Acquisition and Prediction of Gestures' Surface EMG Data Using Sequential Deep Learning Methods

Idan Hasson, M.Sc. Thesis Seminar
Tuesday, 8.1.2019, 11:30
Taub 601
Prof. A. Bronstein

As technology becomes highly integrated into nearly every aspect of life, and in many cases is indispensable, maintaining relative hand functionality is crucial. A transradial amputation is a partial amputation of the arm below the elbow that can greatly impede one’s ability to perform every day tasks at home and at work. With the growing dependency on hand functionality and gesture formation to keep up with technological use, the disparity in functional ability between those that are healthy and those that have received partial amputations increases. As a result, muscle-computer interfaces (muCIs), which translate muscle activity to computer commands, allow individuals who have suffered from transradial amputations to utilize these human-machine interfaces in order to decrease this functionality gap. Surface electromyography (sEMG) is a common method used to measure muscle activity. In this lecture, we describe a method for gesture recognition using sEMG data. Furthermore, we detail our method for massive data collection, including transitional data. The sEMG data is acquired by Myo, a novel and inexpensive Bluetooth compatible device based on the dry electrodes acquisition approach. We describe how to simulate HD-sEMG using more than one Myo. In addition, we use the spatial and the temporal characteristic of the collected data in order to describe convolutional neural network (CNN) and convolutional recurrent neural network (CRNN) that aims to solve the task of gesture recognition. We also try to examine the usability of Myo's IMU data in the gestures recognition task.

Back to the index of events