Optimized circuit and control for prosthetic arm based on myoelectric pattern recognition via power spectral density analysis

Myoelectric pattern recognition has shown promise in the control of the prosthetic arm. But interfering noise and motion artifacts have hindered this kind of method to be used outside a controlled environment. This paper has designed an optimized circuit to process the Electromyography (EMG) signal. EMG signal is acquired from surface skin using sEMG (Surface Electromyography) electrode. EMG can be defined as an electrical potential produced due to contraction of the muscle. EMG signal requires to the undergo process of amplification and noise reduction before it can be converted to digital signal by the analog-digital converter (ADC) and processed to drive the motors or actuators of the prosthetic arm. The proposed denoising algorithm will improve the signal to noise ratio in real life uses. But the improved signal to noise ratio is expected to be insignificant as machine learning algorithm integrate noise as part of the signal. However, the variation of noise in real life uses is expected to occur where the proposed algorithm would potentially have a positive impact and further enhance the feasibility of using prosthetic for daily life.