Improving the Robustness of Myoelectric Pattern Recognition for Upper Limb Prostheses by Covariate Shift Adaptation

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 24; no. 9; pp. 961 - 970
• Main Authors: Vidovic, Marina M.-C., Hwang, Han-Jeong, Amsuss, Sebastian, Hahne, Janne M., Farina, Dario, Muller, Klaus-Robert
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.09.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Adaptation; Adult; Algorithms; Amputation; Amputation Stumps - physiopathology; Amputees - rehabilitation; Artificial Limbs; Calibration; classification; covariate shift; Data Interpretation, Statistical; Electrodes; electromyogram (EMG); Electromyography; Electromyography - methods; Humans; Male; Middle Aged; Muscle Contraction - physiology; Muscle, Skeletal - physiology; myoelectric signals; nonstationarities; pattern recognition; Pattern Recognition, Automated - methods; Radius - surgery; Reproducibility of Results; Sensitivity and Specificity; Testing; Training; Training data; Young Adult
• ISSN: 1534-4320; 1558-0210
• DOI: 10.1109/TNSRE.2015.2492619

Fundamental changes over time of surface EMG signal characteristics are a challenge for myocontrol algorithms controlling prosthetic devices. These changes are generally caused by electrode shifts after donning and doffing, sweating, additional weight or varying arm positions, which results in a cha...