Robust EMG pattern recognition in the presence of confounding factors: features, classifiers and adaptive learning

作者：

Highlights：

• Multiple compounding factors are considered during the data-collection.

• Donning and doffing the electrodes on different arms is firstly tested.

• A variety of features and classifiers are examined to increase the robustness.

• New adaptive learning method effectively maintains the classification accuracy.

摘要

•Multiple compounding factors are considered during the data-collection.•Donning and doffing the electrodes on different arms is firstly tested.•A variety of features and classifiers are examined to increase the robustness.•New adaptive learning method effectively maintains the classification accuracy.

论文关键词：Myoelectric signal,Feature extraction,Pattern recognition,Confounding factor,Hand prosthesis

论文评审过程：Received 20 July 2017, Revised 17 November 2017, Accepted 24 November 2017, Available online 28 November 2017, Version of Record 22 December 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.11.049