Real-time finger force prediction via parallel convolutional neural networks: a preliminary study
Real-time finger force prediction via parallel convolutional neural networks: a preliminary study
复制标题
通过并行卷积神经网络进行实时手指力预测：初步研究
DOI：
10.1109/embc44109.2020.9175390
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Hu, Xiaogang
中科院分区：
文献类型：
--
作者：
Xu, Feng;Zheng, Yang;Hu, Xiaogang
连续而准确地解码预期运动是人机交互的关键。在这里，我们开发了一种新的方法，利用并行卷积神经网络(CNN)实时连续预测单个手指的作用力。我们在没有棘波排序的平行结构中使用CNN来提取群体运动单位放电频率。基于高密度肌电(HD-EMG)的两个特征，即时间能量热图和频谱图来训练CNN参数。然后，基于线性回归模型，使用群体运动单位放电频率来连续预测指力。与传统的肌电幅度法和运动单元分解法的力预测性能进行了比较。结果表明，CNN方法的预测力与实测力之间的相关系数平均为0.91，而离线分解法、在线分解法和肌电振幅法的相关系数分别为0.89、0.82和0.81。此外，基于CNN的方法显示出可推广的性能，CNN针对一个手指进行训练，适用于不同的手指。结果表明，基于CNN的算法可以为人机交互提供一种准确高效的力解码方法。
Continuous and accurate decoding of intended motions is critical for human-machine interactions. Here, we developed a novel approach for real-time continuous prediction of forces in individual fingers using parallel convolutional neural networks (CNNs). We extracted populational motor unit discharge frequency using CNNs in a parallel structure without spike sorting. The CNN parameters were trained based on two features from high-density electromyogram (HD-EMG), namely temporal energy heatmaps and frequency spectrum maps. The populational motor unit discharge frequency was then used to continuously predict finger forces based on a linear regression model. The force prediction performance was compared with a motor unit decomposition method and the conventional EMG amplitude-based method. Our results showed that the correlation coefficient between the predicted and the recorded forces of the CNN approach was on average 0.91, compared with the offline decomposition method of 0.89, the online decomposition method of 0.82, and the EMG amplitude method of 0.81. Additionally, the CNN based approach showed generalizable performance, with CNN trained on one finger applicable to a different finger. The outcomes suggest that our CNN based algorithm can offer an accurate and efficient force decoding method for human-machine interactions.
登录
查看更多内容
影响因子：
4
作者：
Zheng，Yang;Hu，Xiaogang
通讯作者：
Hu，Xiaogang
DOI：
10.1109/jbhi.2019.2926307
发表时间：
2020-03-01
影响因子：
7.7
作者：
Dai, Chenyun;Hu, Xiaogang
通讯作者：
Hu, Xiaogang
影响因子：
7.7
作者：
Dai, Chenyun;Hu, Xiaogang
通讯作者：
Hu, Xiaogang
影响因子：
7.7
作者：
Dai, Chenyun;Hu, Xiaogang
通讯作者：
Hu, Xiaogang