Abstract
Every year, a significant number of people lose a body part in an accident, through sickness or in high-risk manual jobs. Several studies and research works have tried to reduce the constraints and risks in their lives through the use of technology. This work proposes a learning-based approach that performs gesture recognition using a surface electromyography-based device, the Myo Armband released by Thalmic Labs, which is a commercial device and has eight non-intrusive low-cost sensors. With 35 able-bodied subjects, and using the Myo Armband device, which is able to record data at about 200 MHz, we collected a dataset that includes six dissimilar hand gestures. We used a gated recurrent unit network to train a system that, as input, takes raw signals extracted from the surface electromyography sensors. The proposed approach obtained a 99.90% training accuracy and 99.75% validation accuracy. We also evaluated the proposed system on a test set (new subjects) obtaining an accuracy of 77.85%. In addition, we showed the test prediction results for each gesture separately and analyzed which gestures for the Myo armband with our suggested network can be difficult to distinguish accurately. Moreover, we studied for first time the gated recurrent unit network capability in gesture recognition approaches. Finally, we integrated our method in a system that is able to classify live hand gestures.
Highlights
The importance of technology and science in improving the quality of human health and facilitating human life has been amply demonstrated [1,2]
We recorded three basic hand gestures with almost 6000 samples from 10 subjects via the armband, and examined the output to check the competence of the armband and the Gated Recurrent Unit (GRU) network
Based on the preliminary experiments and in order to expand the dataset, we selected 10 dissimilar hand gestures and trained the network, but the Myo armband and its eight sensors were not sufficient to recognize the difference in all the gestures, with test results being around 40%
Summary
The importance of technology and science in improving the quality of human health and facilitating human life has been amply demonstrated [1,2]. With constantly improving technology, efforts are focused on creating several variants of robotic arms and hands that could replace the lost limb with similar characteristics to a real hand in both appearance and movements. Hand gesture recognition via surface (sEMG) sensors placed on the arm has been a subject of considerable research with different features for applications and prosthetics. Quality of life for amputees is highly deficient in comparison to pre amputation (and losing their limb) but can be ameliorated with real-time control systems based on hand movements [17,18]. In CapMyo and csl-hdemg, datasets were recorded by a large number of HD-sEMG with a high sampling rate using dense arrays of individual electrodes, in order to obtain information from the muscles [28]. Bearing in mind the existence of significant differences between sEMG signal and HD-sEMG results [29], we decided to work with sEMG
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
