EMG Pattern Recognition via Bayesian Inference with Scale Mixture-Based Stochastic Generative Models
EMG Pattern Recognition via Bayesian Inference with Scale Mixture-Based Stochastic Generative Models
复制标题
DOI：
10.1016/j.eswa.2021.115644
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
A. Furui;Takuya Igaue;T. Tsuji
中科院分区：
文献类型：
--
作者：
A. Furui;Takuya Igaue;T. Tsuji
肌电(EMG)由于能够反映人体的运动意图，已被用于假手和信息设备的接口信号。虽然各种肌电分类方法已经被引入到基于肌电的控制系统中，但它们都没有充分考虑肌电信号的随机特性。提出了一种结合尺度混合生成模型的肌电模式分类方法。比例混合模型是一种随机肌电模型，其中肌电的方差被视为随机变量，使得方差中的不确定性得以表示。本研究对该模型进行了扩展，并将其用于肌电模式分类。该方法通过变分贝叶斯学习进行训练，从而实现了模型复杂性的自动确定。此外，为了用部分判别方法优化该方法的超参数，引入了基于互信息的确定方法。仿真和肌电分析实验证明了该方法的超参数与分类精度之间的关系，以及该方法的有效性。使用公开的肌电数据集进行的比较表明，该方法的性能优于各种传统的分类器。这些结果表明了该方法的有效性及其在肌电控制系统中的适用性。在肌电模式识别中，基于反映肌电信号随机特性的产生式模型的分类器性能优于传统的通用分类器。
Electromyogram (EMG) has been utilized to interface signals for prosthetic hands and information devices owing to its ability to reflect human motion intentions. Although various EMG classification methods have been introduced into EMG-based control systems, they do not fully consider the stochastic characteristics of EMG signals. This paper proposes an EMG pattern classification method incorporating a scale mixture-based generative model. A scale mixture model is a stochastic EMG model in which the EMG variance is considered as a random variable, enabling the representation of uncertainty in the variance. This model is extended in this study and utilized for EMG pattern classification. The proposed method is trained by variational Bayesian learning, thereby allowing the automatic determination of the model complexity. Furthermore, to optimize the hyperparameters of the proposed method with a partial discriminative approach, a mutual information-based determination method is introduced. Simulation and EMG analysis experiments demonstrated the relationship between the hyperparameters and classification accuracy of the proposed method as well as the validity of the proposed method. The comparison using public EMG datasets revealed that the proposed method outperformed the various conventional classifiers. These results indicated the validity of the proposed method and its applicability to EMG-based control systems. In EMG pattern recognition, a classifier based on a generative model that reflects the stochastic characteristics of EMG signals can outperform the conventional general-purpose classifier.