Single channel surface electromyography blind recognition model based on watermarking

Abstract

A single channel electromyography blind recognition model based on watermarking is proposed in this paper. Single Channel Independent Component Analysis is adopted to avoid complicated circuit connection and the unreliability of hardware and reduce the noise which accompanied with surface Electromyography (sEMG) signals. Embedded watermarking is applied to solve the problem of blind source separation disorder. A self adaptive neural network and some eigenvectors are applied in sEMG features classification. From the classification results, hand gestures can be recognized. In consideration of time-scale synchronization attack, the host sEMG signals are transformed into wavelet domain and the synchronization codes are embedded. The experiment results show that the model proposed in this paper is penetrable against most common signal processing, and can recognize the hand gesture accurately.