Niu Qunfeng, Shi Lei, Niu Yang, Jia Kunming, Fan Guangxiao, Gui Ranran, Wang Li
College of Electrical Engineering, Henan University of Technology, Zhengzhou, China.
Heliyon. 2024 Feb 21;10(5):e26763. doi: 10.1016/j.heliyon.2024.e26763. eCollection 2024 Mar 15.
The key to sEMG (surface electromyography)-based control of robotic hands is the utilization of sEMG signals from the affected hand of amputees to infer their motion intentions. With the advancements in deep learning, researchers have successfully developed viable solutions for CNN (Convolutional Neural Network)-based gesture recognition. However, most studies have primarily concentrated on utilizing sEMG data from the hands of healthy subjects, often relying on high-dimensional feature vectors obtained from a substantial number of electrodes. This approach has yielded high-performing sEMG recognition systems but has failed to consider the considerable inconvenience that the abundance of electrodes poses to the daily lives and work of patients. In this paper, we focused on transradial amputees and used sEMG data from the Ninapro DB3 database as our dataset. Firstly, we introduce a STFT (Short-Time Fourier Transform)-based time-frequency feature fusion map for sEMG. This map includes both time-frequency features and the time-frequency localization of sEMG signals. Secondly, we propose an Improved DenseNet (Dense Convolutional Network) model for recognizing motion intentions in the affected hand of amputees based on their sEMG signals. Finally, addressing the issue of optimizing the number of electrodes carried by amputees, we introduce the PCMIRR (Pearson Correlation and Motion Intention Recognition Rate) algorithm. This algorithm optimizes the number of channels by considering the Pearson correlation between the sEMG channels of amputees and the recognition rate of motion intentions in the affected hand based on single-channel sEMG data. The experimental results reveal that the recognition accuracy, recall, and F1 score achieved by the Improved DenseNet model were 93.82%, 93.61%, and 93.65%, respectively. When the number of electrodes was optimized to 8, the recognition accuracy reached 94.50%. In summary, this paper ultimately attained precise recognition of motion intentions in amputees' affected hands while utilizing the minimum number of sEMG channels. This method offers a novel approach to sEMG-based control of bionic robotic hands.
基于表面肌电图（sEMG）的机器人手控制的关键在于利用截肢者患手的sEMG信号来推断其运动意图。随着深度学习的发展，研究人员已成功开发出基于卷积神经网络（CNN）的可行手势识别解决方案。然而，大多数研究主要集中在利用健康受试者手部的sEMG数据，通常依赖于从大量电极获得的高维特征向量。这种方法产生了高性能的sEMG识别系统，但没有考虑到大量电极给患者日常生活和工作带来的极大不便。在本文中，我们聚焦于经桡骨截肢者，并使用来自Ninapro DB3数据库的sEMG数据作为我们的数据集。首先，我们为sEMG引入了一种基于短时傅里叶变换（STFT）的时频特征融合图。该图包括时频特征以及sEMG信号的时频定位。其次，我们提出了一种改进的密集连接网络（DenseNet）模型，用于基于截肢者患手的sEMG信号识别其运动意图。最后，为了解决优化截肢者携带电极数量的问题，我们引入了PCMIRR（皮尔逊相关性与运动意图识别率）算法。该算法通过考虑截肢者sEMG通道之间的皮尔逊相关性以及基于单通道sEMG数据的患手运动意图识别率来优化通道数量。实验结果表明，改进的DenseNet模型实现的识别准确率、召回率和F1分数分别为93.82%、93.61%和93.65%。当电极数量优化到8个时，识别准确率达到94.50%。总之，本文最终在使用最少数量的sEMG通道的情况下，实现了对截肢者患手运动意图的精确识别。该方法为基于sEMG的仿生机器人手控制提供了一种新途径。
