In virtual reality (VR) systems, the user’s finger and hand positions are sensed and used to control the virtual environments. Direct biocontrol of VR environments using surface electromyographic (EMG) signals may be more synergistic and unconstraining to the user.
The purpose of the present investigation was to develop a technique to predict the finger joint angle from the surface EMG measurements of the extensor muscle using neural network models.MethodologySurface EMG (SMEG) together with the actual joint angle measurements were obtained when the subject was performing flexion-extension rotation of the index finger at three speeds. Several neural networks were trained to predict the joint angle from the parameters extracted from the SEMG signals.
The best networks were selected to form six committees. The neural network committees were evaluated using data from new subjects.
Results: There was hysteresis in the measured SMEG signals during the flexion extension cycle.
However, neural network committees were able to predict the joint angle with reasonable accuracy. The mean RMS errors ranged from 0.085 for fast speed finger extension to 0.147 for slow speed finger extension, and from 0.098 for the fast speed finger flexion to 0.163 for slow speed finger flexion.
Conclusion: Although significant hysteresis was displayed in the measured SEMG signals, the committees of neural networks were able to predict the finger joint angle from SEMG signals.
Author: Nikhil A Shrirao, Narender P Reddy and Durga R Kosuri
Credits/Source: BioMedical Engineering OnLine 2009, 8:2