same feature space, the specific and mutual features of different neuron regions are not considered, which will reduce the expression ability of the feature itself. We propose a cross-channel specific-mutual feature transfer learning (CCSM-FT) network model to solve this problem. The multibranch network extracts the specific and mutual features of brain's multiregion signals. Effective training tricks are used to maximize the distinction between the two kinds of features. Suitable training tricks can also improve the effectiveness of the algorithm compared with novel models. Finally, we transfer two kinds of features to explore the potential of mutual and specific features to enhance the expressive power of the feature and use the auxiliary set to improve identification performance. The experimental results show that the network has a better classification effect in the BCI Competition IV-2a and the HGD datasets.

Enhancing Motor Imagery Classification in Brain–Computer Interfaces Using Deep Learning and Continuous Wavelet Transform

In brain–computer interface (BCI) systems, motor imagery (MI) electroencephalogram (EEG) is widely used to interpret the human brain. However, MI classification is challenging due to weak signals and a lack of high-quality data. While deep learning (DL) methods have shown significant success in pattern recognition, their application to MI-based BCI systems remains limited. To address these challenges, we propose a novel deep learning algorithm that leverages EEG signal features through a two-branch parallel convolutional neural network (CNN). Our approach incorporates different input signals, such as continuous wavelet transform, short-time Fourier transform, and common spatial patterns, and employs various classifiers, including support vector machines and decision trees, to enhance system performance. We evaluate our algorithm using the BCI Competition IV dataset 2B, comparing it with other state-of-the-art methods. Our results demonstrate that the proposed method excels in classification accuracy, offering improvements for MI-based BCI systems.

Joint multi-feature extraction and transfer learning in motor imagery brain computer interface

Motor imagery brain computer interface (BCI) systems are considered one of the most crucial paradigms and have received extensive attention from researchers worldwide. However, the non-stationary from subject-to-subject transfer is a substantial challenge for robust BCI operations. To address this issue, this paper proposes a novel approach that integrates joint multi-feature extraction, specifically combining common spatial patterns (CSP) and wavelet packet transforms (WPT), along with transfer learning (TL) in motor imagery BCI systems. This approach leverages the time-frequency characteristics of WPT and the spatial characteristics of CSP while utilizing transfer learning to facilitate EEG identification for target subjects based on knowledge acquired from non-target subjects. Using dataset IVa from BCI Competition III, our proposed approach achieves an impressive average classification accuracy of 93.4%, outperforming five kinds of state-of-the-art approaches. Furthermore, it offers the advantage of enabling the design of various auxiliary problems to learn different aspects of the target problem from unlabeled data through transfer learning, thereby facilitating the implementation of innovative ideas within our proposed approach. Simultaneously, it demonstrates that integrating CSP and WPT while transferring knowledge from other subjects is highly effective in enhancing the average classification accuracy of EEG signals and it provides a novel solution to address subject-to-subject transfer challenges in motor imagery BCI systems.

Enhancing motor imagery decoding in brain–computer interfaces using Riemann tangent space mapping and cross frequency coupling

ObjectiveMotor Imagery (MI) is a key paradigm in Brain-Computer Interfaces (BCI) aimed at decoding motor intentions from EEG signals. However, accuracy remains challenging due to data limitations, noise, and non-stationarity. MethodThis paper introduces DFBRTS, a novel method leveraging Riemannian geometry and Cross-Frequency Coupling to improve MI-EEG decoding. DFBRTS filters EEG signals using a Dichotomous Filter Bank and employs Riemann Tangent Space Mapping for feature extraction in each sub-band. A lightweight convolutional neural network then performs further feature extraction and classification, supervised by cross-entropy and center loss. Experiments on the BCI competition IV 2a and OpenBMI datasets validate its effectiveness. ResultsDFBRTS outperforms state-of-the-art methods, achieving 78.16 % accuracy for four-class and 71.58 % for two-class classification, surpassing existing benchmarks. ConclusionDFBRTS significantly enhances MI-BCI decoding, promising improved interfaces for individuals with motor ‘‘the potential of DFBRTS to advance robust MI-BCI applications.

