The Decomposed-Source Multi-Task Network (DS-MTNet), a structured multi-task EEG decoding framework, is proposed, which provides a computational step toward incorporating operator-related neural evidence into machine perception in HMC.
Abstract
Current human-machine collaboration (HMC) systems rely on environment-facing sensors to observe visible actions and scene states, but the internal perceptual, intention-related, and state-related processes of operators remain insufficiently integrated into machine perception. Electroencephalography (EEG) provides a non-invasive, time-resolved modality to capture neural activity associated with these processes and can serve as an additional sensing channel in HMC. However, HMC-relevant EEG evidence is often mixed in continuous recordings. Existing EEG decoding methods usually target task-specific classification or aggregate prediction, so multiple HMC-relevant readouts are rarely organized in a unified EEG representation. To address this gap, this paper proposed the Decomposed-Source Multi-Task Network (DS-MTNet), a structured multi-task EEG decoding framework. DS-MTNet integrated three streams, namely EEG waveforms, task-routed source embeddings, and temporal-spectral power features, into reusable slots and used dual gating mechanisms to route task-specific components. The model was tested on a sustained-attention driving EEG dataset with three representative readouts: lane-departure-related epochs for environmental-event processing, steering-response stage for response preparation, and reaction-time-defined alertness state for internal state. DS-MTNet achieved the best mean performance among traditional, single-task deep, and multi-task EEG baselines, with the most robust gains observed for steering-response stage decoding. Ablation and interpretability analyses suggested that DS-MTNet jointly decoded multiple readouts and organized event-related, response-related, and state-related EEG evidence in a unified source-slot representation. These findings provide a computational step toward incorporating operator-related neural evidence into machine perception in HMC.
Electroencephalography (EEG) decoding remains challenging due to the non-stationary nature of neural signals and the limited generalization of existing models across tasks and subjects. To address this challenge, we propose a lightweight and generalizable decoding framework named Hierarchical Convolutional Fusion Transformer (HCFT), which combines dual-branch convolutional encoders and hierarchical Transformer blocks for multi-scale EEG representation learning. Specifically, the model first captures local temporal and spatiotemporal dynamics through time-domain and time space convolutional branches, and then aligns these features via a cross-attention mechanism that enables interaction between branches at each stage. Subsequently, a hierarchical Transformer fusion structure is employed to encode global dependencies across all feature stages. A task-adaptive stabilization strategy of Dynamic Tanh normalization is introduced to enhance transient feature detection and training stability. Extensive experiments are conducted on two representative cross-task benchmark datasets, BCI Competition IV-2b and CHB-MIT, covering both event-related classification and continuous seizure prediction tasks. Results show that HCFT achieves 80.83% average accuracy and a Cohen's kappa of 0.6165 on BCI IV 2b, as well as 99.10% sensitivity, 0.0236 false positives per hour, and 98.82% specificity on CHB-MIT, consistently outperforming over ten state-of-the-art baseline methods. Ablation studies confirm the effect of each core component of the proposed framework. The model also exhibits strong cross-subject generalization and structural interpretability, offering a scalable and versatile framework for advancing general-purpose neural decoding systems.
Haodong Zhang, Jiapeng Zhu, Yitong Chen et al.· IEEE journal of biomedical a...· 0 citations
Motor Imagery-based (MI) Electroencephalography (EEG) has emerged as a leading solution in non-invasive Brain-Computer Interface (BCI) systems, leveraging its strong motor intention correlation to enable reliable neural decoding. However, practical implementation of MI confronts three persistent challenges: low signal-to-noise ratio, substantial variability across subjects or over time, and inherent signal nonstationarity. These fundamental limitations continue to hinder the widespread adoption and operational reliability of MI BCI systems. Despite advances in cross-variability decoding methods, there is a lack of systematic syntheses to guide technological evolution in MI BCI. To address these challenges, this review presents a comprehensive taxonomy of MI EEG cross-variability decoding studies from 2020 to 2025, systematically organizing advances in deep learning and transfer learning. We critically evaluate core algorithmic approaches, including Convolutional Neural Networks (CNN), transformers, feature alignment, domain adaptation, and meta-learning. We then explore the underlying mechanisms of these methods and assess their efficacy across key variability paradigms (mainly cross-subject and cross-session scenarios). Finally, we summarize key findings, highlight unresolved challenges, and outline promising future research directions. These advancements hold significant potential to bridge the gap between laboratory-based MI and real-world clinical and consumer applications.
