Electromyography (EMG) signals find wide applications in the fields of medicine, sports, and rehabilitation. However, the collection of EMG signals is a laborious process constrained by ethical limitations, resulting in a scarcity of available data and limiting its applicability in various tasks. This study aims to address this limitation by employing generative techniques to synthesize high-quality and diverse EMG signal samples and evaluating their classification accuracy through gesture recognition tasks. We propose an improved approach based on Diffusion Probabilistic Models (DDPM), specifically tailored to the characteristics of EMG signals and the requirements of low-data setting. Our approach employs a conditional generative method, leveraging diffusion models and introducing a patch-based training strategy. Additionally, we have improved the network architecture of DDPM to better suit the task of few-shot EMG signals generation. We evaluate the performance of the generated EMG signals in gesture recognition tasks using the Ninapro DB4, DB5, BioPatRec DB2, and DB3 datasets. The results indicate that when using 20% of the available data for training and generating the same amount of synthetic samples, the average classification accuracy of the generated data reached 94.31% of that of the real data. These findings demonstrate the effectiveness of our approach in modeling the distribution of real data and generating usable synthetic data. Moreover, the addition of synthetic data to the training set significantly enhances classification performance, further validating the efficacy of the generated data. Our proposed approach based on diffusion models exhibits promising performance in few-shot EMG signal generation task. This research contributes to the field of EMG signal synthesis and offers new possibilities for data augmentation, enabling more robust and accurate analysis of EMG signals in various applications.

Enhancing information representation in electromyography (EMG) signals is pivotal for interpreting human movement intentions. Traditional methods often concentrate on specific aspects of EMG signals, such as the time or frequency domains, while overlooking spatial features and hidden human motion information that exist across EMG channels. In response, we introduce an innovative approach that integrates multiple feature domains, including time, frequency, and spatial characteristics. By considering the spatial distribution of surface electromyographic electrodes, our method deciphers human movement intentions from a multidimensional perspective, resulting in significantly enhanced gesture recognition accuracy. Our approach employs a divide-and-conquer strategy to reveal connections between different muscle regions and specific gestures. Initially, we establish a microscopic viewpoint by extracting time-domain and frequency-domain features from individual EMG signal channels. We subsequently introduce a macroscopic perspective and incorporate spatial feature information by constructing an inter-channel electromyographic signal covariance matrix to uncover potential spatial features and human motion information. This dynamic fusion of features from multiple dimensions enables our approach to provide comprehensive insights into movement intentions. Furthermore, we introduce the space-to-space (SPS) framework to extend the myoelectric signal channel space, unleashing potential spatial information within and between channels. To validate our method, we conduct extensive experiments using the Ninapro DB4, Ninapro DB5, BioPatRec DB1, BioPatRec DB2, BioPatRec DB3, and Mendeley Data datasets. We systematically explore different combinations of feature extraction techniques. After combining multi-feature fusion with spatial features, the recognition performance of the ANN classifier on the six datasets improved by 2.53%, 2.15%, 1.15%, 1.77%, 1.24%, and 4.73%, respectively, compared to a single fusion approach in the time and frequency domains. Our results confirm the substantial benefits of our fusion approach, emphasizing the pivotal role of spatial feature information in the feature extraction process. This study provides a new way for surface electromyography-based gesture recognition through the fusion of multi-view features.

In the task of upper-limb pattern recognition, effective feature extraction, channel selection, and classification methods are crucial for the construction of an efficient surface electromyography (sEMG) signal classification framework. However, existing deep learning models often face limitations due to improper channel selection methods and overly specific designs, leading to high computational complexity and limited scalability. To address this challenge, this study introduces a deep learning network based on channel feature compression—partial channel selection sEMG net (PCS-EMGNet). This network combines channel feature compression (channel selection) and feature extraction (partial block), aiming to reduce the model’s parameter count while maintaining recognition accuracy. PCS-EMGNet extracts high-dimensional feature vectors from sEMG signals through the partial block, decoding spatial and temporal feature information. Subsequently, channel selection compresses and filters these high-dimensional feature vectors, accurately selecting channel features to reduce the model’s parameter count, thereby decreasing computational complexity and enhancing the model’s processing speed. Moreover, the proposed method ensures the stability of classification, further improving the model’s capability of recognizing features in sEMG signal data. Experimental validation was conducted on five benchmark databases, namely the NinaPro DB4, NinaPro DB5, BioPatRec DB1, BioPatRec DB2, and BioPatRec DB3 datasets. Compared to traditional gesture recognition methods, PCS-EMGNet significantly enhanced recognition accuracy and computational efficiency, broadening its application prospects in real-world settings. The experimental results showed that our model achieved the highest average accuracy of 88.34% across these databases, marking a 9.96% increase in average accuracy compared to models with similar parameter counts. Simultaneously, our model’s parameter size was reduced by an average of 80% compared to previous gesture recognition models, demonstrating the effectiveness of channel feature compression in maintaining recognition accuracy while significantly reducing the parameter count.

Electroencephalography (EEG) is a widely used tool for monitoring brain activity, but it is often disturbed by various artifacts, such as electrooculography (EOG), electromyography (EMG), and electrocardiography (ECG), which degrade signal quality and affect subsequent analysis. Effective EEG denoising is critical for enhancing the performance of EEG-based applications, including disease diagnosis and brain-computer interfaces (BCIs). While recent deep learning (DL) approaches have shown promise in this area, they often struggle to efficiently model the temporal dependencies inherent in EEG signals, as well as to capture local contextual information simultaneously. In this work, we introduce DenoiseMamba, a novel deep learning-based EEG denoising model. The model incorporates the ConvSSD module, which integrates convolutional neural networks (CNNs) with structured state-space duality (SSD) mechanisms. This allows DenoiseMamba to capture both local and global spatiotemporal features, resulting in more effective artifact suppression. Extensive experiments on three semi-simulated datasets demonstrate that DenoiseMamba outperforms existing methods in EEG reconstruction accuracy, effectively eliminating myoelectric, electrooculographic, and electrocardiographic artifacts while preserving critical EEG signal details.