FPGA-based acceleration of high density myoelectric signal processing

In recent years, advances in electromyographic (EMG) sensor technology and machine learning algorithms have led to an increased research effort into high density EMG based pattern recognition methods for prosthesis control. With the goal set on an autonomous multi-movement prosthesis that is capable of performing training and classification of an amputee's EMG signals, the focus of this paper lies in the acceleration of the embedded signal processing chain. Using the Xilinx Zynq as a low-cost off-the-shelf reconfigurable processing platform, we present a solution that is able to compute prosthesis control signals from multi-channel EMG input with up to 256 channels with a maximum processing delay of less than a single millisecond. While the presented system is able to perform training as well as classification, most of our efforts were focused on the acceleration of the feature extraction units, achieving a speed-up of 6.7 for feature extraction alone, and 4.8 for the total processing time as compared to a software only solution.

[1]  K. Englehart,et al.  Resolving the Limb Position Effect in Myoelectric Pattern Recognition , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[2]  Marco Platzner,et al.  ReconOS: An Operating System Approach for Reconfigurable Computing , 2014, IEEE Micro.

[3]  Weijun Xiao,et al.  Promise of embedded system with GPU in artificial leg control: Enabling time-frequency feature extraction from electromyography , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Levi J. Hargrove,et al.  A Comparison of Surface and Intramuscular Myoelectric Signal Classification , 2007, IEEE Transactions on Biomedical Engineering.

[5]  D. Atkins,et al.  Epidemiologic Overview of Individuals with Upper-Limb Loss and Their Reported Research Priorities , 1996 .

[6]  Erik Scheme,et al.  Electromyogram pattern recognition for control of powered upper-limb prostheses: state of the art and challenges for clinical use. , 2011, Journal of rehabilitation research and development.

[7]  Péter Szolgay,et al.  Analysis of myoelectric signals using a Field Programmable SoC , 2013, 2013 European Conference on Circuit Theory and Design (ECCTD).

[8]  D. Farina,et al.  Spatial Correlation of High Density EMG Signals Provides Features Robust to Electrode Number and Shift in Pattern Recognition for Myocontrol , 2015, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  A. Boschmann,et al.  Reducing the limb position effect in pattern recognition based myoelectric control using a high density electrode array , 2013, 2013 ISSNIP Biosignals and Biorobotics Conference: Biosignals and Robotics for Better and Safer Living (BRC).

[10]  Blair A. Lock,et al.  Determining the Optimal Window Length for Pattern Recognition-Based Myoelectric Control: Balancing the Competing Effects of Classification Error and Controller Delay , 2011, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[11]  Kevin B. Englehart,et al.  A robust, real-time control scheme for multifunction myoelectric control , 2003, IEEE Transactions on Biomedical Engineering.

[12]  Joseph R. Cavallaro,et al.  FPGA Implementation of Matrix Inversion Using QRD-RLS Algorithm , 2005, Conference Record of the Thirty-Ninth Asilomar Conference onSignals, Systems and Computers, 2005..

[13]  Todd A Kuiken,et al.  Target Achievement Control Test: evaluating real-time myoelectric pattern-recognition control of multifunctional upper-limb prostheses. , 2011, Journal of rehabilitation research and development.

[14]  Richard F. Weir,et al.  ANALYSIS WINDOW INDUCED CONTROLLER DELAY FOR MULTIFUNCTIONAL PROSTHESES , 2008 .

[15]  D Graupe,et al.  Stochastic analysis of myoelectric temporal signatures for multifunctional single-site activation of prostheses and orthoses. , 1985, Journal of biomedical engineering.

[16]  Todd A. Kuiken,et al.  The Effects of Electrode Size and Orientation on the Sensitivity of Myoelectric Pattern Recognition Systems to Electrode Shift , 2011, IEEE Transactions on Biomedical Engineering.

[17]  Marco Platzner,et al.  Towards robust HD EMG pattern recognition: Reducing electrode displacement effect using structural similarity , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  John M. Miguelez,et al.  Evolution of microprocessor based control systems in upper extremity prosthetics , 2003 .

[19]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[20]  Max Ortiz-Catalan,et al.  BioPatRec: A modular research platform for the control of artificial limbs based on pattern recognition algorithms , 2013, Source Code for Biology and Medicine.

[21]  R. N. Scott,et al.  A three-state myo-electric control , 1966, Medical and biological engineering.

[22]  R.N. Scott,et al.  A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[23]  Ruben H. Zamar,et al.  Parallel Computation of High-Dimensional Robust Correlation and Covariance Matrices , 2006, Algorithmica.