Li-Jun Wang, Yue-Ying Zhou, Peng-Pai Wang et al.· Frontiers in Neuroscience· 0 citations
Accurate decoding of motor imagery electroencephalography (MI-EEG) signals is critical for practical brain-computer interface (BCI) systems. However, conventional approaches typically rely on dense multi-channel recordings, which not only introduce data redundancy but may also incorporate noise, thereby hindering real-world deployment. To address this challenge, we propose a graph neural network-based co-optimization framework that simultaneously performs channel selection and MI classification. The framework comprises two core components: one is the Key Channel Locator (KCL), which models EEG electrodes as graph nodes and identifies a subject-specific, fixed-size subset of informative channels through a dual-perspective evaluation that integrates graph convolutional topology with self-attention-derived feature importance, and the other is the UniEEG-Net, which efficiently decodes MI tasks from the selected channels using multi-scale temporal convolutions, depthwise separable spatial projection, and a self-attention mechanism. We extensively validate the proposed method on three datasets, including BCI Competition IV 2a, High Gamma, and a newly collected dataset. Experimental results demonstrate that our approach achieves performance comparable to that obtained with all channels while using significantly fewer electrodes. Moreover, UniEEG-Net exhibits classification accuracy surpassing current state-of-the-art models. The entire system is thus well-suited for real-world BCI applications, particularly in neurorehabilitation.
Hao-Yu Li, Wei-Dong Dang, Lei Liu et al.· Chaos· 0 citations
Auditory attention decoding (AAD) identifies the attended speaker from physiological signals, supporting neuro-steered hearing devices and natural human-machine interaction. Electroencephalography (EEG) is the dominant modality for AAD but provides incomplete evidence in naturalistic audio-visual scenes, motivating EEG and electrooculography (EOG) fusion. Existing approaches remain limited by weak cross-modal interaction, inefficient temporal modeling, and low robustness to sample variations. To address the limitations, we propose RAMamba-Net, a reliability-aware Mamba-based multimodal fusion network for AAD. RAMamba-Net employs a Mamba-enhanced band-aware convolutional Transformer to capture band-specific EEG patterns and long-range temporal dynamics. A dual-branch temporal-spatial encoder models EOG temporal and inter-channel dependencies. Cross-modal attention enables explicit modality interaction. Then, a reliability-aware module is introduced to estimate sample-wise modality weights for feature and prediction consistency, thereby enhancing multimodal fusion. Experiments on two AAD benchmarks demonstrate that RAMamba-Net effectively exploits complementary EEG-EOG information, yielding accuracy gains of 5.76% over unimodal baselines, together with more robust decoding and discriminative representations. Further analyses show that explicit cross-modal interaction improves multimodal alignment, while the reliability-aware module suppresses unreliable modality evidence and is robust to signal perturbation and parameter variation.
OBJECTIVE
Electroencephalography (EEG) is widely used in brain-computer interfaces (BCIs), but its microvolt-level signals are easily contaminated by electromyography (EMG), electrooculography (EOG), and mixed physiological artifacts. This study develops an EEG denoising framework that suppresses artifacts while preserving information used by downstream biomedical artificial intelligence (AI) tasks. Approach. We propose MTGNet, a task-oriented and spectrally guided EEG denoising framework. MTGNet combines Low-Rank Adaptation (LoRA)-based Task-Aware Consistency Regularization (TACR), a spectrally aware Guidance Network, and parallel Mamba-Transformer backbone. A pretrained 11.97M-parameter backbone learns to preserve intrinsic EEG characteristics from paired noisy-clean data, while 0.33M LoRA parameters enable task-specific adaptation without requiring paired clean EEG references. Main results. On EEGDenoiseNet, MTGNet reduces spectral relative root-mean-square error (S-RRMSE) by over 18.9%, 31.5%, and 14.0% for EMG, EOG, and hybrid artifacts, respectively (p<0.001). On a real-world fatigue EEG dataset, it improves classification accuracy by 6.20-6.69 percentage points compared with unprocessed inputs (p<0.05). Ablation, cross-classifier, and cross-dataset analyses validate the proposed components and support the transferability of MTGNet across the evaluated settings. Significance. The proposed framework provides a practical approach to task-aware EEG denoising, while future work should further validate its applicability across real-world EEG settings involving diverse tasks, artifact types, and acquisition conditions.
Jin-Cheng Hu, Zhongke Gao, Yushi Hao et al.· Journal of Neural Engineerin...· 0 citations
Brain-machine interfaces provide a link between neural activity and external devices, enabling restoration of motor function and advancing human-machine interaction using non-invasive electroencephalography (EEG). However, continuous grasp force decoding remains challenging due to complex temporal dynamics, high inter-subject variability, and limited generalisation of existing approaches. To address this, we propose a hybrid EEG decoding framework that jointly models continuous and tokenised representations, enabling capture of both fine-grained neural structure and long-range temporal dependencies. The proposed approach integrates convolutional-recurrent representation learning, quantisation-based tokenisation, and transformer-based temporal modelling within a unified fusion-based regression architecture. Experimental evaluation on the WAY-EEG-GAL dataset under strict leave-one-subject-out conditions achieves $R^2$ = 0.817 in offline settings and $R^2$ = 0.793 in simulated real-time evaluation, with latency suitable for real-time deployment. These results demonstrate strong cross-subject generalisation and highlight the practicality of hybrid continuous-tokenised representations for real-time EEG-based force decoding in assistive robotics, neuro-rehabilitation, and human-machine interaction.
Sankalp Sunil Turankar, Y. Meena· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
