Patients with amputations of both hands need prosthetic hands that serve both cosmetic andfunctional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, butthere is still the problem of high cost. In this ...
Patients with amputations of both hands need prosthetic hands that serve both cosmetic andfunctional purposes, and research on prosthetic hands using electromyography of remaining muscles is active, butthere is still the problem of high cost. In this study, an artificial prosthetic hand was manufactured and itsperformance was evaluated using low-cost parts and software such as a surface electromyography sensor,machine learning software Edge Impulse, Arduino Nano 33 BLE, and 3D printing. Using signals acquired withsurface electromyography sensors and subjected to digital signal processing through Edge Impulse, the flexingmovement signals of each finger were transmitted to the fingers of the prosthetic hand model through trainingto determine the type of finger movement using machine learning. When the digital signal processing conditionswere set to a notch filter of 60 Hz, a bandpass filter of 10-300 Hz, and a sampling frequency of 1,000 Hz, theaccuracy of machine learning was the highest at 82.1%. The possibility of being confused between each fingerflexion movement was highest for the ring finger, with a 44.7% chance of being confused with the movementof the index finger. More research is needed to successfully develop a low-cost prosthetic hand.