A generic neural network model to estimate populational neural activity for robust neural decoding
A generic neural network model to estimate populational neural activity for robust neural decoding
复制标题
DOI：
10.1016/j.compbiomed.2022.105359
复制
发表时间：
2022-03
影响因子：
7.7
通讯作者：
R. Roy;Feng Xu;D. Kamper;Xiaogang Hu
中科院分区：
文献类型：
--
作者：
R. Roy;Feng Xu;D. Kamper;Xiaogang Hu
鲁棒和连续的神经解码对于可靠和直观的神经机器交互至关重要。本研究开发了一种新的通用神经网络模型，可以连续预测手指的力量解码的人口运动神经元放电activity.MethodWe实现卷积神经网络（CNN）学习映射从高密度肌电图（HD-EMG）信号的前臂肌肉人口运动神经元放电频率。由于肌电信号具有内在的随机性，我们首先提取肌电信号能量和频率图的时空特征，以提高学习效率。然后，我们通过训练多个参与者的群体神经元放电活动，建立了一个通用的神经网络模型。使用回归模型，我们连续实时预测单个手指的力。我们比较了两个国家的最先进的方法的力预测性能：神经元分解方法和一个经典的EMG振幅method.ResultsOur的结果表明，通用CNN模型优于特定主题的神经元分解方法和EMG振幅的方法，表现出较高的相关系数之间的测量和预测力，和较低的力预测误差。此外，CNN模型揭示了更稳定的力预测性能随着时间的推移。ConclusionsOverall，我们的方法提供了一个通用的和有效的连续神经解码方法的实时和强大的人机交互。
BackgroundRobust and continuous neural decoding is crucial for reliable and intuitive neural-machine interactions. This study developed a novel generic neural network model that can continuously predict finger forces based on decoded populational motoneuron firing activities.MethodWe implemented convolutional neural networks (CNNs) to learn the mapping from high-density electromyogram (HD-EMG) signals of forearm muscles to populational motoneuron firing frequency. We first extracted the spatiotemporal features of EMG energy and frequency maps to improve learning efficiency, given that EMG signals are intrinsically stochastic. We then established a generic neural network model by training on the populational neuron firing activities of multiple participants. Using a regression model, we continuously predicted individual finger forces in real-time. We compared the force prediction performance with two state-of-the-art approaches: a neuron-decomposition method and a classic EMG-amplitude method.ResultsOur results showed that the generic CNN model outperformed the subject-specific neuron-decomposition method and the EMG-amplitude method, as demonstrated by a higher correlation coefficient between the measured and predicted forces, and a lower force prediction error. In addition, the CNN model revealed more stable force prediction performance over time.ConclusionsOverall, our approach provides a generic and efficient continuous neural decoding approach for real-time and robust human-robot interactions.