Decoding upper-limb movements from scalp electroencephalography (EEG) is an important problem for brain-computer interfaces (BCIs), but many deep learning models provide limited insight into the brain regions underlying their predictions. We propose a two-branch architecture that combines an LGGNet-inspired local-global graph branch with an EEGNet-style convolutional branch for movement-versus-rest classification. The graph branch groups 61 EEG electrodes into anatomically informed regions and learns their spatial relationships, providing a direct representation of the regions emphasized by the model. We evaluate the proposed architecture using leave-one-subject-out cross-validation on the Ofner upper-limb movement dataset. The model achieves a mean F1-score of 0.74 +/- 0.06 across subjects. Beyond classification performance, we analyze the learned graph structure to identify the regions with the strongest connectivity. Across all held-out subjects, the highest connectivity is consistently observed in the Parietal Left Low region, corresponding to electrodes P1 and P3. This region is opposite to the performed right-arm movements and lies within the posterior parietal area previously associated with upper-limb movement processing. These results show that incorporating a region-based graph into the decoder can provide an anatomically interpretable representation while maintaining effective movement classification, offering a practical approach toward more transparent EEG-based BCIs.
Figures & tables
Fig. 1 : Overview of the proposed dual-branch architecture for movement-versus-rest EEG decoding. A shared temporal feature extraction module feeds an LGGNet-inspired local–global graph branch and an EEGNet-style convolutional branch. Their representations are fused and passed to the final classifier.
Fig. 2 : Spatial grouping of the 61 EEG electrodes into 25 anatomically informed regions used by the graph branch. Spatially adjacent electrodes are grouped according to their scalp locations and channel families. The resulting regions form the nodes of the global graph.
Subject
F1 score (Mean ± Std)
Subject
F1 score (Mean ± Std)
S1
0.72±0.05
S9
0.68±0.03
S2
0.82±0.03
S10
0.85±0.09
S3
0.76±0.08
S11
0.77±0.06
S4
0.77±0.04
S12
0.68±0.04
S5
0.74±0.06
S13
0.69±0.02
S6
0.81±0.02
S14
0.61±0.08
TABLE I : Per-subject movement-versus-rest F1 score under leave-one-subject-out cross-validation. Each value represents the mean ± standard deviation across five runs with different training and validation splits.
Fig. 3 : Final learned adjacency matrix for a representative held-out subject (S4), combining the learned spatial relationships from the graph branch. Rows and columns correspond to the 25 predefined EEG regions, and matrix values represent the learned connectivity strengths between region pairs.
Fig. 4 : Ranking of EEG regions according to their connectivity strength in the learned graph for a representative held-out subject (S4). Region strength is computed as the sum of the learned edge weights associated with each region.
Motor imagery (MI) brain--computer interfaces (BCIs) have emerged as a promising approach for establishing flexible communication pathways between the human brain and external devices , particularly for individuals affected by stroke or neurodegenerative disorders. Reliable decoding of motor-imagery electroencephalography (MI-EEG) remains challenging because EEG recordings contain substantial noise and exhibit complex, weakly informative relationships with the underlying brain activity. Although deep learning provides an effective means of learning representations directly from EEG signals, its application to MI-EEG feature learning remains comparatively limited. This study introduces a hybrid deep-learning architecture that integrates a convolutional neural network (CNN) with a bidirectional long short-term memory (bi-LSTM) network. The CNN is used to learn high-level spatial and temporal representations directly from raw MI-EEG recordings, whereas the bi-LSTM models temporal dependencies and relationships among the extracted features. The proposed approach is evaluated using both a publicly available dataset and a privately acquired dataset obtained with an EEG acquisition system. The experimental results indicate that the CNN&bi-LSTM architecture provides robust performance for both two- and three-class motor-imagery classification and demonstrates promising subject-independent decoding capability across the evaluated methods.
Athanasios Karagounis
School of Science, Department of Digital Industry Technologies GR34400, Psachna, Greece
In this paper, we consider applying computer vision algorithms for the classification problem one faces in neuroscience during EEG data analysis. Our approach is to apply a combination of computer vision and neural network methods to solve human brain activity classification problems during hand movement. We pre-processed raw EEG signals and generated 2D EEG topograms. Later, we developed supervised and semi-supervised neural networks to classify different motor cortex activities.
Albert Nasybullin, Semen Kurkin
Faculty of Computer Science and Engineering, Innopolis University, Innopolis, Russia · Neuroscience and Cognitive Technology Laboratory, Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia
Brain-machine interfaces (BMIs) can assist individuals with limited mobility, such as stroke survivors or amputees. One of the key challenges in developing BMIs is expanding their usability and control, which can be achieved by accurately decoding multiple kinematic and kinetic parameters. To address this, we propose three regression models: partial least squares regressor, multilayered perceptron, and attention based regressor, to decode multiple movement parameters from EEG signals. We evaluated these models on the WAY EEG GAL dataset, focusing on their performance under subject specific and subject independent conditions with two strategies: a single model for all parameters and a baseline with separate models for each parameter. Among all regressors, the attention based regressor achieved the best performance, with an R2 of 0.8 and a latency of 29.2 milliseconds, demonstrating significant improvement in simultaneous multi parameter decoding. However, its performance dropped for single parameter decoding. The multi layered perceptron showed more consistent but lower accuracy across both decoding types (R2 = 0.49). These findings highlight the potential of attention based models for real time multi command BMI systems and contribute to the development of more intuitive control devices.
Parth G. Dangi, Yogesh Kumar Meena
Human-AI Interaction (HAIx) Lab, IIT Gandhinagar, India