Linear and Nonlinear Regression Techniques for Simultaneous and Proportional Myoelectric Control

Published on Mar 1, 2014in IEEE Transactions on Neural Systems and Rehabilitation Engineering3.48
· DOI :10.1109/TNSRE.2014.2305520
Janne M. Hahne7
Estimated H-index: 7
F. Biebmann1
Estimated H-index: 1
+ 5 AuthorsLucas C. Parra46
Estimated H-index: 46
(CCNY: City College of New York)
In recent years the number of active controllable joints in electrically powered hand-prostheses has increased significantly. However, the control strategies for these devices in current clinical use are inadequate as they require separate and sequential control of each degree-of-freedom (DoF). In this study we systematically compare linear and nonlinear regression techniques for an independent, simultaneous and proportional myoelectric control of wrist movements with two DoF. These techniques include linear regression, mixture of linear experts (ME), multilayer-perceptron, and kernel ridge regression (KRR). They are investigated offline with electro-myographic signals acquired from ten able-bodied subjects and one person with congenital upper limb deficiency. The control accuracy is reported as a function of the number of electrodes and the amount and diversity of training data providing guidance for the requirements in clinical practice. The results showed that KRR, a nonparametric statistical learning method, outperformed the other methods. However, simple transformations in the feature space could linearize the problem, so that linear models could achieve similar performance as KRR at much lower computational costs. Especially ME, a physiologically inspired extension of linear regression represents a promising candidate for the next generation of prosthetic devices.
  • References (35)
  • Citations (99)
#1Aaron J. Young (Rehabilitation Institute of Chicago)H-Index: 19
#2Lauren H. Smith (NU: Northwestern University)H-Index: 11
Last.Levi J. Hargrove (NU: Northwestern University)H-Index: 29
view all 4 authors...
#1Ning Jiang (GAU: University of Göttingen)H-Index: 27
#2Silvia Muceli (GAU: University of Göttingen)H-Index: 18
Last.Dario Farina (GAU: University of Göttingen)H-Index: 70
view all 4 authors...
#1Janne M. HahneH-Index: 7
#2Hubertus Rehbaum (GAU: University of Göttingen)H-Index: 8
Last.Lucas C. Parra (CCNY: City College of New York)H-Index: 46
view all 8 authors...
Cited By99
#1Shunta Togo (University of Electro-Communications)H-Index: 3
#2Yuta Murai (University of Electro-Communications)
Last.Yokoi Hiroshi (University of Electro-Communications)H-Index: 20
view all 0 authors...
#1Wing-Kin Tam (UMN: University of Minnesota)H-Index: 5
#2Tong Wu (UMN: University of Minnesota)H-Index: 5
Last.Zhi Yang (UMN: University of Minnesota)H-Index: 15
view all 5 authors...
#1Kexiang Li (HEBUT: Hebei University of Technology)
#2Jianhua Zhang (CAS: Chinese Academy of Sciences)
Last.Zhang Minglu (HEBUT: Hebei University of Technology)H-Index: 7
view all 4 authors...
#1Sorawit Stapornchaisit (TITech: Tokyo Institute of Technology)
#2YeongDae Kim (TITech: Tokyo Institute of Technology)
Last.Yasuharu Koike (TITech: Tokyo Institute of Technology)H-Index: 20
view all 5 authors...
#1Neil Y. Yen (University of Aizu)H-Index: 11
#2Jia-Wei Chang (National Taichung University of Science and Technology)
Last.You-Ming Yong (NCHU: National Chung Hsing University)
view all 4 authors...
#1Agamemnon Krasoulis (Edin.: University of Edinburgh)H-Index: 4
#2Sethu Vijayakumar (Edin.: University of Edinburgh)H-Index: 33
Last.Kianoush Nazarpour (Newcastle University)H-Index: 16
view all 0 authors...
#1R. Fazai (Texas A&M University at Qatar)
#2K. Abodayeh (Prince Sultan University)
Last.George E. Georghiou (UCY: University of Cyprus)H-Index: 22
view all 7 authors...
#1Agamemnon Krasoulis (Newcastle University)H-Index: 4
#2Sethu Vijayakumar (Edin.: University of Edinburgh)H-Index: 33
Last.Kianoush Nazarpour (Newcastle University)H-Index: 16
view all 3 authors...
View next paperExtracting Simultaneous and Proportional Neural Control Information for Multiple-DOF Prostheses From the Surface Electromyographic Signal