Artificial neural networks (ANNs) were used to classify EMG signals from an arm. Using an amplifier card from the Smart Hand project or prosthetic hand, 16-channel EMG signals were collected from the patients arm and Filtered. After time-domain feature extraction, simple back-propagation training was used to train the networks. During the training, the patient moved his Fingers according to a predefined pattern. After the training, the patient could move an artificial hand by duplicating the movements made during training. Artificial hands are nothing new. One of the earliest mentions is of a Roman general that fought with an iron arm back around the year 50 AD and many of researchers have done on this project. Hopefully, this work will show that this approach to the problem of controlling hand prosthesis is viable and that it has benefits over other methods previously used.