A Real-Time Fail-Safe Algorithm for Decoding of Myoelectric Signals to Control a Prosthetic Arm

In this article a real-time self-tuning algorithm of detecting fingers movements based on the electromyographic (EMG) sensors is developed. A multi-level input data processing from the EMG sensor with self diagnosis is suggested. It provides the identification of muscle tension, which corresponds of several types of finger movements. This solution enables to use the lowbit controllers to manipulate the prosthetic hand. The results of system modeling and testing on the Arduino nano microcontroller demonstrated that the system identifies finger movements with high accuracy.