Multivariate Empirical Mode Decomposition Based EMG Signal Analysis For Smart Prosthesis
Küçük Resim Yok
Electromyography (EMG) signals are successfully used for human-robot interaction with biomedical applications. One of the basic components of many modern prosthesis is the myoelectric control system which controls prosthetic movements through EMG signals. In this study, multivariate empirical mode decomposition (MEMD) based signal processing and analysis of EMG signals was investigated in the decision making process of smart hand proshesis movements of transradial amputees. Due to MEMD's non-linear and non-stationary signal processing capability, the obtained MEMD-based features are intended to increase the performance of the controlled prosthesis using multi-channel EMG signals. The MEMD-based features obtained through the EMG signals recorded for 6 positions from 9 transradial amputees were classified by the nearest neighbors and decision tree algorithms and an average of 77% (up to 100% for some amputees) accuracy was obtained for a maximum of 9 amputees.
26th IEEE Signal Processing and Communications Applications Conference (SIU) -- MAY 02-05, 2018 -- Izmir, TURKEY
Smart prosthesis, Electromyography, Multivariate empirical mode decomposition, Sample entropy
2018 26Th Signal Processing And Communications Applications Conference (Siu)