Classification of human hand movements based on EMG signals using nonlinear dimensionality reduction and data fusion techniques
作者：
Highlights：
• STFT can be used as a single informative feature for movement identification.
• Large training data reveals high classification rates for single subject setting.
• Diffusion Maps outperformed PCA in case of limited training data.
• The alignment algorithm enables robust classification of a new subject's data.
• The proposed alignment algorithm can be adopted for many EMG classification tasks.
摘要
•STFT can be used as a single informative feature for movement identification.•Large training data reveals high classification rates for single subject setting.•Diffusion Maps outperformed PCA in case of limited training data.•The alignment algorithm enables robust classification of a new subject's data.•The proposed alignment algorithm can be adopted for many EMG classification tasks.
论文关键词：Electromyography,Machine learning,Principal component analysis,Diffusion maps,Data fusion,Graph alignment
论文评审过程：Received 6 April 2019, Revised 23 December 2019, Accepted 4 February 2020, Available online 5 February 2020, Version of Record 15 February 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113281
