Robot mobile control based on three EMG signals using an artificial neural network

Abstract

The EMG signals can be produced from the human muscle activity. This paper explains the control system of the robot mobile which uses the EMG signal from three muscles contraction such as the jaw muscles, the right arm muscles, and the left arm muscles. The peak values of the EMG signal was used as the input to the ANN system using the Backpropagation algorithm, and it produces the output which has nine target conditions; the forward, then turn right and then turn left where each of them has the variations such as the slow, the medium and the fast. The ANN has been trained with 270 of the training data, and it has been tested with 135 of the testing data from 15 respondents who performed muscle contraction activities. Based on the test result, there are only two unrecognizable data with the rate of the system accuracy is 98.52%. The movements of the robot mobile can be controlled based on the recognized movement patterns with the specified target conditions.

Electrooculogram (EOG) based Mouse Cursor Controller Using the Continuous Wavelet Transform and Statistic Features

“…A control system using EOG signals may be the last alternative if the hands and feet are also disabled. This proposed study can complement the previous study by Rusydi et al [19], where muscle signals and EOG can be utilized for the control system.…”