Towards cybernetic hand: A neural network method for hand prosthesis control

Intelligent systems can feel, learn, interpret, act and correct themselves based on their last trials or forget them completely. The major goal in an intelligent system is to model the human behavior and set it up on a machine. The main control command of a cybernetic hand should be posted by the remaining healthy organs of the disabled person. These commands can be from several channels, which their recording and detecting are different and need complicated study. In this research, we suppose that, this stage has been done or in other words, the command has been already sent and detected. So the main goal is to control a long hand, which has the part above the elbow missing, by an angle indicated by the disabled. This means that, the system input is the position desired by the disabled and the output is the elbow-joint angle variation. Therefore the goal is a suitable control design based on neural network theory in order to meet the given mapping.