Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Aug 26:2021:6591035.
doi: 10.1155/2021/6591035. eCollection 2021.

A Hierarchical View Pooling Network for Multichannel Surface Electromyography-Based Gesture Recognition

Wentao Wei  1 , Hong Hong  2 , Xiaoli Wu  1
Affiliations

A Hierarchical View Pooling Network for Multichannel Surface Electromyography-Based Gesture Recognition

Wentao Wei et al. Comput Intell Neurosci. .

Abstract

Hand gesture recognition based on surface electromyography (sEMG) plays an important role in the field of biomedical and rehabilitation engineering. Recently, there is a remarkable progress in gesture recognition using high-density surface electromyography (HD-sEMG) recorded by sensor arrays. On the other hand, robust gesture recognition using multichannel sEMG recorded by sparsely placed sensors remains a major challenge. In the context of multiview deep learning, this paper presents a hierarchical view pooling network (HVPN) framework, which improves multichannel sEMG-based gesture recognition by learning not only view-specific deep features but also view-shared deep features from hierarchically pooled multiview feature spaces. Extensive intrasubject and intersubject evaluations were conducted on the large-scale noninvasive adaptive prosthetics (NinaPro) database to comprehensively evaluate our proposed HVPN framework. Results showed that when using 200 ms sliding windows to segment data, the proposed HVPN framework could achieve the intrasubject gesture recognition accuracy of 88.4%, 85.8%, 68.2%, 72.9%, and 90.3% and the intersubject gesture recognition accuracy of 84.9%, 82.0%, 65.6%, 70.2%, and 88.9% on the first five subdatabases of NinaPro, respectively, which outperformed the state-of-the-art methods.

PubMed Disclaimer

Conflict of interest statement

The authors declare that there are no conflicts of interest regarding the publication of this paper.

Figures

Figure 1
Figure 1
A schematic diagram of the proposed HVPN framework. FLVP, Conv, LC, and FC denote the feature-level view pooling layer, convolutional layer, locally connected layer, and fully connected layer, respectively. The numbers after the layer name denote the size and number of the filters or neurons; for example, Conv 3 × 3@64 denotes a CNN with 64 3 × 3 filters, and FC 1024 denotes an FC layer with 1024 hidden units.
Figure 2
Figure 2
Diagram of the FLVP layer.
Figure 3
Figure 3
Schematic diagrams of (a) VS-L1VP, (b) VS-L2VP, and (c) VS-ONLY.
Algorithm 1
Algorithm 1
The image generation algorithm used in this paper [39].
See this image and copyright information in PMC

References

    1. Beanbonyka R., Nak-Jun S., Sedong M., Min H. Deep learning in physiological signal data: a survey. Sensors. 2020;20(4):p. 969. doi: 10.3390/s20040969. - DOI - PMC - PubMed
    1. Chen X., Wang S., Huang C., Cao S., Zhang X. ICA-based muscle-tendon units localization and activation analysis during dynamic motion tasks. Medical & Biological Engineering & Computing. 2018;56(3):341–353. doi: 10.1007/s11517-017-1677-z. - DOI - PubMed
    1. Li C., Li G., Jiang G., Chen D., Liu H. Surface EMG data aggregation processing for intelligent prosthetic action recognition. Neural Computing and Applications. 2018;32(22):16795–16806. doi: 10.1007/s00521-018-3909-z. - DOI
    1. Shi G., Xu G., Wang H., Duan N., Zhang S. Fuzzy-adaptive impedance control of upper limb rehabilitation robot based on sEMG. Proceedings of International Conference on Ubiquitous Robots; June 2019; Jeju, Korea. pp. 745–749. - DOI
    1. Ma R., Zhang L., Li G., Jiang D., Xu S., Chen D. Grasping force prediction based on sEMG signals. Alexandria Engineering Journal. 2020;59(3):1135–1147. doi: 10.1016/j.aej.2020.01.007. - DOI

LinkOut - more resources