Galileo bionic hand: sEMG activated approaches for a multifunction upper-limb prosthetic

Surface electromyography (sEMG) commonly used in upper-limb prostheses requires expensive medical equipment to get accurate results, and even then only a few actions can be classified. We propose an sEMG activated embedded system based on Digital Signal Processing and Machine Learning, to interpret the user intention with the purpose of controlling a low-cost 3D printed hand prosthesis with multiple Degrees of Freedom (DOF). The system has three different operating modes with a user-friendly Human Machine Interface (HMI), in order to increase the amount of customized hand postures that can be performed by the user, providing functionalities that fit on their daily chores and allowing to use inexpensive surface mounted passive electrodes in order to keep a low cost approach. Inasmuch as sEMG activation allows the user to consciously perform the desired action, on the other hand a touchscreen enables the possibility to select different predefined actions and operating modes, as well as provide necessary visual feedback. Moreover, in another operating mode, a speech recognition module recognizes user speech in 3 different languages, allowing the user more sEMG activated postures. Finally, an operating mode based on Artificial Neural Networks (ANN) classifies 5 hand gestures that can be easily accomplished by below elbow amputees. The system was tested and obtained high accuracy and great responsiveness on the different modes of operation.