Self-Correcting Pattern Recognition System of Surface EMG Signals for Upper Limb Prosthesis Control

被引:149
作者
Amsuess, Sebastian [1 ]
Goebel, Peter M. [2 ]
Jiang, Ning [1 ]
Graimann, Bernhard [3 ]
Paredes, Liliana [4 ]
Farina, Dario [1 ]
机构
[1] Univ Gottingen, Dept Neurorehabil Engn, D-37073 Gottingen, Germany
[2] Otto Bock Healthcare Prod GmbH, A-1060 Vienna, Austria
[3] Otto Bock Healthcare GmbH, D-37115 Duderstadt, Germany
[4] Fdn Osped San Camillo, Lab Robot & Cinemat, I-30126 Venice, Italy
关键词
Artificial neural networks (ANNs); myoelectric control; pattern recognition (PR); robustness; upper limb prostheses; REAL-TIME CONTROL; OF-THE-ART; ROBUST;
D O I
10.1109/TBME.2013.2296274
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Pattern recognition methods for classifying user motion intent based on surface electromyography developed by research groups in well-controlled laboratory conditions are not yet clinically viable for upper limb prosthesis control, due to their limited robustness in users' real-life situations. To address this problem, a novel postprocessing algorithm, aiming to detect and remove misclassifications of a pattern recognition system of fore-arm and hand motions, is proposed. Using the maximum likelihood calculated by a classifier and the mean global muscle activity of the forearm, an artificial neural network was trained to detect potentially erroneous classification decisions. This system was compared to four previously proposed classification postprocessing methods, in both able-bodied and amputee subjects. Various nonstationarities were included in the experimental protocol to account for challenges posed in real-life settings, such as different contraction levels, static and dynamic motion phases, and effects induced by day-to-day transfers, such as electrode shifts, impedance changes, and psychometric user variability. The improvement in classification accuracy with respect to the unprocessed classifier ranged from 4.8% to 31.6%, depending on the scenarios investigated. The system significantly reduced misclassifications to wrong active classes and is thus a promising approach for improving the robustness of hand prosthesis controllability.
引用
收藏
页码:1167 / 1176
页数:10
相关论文
共 37 条
  • [1] Amsüss S, 2013, IEEE ENG MED BIO, P3622, DOI 10.1109/EMBC.2013.6610327
  • [2] Baikun Wan, 2010, 2010 IEEE International Conference on Robotics and Biomimetics (ROBIO), P1229, DOI 10.1109/ROBIO.2010.5723504
  • [3] Estimating contraction level using root mean square amplitude in control subjects and patients with neuromuscular disorders
    Boe, Shaun G.
    Rice, Charles L.
    Doherty, Timothy J.
    [J]. ARCHIVES OF PHYSICAL MEDICINE AND REHABILITATION, 2008, 89 (04): : 711 - 718
  • [4] Application of a self-enhancing classification method to electromyography pattern recognition for multifunctional prosthesis control
    Chen, Xinpu
    Zhang, Dingguo
    Zhu, Xiangyang
    [J]. JOURNAL OF NEUROENGINEERING AND REHABILITATION, 2013, 10
  • [5] Chicoine CL, 2012, IEEE ENG MED BIO, P1876, DOI 10.1109/EMBC.2012.6346318
  • [6] A robust, real-time control scheme for multifunction myoelectric control
    Englehart, K
    Hudgins, B
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2003, 50 (07) : 848 - 854
  • [7] The extraction of neural strategies from the surface EMG
    Farina, D
    Merletti, R
    Enoka, RM
    [J]. JOURNAL OF APPLIED PHYSIOLOGY, 2004, 96 (04) : 1486 - 1495
  • [8] The optimal controller delay for myoelectric prostheses
    Farrell, Todd R.
    Weir, Richard F.
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2007, 15 (01) : 111 - 118
  • [9] Control of Upper Limb Prostheses: Terminology and Proportional Myoelectric Control-A Review
    Fougner, Anders
    Stavdahl, Oyvind
    Kyberd, Peter J.
    Losier, Yves G.
    Parker, Philip A.
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2012, 20 (05) : 663 - 677
  • [10] Fukunaga K., 1990, INTRO STAT PATTERN R, P579