EMG pattern recognition via Bayesian inference with scale mixture-based stochastic generative models
作者：
Highlights：
• We proposed an EMG pattern classification method based on a stochastic EMG model.
• The proposed model is trained by variational Bayesian learning.
• The hyperparameter can be determined by mutual information maximization.
• Simulations, EMG analysis, and classification experiments were conducted.
• The proposed method outperformed general generative/discriminative classifiers.
摘要
•We proposed an EMG pattern classification method based on a stochastic EMG model.•The proposed model is trained by variational Bayesian learning.•The hyperparameter can be determined by mutual information maximization.•Simulations, EMG analysis, and classification experiments were conducted.•The proposed method outperformed general generative/discriminative classifiers.
论文关键词：Electromyogram (EMG),Pattern recognition,Motion classification,Scale mixture model,Bayesian inference
论文评审过程：Received 1 December 2020, Revised 9 June 2021, Accepted 19 July 2021, Available online 30 July 2021, Version of Record 4 August 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115644
