Study on the Effects of Electrical Stimulation on the Pattern Recognition for an EMG Prosthetic Application

The need of biofeedback in Man-Machine interfaces is of vital importance for the development of subconscious control with external devices. In order to obtain extended proprioception, in other words, to include the external devices into the body schema, we need to provide with more feedback channels to the human body. In this study we look into the use of electrical stimulation as biofeedback and its effects over the pattern recognition process from the EMG signals that controls the hand movements.

I. Introduction

Although some studies has been done on electrically powered prosthetic devices [1], [2] and the efficiency increase due to tactile feedback [3], [4], there is a little study done on the application of biofeedback in order to obtain close loop systems[5], [6]. In the area of man-machine interfaces we find some studies [7] on haptic interfaces in order to provide tactile feedback. All these studies focus on the sensorial substitution using the finger tips. Regrettably, those cannot be applied to prosthetic devices where the user presents partial or complete loss of the arm, which are our interest in this study; therefore, we need to find a different way to provide the required feedback for the control system. One idea is to interact directly with the nervous system, in order to communicate the information to the brain using the same pathway as other sensorial information in the body. We propose the use of electrical stimulation for this purpose because it acts directly and strongly on the afferent nerves. In this study, we use an EMG controlled electrically powered prosthetic hand (Fig. 1). The system uses a neural network as classification unit to identify the intended movement from the user. As the studies done on the control of Functional Electrical Stimulation (FES) by Electromyography (EMG) [8], the problem to solve is the effects on the EMG signal by the electrical noise generated by the electrical stimulation, which can overwrite the signal generated by the muscles. In this study we look for the proper biofeedback for the EMG controlled prosthetic hand user to interact with the environment in order to develop an extended proprioception control. In this paper we measure the effects on the EMG acquisition process by the electrical stimulation. Fig. 1:

Electrically powered EMG controlled robot hand