Mitigating the Concurrent Interference of Electrode Shift and Loosening in Myoelectric Pattern Recognition Using Siamese Autoencoder Network

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 32; pp. 3388 - 3398
• Main Authors: Gao, Ge, Zhang, Xu, Chen, Xiang, Chen, Zhang
• Format: Journal Article
• Language: English
• Published: United States IEEE 2024
• Subjects: Adult; Algorithms; Data collection; electrode loosening; electrode shift; Electrodes; Electromyography; Electromyography - methods; Feature extraction; Female; Gestures; Humans; Interference; Male; Myoelectric pattern recognition; Neural Networks, Computer; Pattern Recognition, Automated - methods; Reproducibility of Results; Robustness; Siamese autoencoder network; Support Vector Machine; surface electromyography; Testing; Young Adult

The objective of this work is to develop a novel myoelectric pattern recognition (MPR) method to mitigate the concurrent interference of electrode shift and loosening, thereby improving the practicality of MPR-based gestural interfaces towards intelligent control. A Siamese auto-encoder network (SAE...