Prediction of joint angle by combining multiple linear regression with autoregressive (AR) model and Kalman filter

In this paper, a new prediction algorithm combining multiple linear regression with autoregressive model and Kalman filter (MLRAR-KF) is proposed to predict the elbow joint angle. The MLRAR model updating weights with Kalman filter is shown to be able to predict joint motion with high accuracy and well robustness. In comparison to existing prediction algorithms, MLRAR-KF can predict joint angle with higher accuracy and better robustness. A data acquisition system was used to collect sEMG and elbow joint angle signals of human upper limb. The experimental results demonstrate the benefits of MLRAR-KF prediction algorithm. Comparison of computational complexity about some existing prediction methods and MLRAR-KF is conducted to analyze the real-time performance.

[1]  Silvia Conforto,et al.  An optimized method for tremor detection and temporal tracking through repeated second order moment calculations on the surface EMG signal. , 2012, Medical engineering & physics.

[2]  Hong-Bo Xie,et al.  Estimation of wrist angle from sonomyography using support vector machine and artificial neural network models. , 2009, Medical engineering & physics.

[3]  S. Y. Chen,et al.  Kalman Filter for Robot Vision: A Survey , 2012, IEEE Transactions on Industrial Electronics.

[4]  Lida Xu,et al.  EMG and EPP-Integrated Human–Machine Interface Between the Paralyzed and Rehabilitation Exoskeleton , 2012, IEEE Transactions on Information Technology in Biomedicine.

[5]  Taha B. M. J. Ouarda,et al.  Recursion‐based multiple changepoint detection in multiple linear regression and application to river streamflows , 2007 .

[6]  Gian Domenico Iannetti,et al.  Multiple linear regression to estimate time-frequency electrophysiological responses in single trials , 2015, NeuroImage.

[7]  Robert Tibold,et al.  Prediction of muscle activity during loaded movements of the upper limb , 2014, Journal of NeuroEngineering and Rehabilitation.

[8]  Wei Tech Ang,et al.  Multistep Prediction of Physiological Tremor Based on Machine Learning for Robotics Assisted Microsurgery , 2015, IEEE Transactions on Cybernetics.

[9]  W. D. Hohenboken,et al.  Alternatives to least squares in multiple linear regression to predict production traits , 1995 .

[10]  Wei Tech Ang,et al.  Multistep Prediction of Physiological Tremor for Surgical Robotics Applications , 2013, IEEE Transactions on Biomedical Engineering.

[11]  Daniel J. Bauer,et al.  Computational Tools for Probing Interactions in Multiple Linear Regression, Multilevel Modeling, and Latent Curve Analysis , 2006 .

[12]  Kejun Zhang,et al.  An Upper-Limb Power-Assist Exoskeleton Using Proportional Myoelectric Control , 2014, Sensors.

[13]  Robert Riener,et al.  Control strategies for active lower extremity prosthetics and orthotics: a review , 2015, Journal of NeuroEngineering and Rehabilitation.

[14]  Win Tun Latt,et al.  Physiological Tremor Estimation With Autoregressive (AR) Model and Kalman Filter for Robotics Applications , 2013, IEEE Sensors Journal.

[15]  Jie Zhao,et al.  Prediction of sEMG-based tremor joint angle using the RBF neural network , 2012, 2012 IEEE International Conference on Mechatronics and Automation.

[16]  Y. Lian,et al.  A Multiple Linear Regression Model for Estimating Global Solar Radiation in Guangzhou, China , 2013 .

[17]  Eiji Inoue,et al.  Evaluation of a multiple linear regression model for the prediction of panicle number in rice , 2012 .