School of Medical Technology and Engineering, Henan University of Science and Technology, Luoyang 471023, China.
School of Mechanical and Electrical Engineering, Henan University of Science and Technology, Luoyang 471003, China.
Sensors (Basel). 2024 Apr 24;24(9):2702. doi: 10.3390/s24092702.
Currently, surface EMG signals have a wide range of applications in human-computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model's capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.
目前，表面肌电信号在人机交互系统中有广泛的应用。然而，基于传统机器学习为手势识别模型选择特征可能具有挑战性，并且可能无法产生令人满意的结果。考虑到神经网络的强大非线性泛化能力，本文提出了一种具有注意力机制的双流残差网络模型，用于手势识别。一个分支处理表面肌电信号，另一个分支处理手加速度信号。分段网络用于充分提取手的生理和运动特征。为了增强模型学习关键信息的能力，我们在全局平均池化后引入了注意力机制。该机制增强了相关特征，削弱了不相关特征。最后，融合来自两个分支学习的深度特征，进一步提高多手势识别的准确性。在 NinaPro DB2 公共数据集上进行的实验，对于 49 个手势，识别准确率达到 88.25%。这表明，我们的网络模型可以有效地捕捉手势特征，提高各种手势的准确性和鲁棒性。这种多源信息融合方法有望为外骨骼机器人和肌电假肢控制系统提供更准确和实时的命令，从而提高用户体验和机器人操作的自然性。
