EMG Pattern Recognition and Grasping Force Estimation: Improvement to the Myocontrol of Multi-DOF Prosthetic Hands

被引:40
作者
Yang, Dapeng [1 ]
Zhao, Jingdong [1 ]
Gu, Yikun [1 ]
Jiang, Li [1 ]
Liu, Hong [1 ]
机构
[1] Harbin Inst Technol, State Key Lab Robot & Syst, Harbin 150006, Heilongjiang, Peoples R China
来源
2009 IEEE-RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS | 2009年
关键词
CLASSIFICATION SCHEME;
D O I
10.1109/IROS.2009.5354544
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The multi-DOF prosthetic hand's myocontrol needs to recognize more hand gestures (or motions) based on myoelectric signals. This paper presents a classification method, which is based on the support vector machine (SVM), to classify 19 different hand gesture modes through electromyographic (EMG) signals acquired from six surface myoelectric electrodes. All hand gestures are based on a 3-DOF configuration, which makes the hand perform like three-fingered. The training performance is very high within each test session, but the cross-session validation is typically low. Acceptable cross-session performance can be achieved by training with more sessions or fewer gesture modes. A fast rhythm muscle contraction is suggested, which can make the training samples more resourceful and improve the prediction accuracy comparing with a relative slow muscle contraction method. For many precise grasp tasks, it is beneficial to the prosthetic hand's myocontrol if we can efficiently extract the grasp force directly from EMG signals. Through grasping a JR3 6 dimension force/torque sensor, the force signal applying to the sensor can be recorded synchronously with myoelectric signals. This paper uses three methods, local weighted projection regression (LWPR), artificial neural network (ANN) and SVM, to find the best regression relationship between these two kinds of signals. It reveals that the SVM method is better than ANN and LWPR, especially in the case of cross-session validation. Also, the performance of grasping force estimation based on specific hand gestures is superior to the performance of grasping with random fingers.
引用
收藏
页码:516 / 521
页数:6
相关论文
共 19 条
  • [1] [Anonymous], OTTOBOCK SENSORHAND
  • [2] Biagiotti L, 2003, IEEE INT CONF ROBOT, P3187
  • [3] Learning EMG control of a robotic hand: Towards active prostheses
    Bitzer, Sebastian
    van der Smagt, Patrick
    [J]. 2006 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), VOLS 1-10, 2006, : 2819 - +
  • [4] Boser B. E., 1992, Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory, P144, DOI 10.1145/130385.130401
  • [5] Carrozza MC, 2003, IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, P2642
  • [6] The development of a novel prosthetic hand - Ongoing research and preliminary results
    Carrozza, MC
    Massa, B
    Micera, S
    Lazzarini, R
    Zecca, M
    Dario, P
    [J]. IEEE-ASME TRANSACTIONS ON MECHATRONICS, 2002, 7 (02) : 108 - 114
  • [7] Surface EMG in advanced hand prosthetics
    Castellini, Claudio
    van der Smagt, Patrick
    [J]. BIOLOGICAL CYBERNETICS, 2009, 100 (01) : 35 - 47
  • [8] 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
  • [9] A wavelet-based continuous classification scheme for multifunction myoelectric control
    Englehart, K
    Hudgins, B
    Parker, PA
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2001, 48 (03) : 302 - 311
  • [10] TRAINING FEEDFORWARD NETWORKS WITH THE MARQUARDT ALGORITHM
    HAGAN, MT
    MENHAJ, MB
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 1994, 5 (06): : 989 - 993