Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Filters applied. Clear all
. 2019 Jan 17;19(2):371.
doi: 10.3390/s19020371.

Inferring Static Hand Poses From a Low-Cost Non-Intrusive sEMG Sensor

Affiliations
Free PMC article

Inferring Static Hand Poses From a Low-Cost Non-Intrusive sEMG Sensor

Nadia Nasri et al. Sensors (Basel). .
Free PMC article

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.

Keywords: dataset; gated recurrent units; gesture recognition; surface electromyography sensor.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Public database summary table.
Figure 2
Figure 2
Myo armband tear-down [46].
Figure 3
Figure 3
Hand gestures.
Figure 4
Figure 4
Raw signals (eight) captured with by Myo armband device.
Figure 5
Figure 5
Window method implemented on input data.
Figure 6
Figure 6
Proposed neural network architecture for hand gesture recognition.
Figure 7
Figure 7
Confusion matrix for three gestures.
Figure 8
Figure 8
Accuracy and loss graph during the training process.
Figure 9
Figure 9
Categorize data by features via T-SNE.
Figure 10
Figure 10
Confusion matrix.
Figure 11
Figure 11
Confusion matrix from a patient with CMT disease.

Similar articles

See all similar articles

Cited by 2 articles

References

    1. Cook A.M., Polgar J.M. Essentials of Assistive Technologies. ELSEVIER Mosby; Amsterdam, The Netherlands: 2012.
    1. Costa A., Martinez-Martin E., Cazorla M., Julian V. PHAROS—PHysical Assistant RObot System. Sensors. 2018;18:2633 doi: 10.3390/s18082633. - DOI - PMC - PubMed
    1. LeBlanc M. Give Hope—Give a Hand. The Ellen Meadows Prosthetic Hand Foundation; San Francisco, CA, USA: 2008. The LN-4 Prosthetic Hand.
    1. Momen K., Krishnan S., Chau T. Real-time classification of forearm electromyographic signals corresponding to user-selected intentional movements for multifunction prosthesis control. IEEE Trans. Neural Syst. Rehabil. Eng. 2007;15:535–542. doi: 10.1109/TNSRE.2007.908376. - DOI - PubMed
    1. Amsuss S., Goebel P.M., Jiang N., Graimann B., Paredes L., Farina D. Self-correcting pattern recognition system of surface EMG signals for upper limb prosthesis control. IEEE Trans. Biomed. Eng. 2014;61:1167–1176. doi: 10.1109/TBME.2013.2296274. - DOI - PubMed
Feedback