Surface electromyography (sEMG) is a promising approach for non-invasive gesture recognition in human – computer interaction and rehabilitation. However, existing high-accuracy models often incur high computational costs, thereby limiting real-time deployment. To address this, we propose FSGR-Net, a lightweight residual network that reconstructs ResNet50 using a small-convolution stacking strategy and a Lite-Fusion Block. The Lite-Fusion Block integrates Depthwise Separable Convolution (DSC), Ghost Convolution, and a channel compression – expansion mechanism to reduce redundancy. In particular, a Frequency-Enhanced Channel Attention Mechanism (FECAM) is introduced after DSC layers to enhance discriminative features while mitigating the Gibbs phenomenon. Furthermore, a joint data augmentation strategy—time-shifting and masking—is applied to improve generalization. Evaluations on NinaPro DB1, DB5, and our SC-Myo Datasets show that FSGR-Net achieves 93.17%, 87.83%, and 93.35% accuracy, respectively, with only 0.85M parameters and 0.22G FLOPs, demonstrating strong potential for deployment in mobile and low-power wearable systems.
With the increasing application of three-dimensional pure aluminum microstructures in micro-electromechanical systems (MEMS) and for fabricating terahertz components, high-quality micro-shaping of pure aluminum has gradually attracted attention. Recently, high-quality three-dimensional microstructures of pure aluminum with a short machining path have been obtained through wire electrochemical micromachining (WECMM), owing to its sub-micrometer-scale machining precision. However, machining accuracy and stability decrease owing to the adhesion of insoluble products on the surface of the wire electrode in long-duration WECMM, which limits the application of pure aluminum microstructures with a long machining path. In this study, the bipolar nanosecond pulses are used to improve the machining accuracy and stability in long-duration WECMM of pure aluminum. A negative voltage of −0.5 V was considered appropriate based on experimental results. Compared with the traditional WECMM using unipolar pulses, the machining accuracy of the machined micro-slit and the duration of stable machining were significantly improved in long-duration WECMM using bipolar nanosecond pulses.
30 September 2025 in Concurrency and Computation: Practice and Experience
Three wind shear wind field modeling methods has been introduced in this paper. By use of computer numerical simulation, the model can not only simulate the real wind shear of wind field, buy can also provide other useful physical quantities. In the study of low-level wind shear detection system process, the wind field model that can truly reflect the physical characteristics change of wind field is establised. The experiments results show that the most typical shear wind field is caused by the down flow.
Patch level-based noise level estimation (NLE) is often inaccurate and inefficient because of the harsh criteria required to select a small number of homogeneous patches. In this paper, a fast image NLE method based on a global search for similar pixels is proposed to solve the above problem. Specifically, the mean square distance (MSD) is first expressed in the form of the standard deviation (std) and mean value of image patches. Afterward, the two values, std and mean, are calculated and stored in advance. Then, a 2D statistical histogram and summed area table are adopted to speed up the search for similar patches. Further, the most similar pixels are selected from similar patches to obtain an initial estimation. Finally, we correct the deviation of the initial estimation by re-injecting noise for secondary estimation. Experimental results show that the proposed method outperforms the state-of-the-art techniques in fast NLE and guided denoising.