The corresponding relationship research between human lower limb operation mode and muscle information

Surface EMG (sEMG) with correlation exists between the active and functional status of the muscle can be a very good reaction to neuromuscular activity. Studies concerning this has important significance to the development of research on rehabilitation robot. This paper aims to study the action pattern recognition technology. We can obtain the characteristic value of lower limb EMG signal and pattern recognition with the time and the level of excitement with the muscles corresponding to the lower extremity operation mode. The first step to deal with the collected muscles sEMG is to conduct a denoising pretreatment, and then use the Power spectral ratio method to obtain a characteristic value of each muscle. Finally, make a BP neural network to the obtained features so that we can identify corresponding relationship between the sEMG and the lower extremity operation mode. It was found that the excitement of the time and the level of excitement are different for each muscle sEMG. sEMG have similar activity in the same mode, and a clear distinction in the different operating modes. In a different operation mode, conduct a pattern recognition to the characteristic value of the surface EMG, and the operating mode thereof can be discriminated.

[1]  Adrian D. C. Chan,et al.  Myoelectric Control Development Toolbox , 2007 .

[2]  Toshio Tsuji,et al.  Pattern classification of time-series EMG signals using neural networks , 2000 .

[3]  A. Willsky,et al.  Upper Extremity Limb Function Discrimination Using EMG Signal Analysis , 1983, IEEE Transactions on Biomedical Engineering.

[4]  K Kunze,et al.  Discriminant classification of motor unit potentials (MUPs) successfully separates neurogenic and myopathic conditions. A comparison of multi- and univariate diagnostical algorithms for MUP analysis. , 1995, Electroencephalography and clinical neurophysiology.

[5]  Blake Hannaford,et al.  Hill-Based Model as a Myoprocessor for a Neural Controlled Powered Exoskeleton Arm - Parameters Optimization , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[6]  David G Lloyd,et al.  Neuromusculoskeletal modeling: estimation of muscle forces and joint moments and movements from measurements of neural command. , 2004, Journal of applied biomechanics.

[7]  Adrian D. C. Chan,et al.  Continuous myoelectric control for powered prostheses using hidden Markov models , 2005, IEEE Transactions on Biomedical Engineering.

[8]  Lin Wang,et al.  Prediction of joint moments using a neural network model of muscle activations from EMG signals , 2002, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  Anders Fuglsang-Frederiksen,et al.  Power spectrum analysis of the EMG pattern in normal and diseased muscles , 1989, Journal of the Neurological Sciences.

[10]  Toshio Tsuji,et al.  A Hybrid Motion Classification Approach for EMG-Based Human–Robot Interfaces Using Bayesian and Neural Networks , 2009, IEEE Transactions on Robotics.