Optimal strategy of sEMG feature and measurement position for grasp force estimation

Grasp force estimation based on surface electromyography (sEMG) is essential for the dexterous control of a prosthetic hand. Nowadays, although increasing the number of sEMG measurement positions and extracting more features are common methods to increase the accuracy of grasp force estimation, it will increase the computational burden. In this paper, an approach based on analysis of variance (ANOVA) and generalized regression neural network (GRNN) for optimal measurement positions and features is proposed, with the purpose of using fewer measurement positions or features to achieve higher estimation accuracy. Firstly, we captured six channels of sEMG from subjects’ forearm and grasp force synchronously. Then, four kinds of features in time domain are extracted from each channel of sEMG. By combining different measurement position sets (MPSs) and feature set (FSs), we construct 945 data sets. These data sets are fed to GRNN to realize grasp force estimation. Normalized root mean square error (NRMS), normalized mean of absolute error (NMAE), and correlation coefficient (CC) between estimated grasp force and actual force are introduced to evaluate the performance of grasp force estimation. Finally, ANOVA and Tukey HSD testing are introduced to analyze grasp force estimation results so as to obtain the optimal measurement positions and features. We obtain the optimal MPSs for grasp force estimation when different FSs are employed, and the optimal FSs when different MPSs are utilized.

[1]  Gongfa Li,et al.  Grasping force prediction based on sEMG signals , 2020 .

[2]  Christian Cipriani,et al.  Grasp force estimation from the transient EMG using high-density surface recordings , 2020, Journal of neural engineering.

[3]  Xu Zhang,et al.  Elbow-flexion force estimation during arm posture dynamically changing between pronation and supination , 2019, Journal of neural engineering.

[4]  Paolo Bifulco,et al.  Real-Time EMG Based Pattern Recognition Control for Hand Prostheses: A Review on Existing Methods, Challenges and Future Implementation , 2019, Sensors.

[5]  M. Rehman.  Design and development of sEMG Prosthetics for recovering amputation of the human hand , 2019, Pure and Applied Biology.

[6]  Seungyeon Kim,et al.  Grasping Force Estimation by sEMG Signals and Arm Posture: Tensor Decomposition Approach , 2019, Journal of Bionic Engineering.

[7]  Xun Chen,et al.  Feasibility Study of Advanced Neural Networks Applied to sEMG-Based Force Estimation , 2018, Sensors.

[8]  Xun Chen,et al.  HD-sEMG-based research on activation heterogeneity of skeletal muscles and the joint force estimation during elbow flexion , 2018, Journal of neural engineering.

[9]  Yuki Ban,et al.  Estimating the Direction of Force Applied to the Grasped Object Using the Surface EMG , 2018, EuroHaptics.

[10]  Sean R. Anderson,et al.  Simultaneous Force Regression and Movement Classification of Fingers via Surface EMG within a Unified Bayesian Framework , 2018, Front. Bioeng. Biotechnol..

[11]  Hiroshi Yokoi,et al.  Development of myoelectric hand that determines hand posture and estimates grip force simultaneously , 2017, Biomed. Signal Process. Control..

[12]  Aiguo Song,et al.  Grip Force and 3D Push-Pull Force Estimation Based on sEMG and GRNN , 2017, Front. Neurosci..

[13]  B. Qiu,et al.  An isometric muscle force estimation framework based on a high-density surface EMG array and an NMF algorithm , 2017, Journal of neural engineering.

[14]  Bingke Zhang,et al.  Pattern-based grasping force estimation from surface electromyography , 2017, 2017 International Conference on Algorithms, Methodology, Models and Applications in Emerging Technologies (ICAMMAET).

[15]  Jianping Wang,et al.  Surface EMG based handgrip force predictions using gene expression programming , 2016, Neurocomputing.

[16]  Aiguo Song,et al.  A Control Strategy with Tactile Perception Feedback for EMG Prosthetic Hand , 2015, J. Sensors.

[17]  Winnie Jensen,et al.  Simultaneous and Proportional Force Estimation in Multiple Degrees of Freedom From Intramuscular EMG , 2012, IEEE Transactions on Biomedical Engineering.

[18]  Hong Liu,et al.  EMG pattern recognition and grasping force estimation: Improvement to the myocontrol of multi-DOF prosthetic hands , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Hong Liu,et al.  Estimation of hand grasp force based on forearm surface EMG , 2009, 2009 International Conference on Mechatronics and Automation.

[20]  Bruce C. Wheeler,et al.  EMG feature evaluation for movement control of upper extremity prostheses , 1995 .

[21]  Wei Chen,et al.  Cross-Comparison of EMG-to-Force Methods for Multi-DoF Finger Force Prediction Using One-DoF Training , 2020, IEEE Access.

[22]  Kejun Zhang,et al.  Modified EMG-based handgrip force prediction using extreme learning machine , 2017, Soft Comput..

[23]  Masao Yanagisawa,et al.  An Evaluation of Hand-Force Prediction Using Artificial Neural-Network Regression Models of Surface EMG Signals for Handwear Devices , 2017, J. Sensors.

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