Name
Title | ||
|---|---|---|
Knee Joint Angle Prediction Based on Muscle Synergy Theory and Generalized Regression Neural Network |
Abstract | ||
|---|---|---|
Continuous joint motion estimation plays an important part in accomplishing more compliant and safer human-machine interaction (HMI). Surface electromyogram (sEMG) signals, which contain abundant motion information, can be used as a source for continuous joint motion estimation. In this paper, a knee joint angle prediction system based on muscle synergy theory and generalized regression neural network (GRNN) was proposed. The wavelet transform threshold method was used for sEMG signals and angle trajectories denoising. The time-domain features wave-length extracted from four-channel sEMG signals were decomposed into a synergy matrix and an activation coefficient matrix by using nonnegative matrix factorization based on muscle synergy theory. A GRNN based on golden-section search was employed to build the activation model mapping from the activation coefficients to the knee joint angles, so as to realize the continuous knee joint angle estimation. The experimental results show that the average coefficient of determination is 0.933. In addition, a user graphic interface based on the Java platform was designed to display the dynamic sEMG data and predicted knee joint angles in real time. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/AIM.2018.8452230 | 2018 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM) |
Keywords | Field | DocType |
muscle synergy theory,generalized regression neural network,time-domain features wave-length,four-channel sEMG signals,synergy matrix,activation coefficient matrix,nonnegative matrix factorization,continuous knee joint angle estimation,continuous joint motion estimation,human-machine interaction,surface electromyogram signals,knee joint angle prediction system,wavelet transform threshold method,Java platform | Coefficient matrix,Pattern recognition,Matrix (mathematics),Computer science,Control theory,Matrix decomposition,Non-negative matrix factorization,Knee Joint,Artificial intelligence,Motion estimation,Artificial neural network,Wavelet transform | Conference |
ISSN | ISBN | Citations |
2159-6255 | 978-1-5386-1855-4 | 0 |
PageRank | References | Authors |
0.34 | 5 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Quan Liu | 1 | 145 | 30.01 |
| Liangyun Ma | 2 | 0 | 0.34 |
| Qingsong Ai | 3 | 43 | 15.50 |
| Kun Chen | 4 | 0 | 0.34 |
| Wei Meng | 5 | 294 | 30.14 |