A zero precision loss framework for EEG channel selection: enhancing efficiency and maintaining interpretability

The brain-computer interface (BCI) systems based on motor imagery typically rely on a large number of electrode channels to acquire information. The rational selection of electroencephalography (EEG) channel combinations is crucial for optimizing computational efficiency and enhancing practical applicability. However, evaluating all potential channel combinations individually is impractical. This study aims to explore a strategy for quickly achieving a balance between maximizing channel reduction and minimizing precision loss. To this end, we developed a spatio-temporal attention perception network named STAPNet. Based on the channel contributions adaptively generated by its subnetwork, we propose an extended step bi-directional search strategy that includes variable ratio channel selection (VRCS) and strided greedy channel selection (SGCS), designed to enhance global search capabilities and accelerate the optimization process. Experimental results show that on the High Gamma and BCI Competition IV 2a public datasets, the framework respectively achieved average maximum accuracies of 91.47% and 84.17%. Under conditions of zero precision loss, the average number of channels was reduced by a maximum of 87.5%. Additionally, to investigate the impact of neural information loss due to channel reduction on the interpretation of complex brain functions, we employed a heatmap visualization algorithm to verify the universal importance and complete symmetry of the selected optimal channel combination across multiple datasets. This is consistent with the brain’s cooperative mechanism when processing tasks involving both the left and right hands.

Enhanced Motor Imagery Classification through Channel Selection and Machine Learning Algorithms for BCI Applications

Brain-Computer Interface (BCI) applications utilizing Electroencephalography (EEG) signals have garnered significant attention for their potential to facilitate through communication between the brain and external devices. EEG-based BCIs offer a non-invasive means to interpret neural activity, enabling a range of applications in healthcare, gaming, and cognitive neuroscience. This study explores motor imagery (MI) EEG signals classification, employing a variety of signal processing techniques as well as machine learning algorithms to increase accuracy and reliability. Using data from the BCI Competition IV dataset, the proposed methodology involves EEG band separation via Butterworth bandpass filters, channel selection through a wrapper method using K-nearest neighbors (KNN), and classification of motor imagery tasks. The study demonstrates a high classification accuracy of 98% across different motor imagery tasks, highlighting the effectiveness of the proposed approach. This method not only shows promise for BCI applications aimed at assisting individuals with motor disabilities but also for gaming and potential security applications such as user authentication. Future work will focus on further enhancing the model's accuracy and exploring its integration into diverse practical applications.

A Method for the Spatial Interpolation of EEG Signals Based on the Bidirectional Long Short-Term Memory Network.

The precision of electroencephalograms (EEGs) significantly impacts the performance of brain-computer interfaces (BCI). Currently, the majority of research into BCI technology gives priority to lightweight design and a reduced electrode count to make it more suitable for application in wearable environments. This paper introduces a deep learning-based time series bidirectional (BiLSTM) network that is designed to capture the inherent characteristics of EEG channels obtained from neighboring electrodes. It aims to predict the EEG data time series and facilitate the conversion process from low-density EEG signals to high-density EEG signals. BiLSTM pays more attention to the dependencies in time series data rather than mathematical maps, and the root mean square error can be effectively restricted to below 0.4μV, which is less than half the error in traditional methods. After expanding the BCI Competition III 3a dataset from 18 channels to 60 channels, we conducted classification experiments on four types of motor imagery tasks. Compared to the original low-density EEG signals (18 channels), the classification accuracy was around 82%, an increase of about 20%. When juxtaposed with real high-density signals, the increment in the error rate remained below 5%. The expansion of the EEG channels showed a substantial and notable improvement compared with the original low-density signals.

EEG-VTTCNet: A loss joint training model based on the vision transformer and the temporal convolution network for EEG-based motor imagery classification

Brain-computer interface (BCI) is a technology that directly connects signals between the human brain and a computer or other external device. Motor imagery electroencephalographic (MI-EEG) signals are considered a promising paradigm for BCI systems, with a wide range of potential applications in medical rehabilitation, human–computer interaction, and virtual reality. Accurate decoding of MI-EEG signals poses a significant challenge due to issues related to the quality of the collected EEG data and subject variability. Therefore, developing an efficient MI-EEG decoding network is crucial and warrants research. This paper proposes a loss joint training model based on the vision transformer (VIT) and the temporal convolutional network (EEG-VTTCNet) to classify MI-EEG signals. To take advantage of multiple modules together, the EEG-VTTCNet adopts a shared convolution strategy and a dual-branching strategy. The dual-branching modules perform complementary learning and jointly train shared convolutional modules with better performance. We conducted experiments on the BCI Competition IV-2a and IV-2b datasets, and the proposed network outperformed the current state-of-the-art techniques with an accuracy of 84.58% and 90.94%, respectively, for the subject-dependent mode. In addition, we used t-SNE to visualize the features extracted by the proposed network, further demonstrating the effectiveness of the feature extraction framework. We also conducted extensive ablation and hyperparameter tuning experiments to construct a robust network architecture that can be well generalized.