Recently, deep-learning-based approaches have been widely applied in sEMG-based gesture recognition. While some existing methods have explored the integration of time-domain and frequency-domain features, many still face challenges in comprehensively leveraging the complementary information from both domains, often due to limitations in capturing multi-scale temporal dependencies or sub-optimal fusion strategies. To address these persistent limitations and further enhance accuracy and robustness, we propose the Multi-Scale Dual-Stream Fusion Network (MSDS-FusionNet), a novel deep learning framework that integrates temporal and frequency-domain features for enhanced gesture classification accuracy. MSDS-FusionNet introduces two key innovations: the Multi-Scale Mamba (MSM) modules, which extract multi-scale temporal features through parallel convolutions with varying kernel sizes and linear-time sequence modeling with selective state spaces, enabling the capture of temporal patterns at multiple scales and the modeling of both short-term and long-term dependencies; and the Bi-directional Attention Fusion Module (BAFM), which effectively combines temporal and frequency-domain features using bi-directional attention mechanisms to fuse complementary information and improve recognition accuracy dynamically. Extensive experiments on the NinaPro dataset demonstrate that MSDS-FusionNet outperforms state-of-the-art methods, achieving accuracy improvements of up to 2.41%, 2.46%, and 1.38% on the DB2, DB3, and DB4 datasets, respectively, with final accuracies of 90.15%, 72.32%, and 87.10%. This study presents a robust and flexible solution for sEMG-based gesture recognition, effectively addressing the complexities of recognizing intricate gestures and offering significant potential for applications in prosthetics, virtual reality, and assistive technologies. The code of this study is available at https://github.com/hdy6438/MSDS-FusionNet.

This paper addresses the challenge of offloading resource-intensive image segmentation tasks and allocating computing resources within the Internet of Vehicles (IoV) using edge-based AI. To overcome the limitations of onboard computing in smart vehicles, this study develops an efficient edge computing resource allocation system. The core of this system is an improved model-free soft actor–critic (iSAC) algorithm, which is enhanced by incorporating prioritized experience replay (PER). This PER-iSAC algorithm is designed to accelerate the learning process, maintain stability, and improve the efficiency and accuracy of computation offloading. Furthermore, an integrated computing and networking scheduling framework is employed to minimize overall task completion time. Simulation experiments were conducted to compare the PER-iSAC algorithm against baseline algorithms (Standard SAC and PPO). The results demonstrate that the proposed PER-iSAC significantly reduces task allocation error rates and optimizes task completion times. This research offers a practical engineering solution for enhancing the computational capabilities of IoV systems, thereby contributing to the development of more responsive and reliable autonomous driving applications.

This paper investigates the offloading of image segmentation tasks and the allocation of corresponding computing resources for the Internet of Vehicles (IoV) supported by edge intelligence. With the convergence of 5G technology and artificial intelligence, the demand for high-precision sensors and navigation in smart connected vehicles is growing. Image segmentation technology, a crucial component of autonomous driving systems, requires substantial computing power and communication bandwidth. Faced with the shortage of onboard computing power and rising costs, edge computing offers a solution by offloading computing tasks to roadside servers close to the data source, i.e., connected cars, thereby alleviating network bandwidth and power consumption pressures and reducing system latency. This paper constructs an efficient edge computing resource allocation system based on an improved model-free Soft Actor-Critic (iSAC) algorithm with maximum entropy, and enhances the offloading efficiency by employing an integrated computing and networking scheduling framework to minimize task completion time. By incorporating Prioritized Experience Replay (PER), the iSAC algorithm accelerates the learning process while maintaining stability and improving the efficiency and accuracy of computation offloading. Simulation experiments compare the performance of iSAC with baseline algorithms, demonstrating its advantages in reducing error rates and optimizing task completion time. Future research will investigate task diversity and priority requirements in IoV.

Recently, deep-learning-based approaches have been widely applied in sEMG-based gesture recognition, however, existing methods typically focus on either time-domain or frequency-domain features, failing to leverage the complementary information from both domains, which limits the accuracy and robustness of gesture recognition systems. To address these limitations, we propose the Multi-Scale Dual-Stream Fusion Network (MSDS-FusionNet), a novel deep learning framework that integrates temporal and frequency-domain features for enhanced gesture classification accuracy. MSDS-FusionNet introduces two key innovations: the Multi-Scale Mamba (MSM) modules, which extract multi-scale temporal features through parallel convolutions with varying kernel sizes and linear-time sequence modeling with selective state spaces, enabling the capture of temporal patterns at multiple scales and the modeling of both short-term and long-term dependencies; and the Bi-directional Attention Fusion Module (BAFM), which effectively combines temporal and frequency-domain features using bi-directional attention mechanisms to fuse complementary information and improve recognition accuracy dynamically. Extensive experiments on the NinaPro dataset demonstrate that MSDS-FusionNet outperforms state-of-the-art methods, achieving accuracy improvements of up to 2.41%, 2.46%, and 1.38% on the DB2, DB3, and DB4 datasets, respectively, with final accuracies of 90.15%, 72.32%, and 87.10%. This study presents a robust and flexible solution for sEMG-based gesture recognition, effectively addressing the complexities of recognizing intricate gestures and offering significant potential for applications in prosthetics, virtual reality, and assistive technologies. The code of this study is available at https://github.com/hdy6438/MSDS-FusionNet.