DefinePK

Abstract

In the present paper, we introduce a methodology for movement inception detection based on superficial Electromyography Signals (sEMG). Consequently, a mathematical model using feature extraction and feature flow is proposed, selected features are Mean Absolute Value (MAV), Root Mean Square (RMS), and Entropy (H). The first two are chosen due to the low computational cost, and the last one is chosen due to its outstanding behavior to recognize movements. Moreover, an experimental assessment is carried out using a wearable device so-called Myo Armband bracelet, during experiments three subjects execute grasp (close hand) and release (open hand) movements. Finally, experimental results show that entropy and entropy flow are suitable for detecting movement inception and for further classification of movement, and our methodology allows detecting movement inception in $245.9$ms, out of laboratory conditions.