Objective.Deep learning (DL) networks are increasingly attracting attention across various fields, including electroencephalography (EEG) signal processing. These models provide comparable performance to that of traditional techniques. At present, however, there is a lack of well-structured and standardized datasets with specific benchmark limit the development of DL solutions for EEG denoising.Approach.Here, we present EEGdenoiseNet, a benchmark EEG dataset that is suited for training and testing DL-based denoising models, as well as for performance comparisons across models. EEGdenoiseNet contains 4514 clean EEG segments, 3400 ocular artifact segments and 5598 muscular artifact segments, allowing users to synthesize contaminated EEG segments with the ground-truth clean EEG.Main results.We used EEGdenoiseNet to evaluate denoising performance of four classical networks (a fully-connected network, a simple and a complex convolution network, and a recurrent neural network). Our results suggested that DL methods have great potential for EEG denoising even under high noise contamination.Significance.Through EEGdenoiseNet, we hope to accelerate the development of the emerging field of DL-based EEG denoising. The dataset and code are available athttps://github.com/ncclabsustech/EEGdenoiseNet.

Balance and walking are fundamental to support common daily activities. Relatively accurate characterizations of normal and impaired gait features were attained at the kinematic and muscular levels. Conversely, the neural processes underlying gait dynamics still need to be elucidated. To shed light on gait‐related modulations of neural activity, we collected high‐density electroencephalography (hdEEG) signals and ankle acceleration data in young healthy participants during treadmill walking. We used the ankle acceleration data to segment each gait cycle in four phases: initial double support, right leg swing, final double support, left leg swing. Then, we processed hdEEG signals to extract neural oscillations in alpha, beta, and gamma bands, and examined event‐related desynchronization/synchronization (ERD/ERS) across gait phases. Our results showed that ERD/ERS modulations for alpha, beta, and gamma bands were strongest in the primary sensorimotor cortex (M1), but were also found in premotor cortex, thalamus and cerebellum. We observed a modulation of neural oscillations across gait phases in M1 and cerebellum, and an interaction between frequency band and gait phase in premotor cortex and thalamus. Furthermore, an ERD/ERS lateralization effect was present in M1 for the alpha and beta bands, and in the cerebellum for the beta and gamma bands. Overall, our findings demonstrate that an electrophysiological source imaging approach based on hdEEG can be used to investigate dynamic neural processes of gait control. Future work on the development of mobile hdEEG‐based brain–body imaging platforms may enable overground walking investigations, with potential applications in the study of gait disorders.

Currently, the integration of artificial intelligence (AI) techniques with multimodal physiological signals represents a pivotal approach to detect affective disorders (ADs). With the increasing complexity and diversity of physiological signal modalities, researchers have introduced various AI methods using multimodal physiological signals to improve model classification performance and explainability to increase trust and facilitate clinical adoption. Among these methods, spiking neural networks (SNNs) stand out as a promising avenue due to their alignment with the operating principles of the human brain, robust biological explainability, and adeptness in processing spatial–temporal information in an efficient event-driven manner with low power consumption. Furthermore, the emergence of neuromorphic computing (NC) chips based on SNNs has greatly bolstered the field of NC, enabling effective support for objective, pervasive, and wearable AI-assisted medical diagnostic devices for ADs and other diseases. This article presents a review of recent achievements in multimodal AD detection and points out the associated challenges in utilizing multimodal physiological signals and NC based on SNNs for AD detection. Building upon this foundation, we give perspectives on future work. The intended readership for this review consists of researchers in the fields of cognitive computing, computational psychophysiology, affective computing, NC, and brain-inspired computing. We hope that this survey not only garners increased attention from the scientific community but also serves as a valuable guide for future studies in this field.

EEG source localization is an important technical issue in EEG analysis. Despite many numerical methods existed for EEG source localization, they all rely on strong priors and the deep sources are intractable. Here we propose a deep learning framework using spatial basis function decomposition for EEG source localization. This framework combines the edge sparsity prior and Gaussian source basis, called Edge Sparse Basis Network (ESBN). The performance of ESBN is validated by both synthetic data and real EEG data during motor tasks. The results suggest that the supervised ESBN outperforms the traditional numerical methods in synthetic data and the unsupervised fine-tuning provides more focal and accurate localizations in real data. Our proposed deep learning framework can be extended to account for other source priors, and the real-time property of ESBN can facilitate the applications of EEG in brain-computer interfaces and clinics.

Objective. Electroencephalography (EEG) is a widely used technique to address research questions about brain functioning, from controlled laboratorial conditions to naturalistic environments. However, EEG data are affected by biological (e.g. ocular, myogenic) and non-biological (e.g. movement-related) artifacts, which—depending on their extent—may limit the interpretability of the study results. Blind source separation (BSS) approaches have demonstrated to be particularly promising for the attenuation of artifacts in high-density EEG (hdEEG) data. Previous EEG artifact removal studies suggested that it may not be optimal to use the same BSS method for different kinds of artifacts. Approach. In this study, we developed a novel multi-step BSS approach to optimize the attenuation of ocular, movement-related and myogenic artifacts from hdEEG data. For validation purposes, we used hdEEG data collected in a group of healthy participants in standing, slow-walking and fast-walking conditions. During part of the experiment, a series of tone bursts were used to evoke auditory responses. We quantified event-related potentials (ERPs) using hdEEG signals collected during an auditory stimulation, as well as the event-related desynchronization (ERD) by contrasting hdEEG signals collected in walking and standing conditions, without auditory stimulation. We compared the results obtained in terms of auditory ERP and motor-related ERD using the proposed multi-step BSS approach, with respect to two classically used single-step BSS approaches. Main results. The use of our approach yielded the lowest residual noise in the hdEEG data, and permitted to retrieve stronger and more reliable modulations of neural activity than alternative solutions. Overall, our study confirmed that the performance of BSS-based artifact removal can be improved by using specific BSS methods and parameters for different kinds of artifacts. Significance. Our technological solution supports a wider use of hdEEG-based source imaging in movement and rehabilitation studies, and contributes to the further development of mobile brain/body imaging applications.

Given the significant global health burden caused by depression, numerous studies have utilized artificial intelligence techniques to objectively and automatically detect depression. However, existing research primarily focuses on improving the accuracy of depression recognition while overlooking the explainability of detection models and the evaluation of feature importance. In this paper, we propose a novel framework named Enhanced Domain Adversarial Neural Network (E-DANN) for depression detection. First, we extract joint features that combine audio-specific physical properties and EEG responses to construct a multimodal feature space, which facilitates the understanding of how EEG signals dynamically respond to the physical properties of audio. Next, we employ the feature decoupling framework of E-DANN, which separates the extracted feature space into shared features and private features through adversarial training. The decoupled private features are then utilized for the binary classification of depression. Our experimental results validate the effectiveness of the proposed framework, which achieves accurate classification of normal controls and individuals with depression (accuracy: 92.28 ± 7.45%, specificity: 94.67 ± 7.30%, sensitivity: 89.11 ± 1.01%, and F1 score: 90.89 ± 8.60%). Furthermore, we employ an Explainable Artificial Intelligence (XAI) approach to hierarchically visualize feature importance and elucidate complex feature interaction patterns. In summary, this study provides a theoretical foundation for developing explainable diagnostic tools for depression and contributes to improving the clinical trustworthiness of AI-assisted diagnostic systems.