Electromyogram signal is a biomedical signal that measures electrical activity produced in a muscle during its contraction. This work presents a prototype system for moving a prosthetic lower arm, without prior operation intervention, using electrodes that measure electromyogram (EMG) signals placed on two muscles only. The signals are then read by sensors connected to Arduino microcontroller, processed and passed to MATLAB via Bluetooth where features are extracted and input to a neural network to classify one out of six movements. A servo motor receives a driving signal to move the simulated arm to the required position. The system enables the arm to do six movements without any external help. The system results are compared to other systems' results and it was able to achieve 99.7% classification rate which is considered, among other systems, the highest for classifying six movements