Directional Forgetting for Stable Co-Adaptation in Myoelectric Control

Published on May 13, 2019in Sensors3.03
· DOI :10.3390/s19092203
Dennis Yeung , Dario Farina70
Estimated H-index: 70
+ 0 AuthorsIvan Vujaklija
Conventional myoelectric controllers provide a mapping between electromyographic signals and prosthetic functions. However, due to a number of instabilities continuously challenging this process, an initial mapping may require an extended calibration phase with long periods of user-training in order to ensure satisfactory performance. Recently, studies on co-adaptation have highlighted the benefits of concurrent user learning and machine adaptation where systems can cope with deficiencies in the initial model by learning from newly acquired data. However, the success remains highly dependent on careful weighting of these new data. In this study, we proposed a function driven directional forgetting approach to the recursive least-squares algorithm as opposed to the classic exponential forgetting scheme. By only discounting past information in the same direction of the new data, local corrections to the mapping would induce less distortion to other regions. To validate the approach, subjects performed a set of real-time myoelectric tasks over a range of forgetting factors. Results show that directional forgetting with a forgetting factor of 0.995 outperformed exponential forgetting as well as unassisted user learning. Moreover, myoelectric control remained stable after adaptation with directional forgetting over a range of forgetting factors. These results indicate that a directional approach to discounting past training data can improve performance and alleviate sensitivities to parameter selection in recursive adaptation algorithms.
  • References (38)
  • Citations (0)
#1Ivan Vujaklija (Imperial College London)H-Index: 9
#2Vahid Shalchyan (IUST: Iran University of Science and Technology)H-Index: 3
Last.Dario Farina (Imperial College London)H-Index: 70
view all 6 authors...
#1Janne M. Hahne (GAU: University of Göttingen)H-Index: 7
#2Meike A. Schweisfurth (Hamburg University of Applied Sciences)H-Index: 5
Last.Dario Farina (Imperial College London)H-Index: 70
view all 4 authors...
#1Xiangyang Zhu (SJTU: Shanghai Jiao Tong University)H-Index: 21
#2Jianwei Liu (SJTU: Shanghai Jiao Tong University)H-Index: 5
Last.Ning Jiang (UW: University of Waterloo)H-Index: 27
view all 5 authors...
Oct 1, 2016 in SMC (Systems, Man and Cybernetics)
#1Wenjuan Zhang (NCSU: North Carolina State University)H-Index: 2
#2Melissa Mae White (NCSU: North Carolina State University)H-Index: 2
Last.David B. Kaber (NCSU: North Carolina State University)H-Index: 29
view all 7 authors...
#1Ivan Vujaklija (GAU: University of Göttingen)H-Index: 9
#2Dario FarinaH-Index: 70
Last.Oskar C. Aszmann (Medical University of Vienna)H-Index: 24
view all 3 authors...
Cited By0
View next paperA theory for the risk bound of myoelectric control with adaptive learning