Classification of myopotentials of hand’s motions to control applications

Realization of the system for classification of hand’s gestures is described in this paper. The first goal was to create hardware that would be able to measure signal of myopotentials for computer analysis without external noise and with right amplification. The second goal was to program an algorithm which could classify specific gestures of hand. Hardware prototype of four measuring channels was created by combination of 2nd order filters and right amount amplification. The user is isolated from the power source using galvanic isolation because of usage of active electrodes. For digitizing the data, the Arduino Nano microcontroller was selected and programmed using defined communication protocol. The computer software is programmed in C# programming language. Signal processing and drawing to user interface is in real time. The one of five possible gestures that user made is chosen using fuzzy logic and designed system of scaling.