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
. 2022 Nov 2;22(21):8438.
doi: 10.3390/s22218438.

A Spatio-Temporal Graph Convolutional Network Model for Internet of Medical Things (IoMT)

Dipon Kumar Ghosh  1 , Amitabha Chakrabarty  1 , Hyeonjoon Moon  2 , M Jalil Piran  2
Affiliations

A Spatio-Temporal Graph Convolutional Network Model for Internet of Medical Things (IoMT)

Dipon Kumar Ghosh et al. Sensors (Basel). .

Abstract

In order to provide intelligent and efficient healthcare services in the Internet of Medical Things (IoMT), human action recognition (HAR) can play a crucial role. As a result of their stringent requirements, such as high computational complexity and memory efficiency, classical HAR techniques are not applicable to modern and intelligent healthcare services, e.g., IoMT. To address these issues, we present in this paper a novel HAR technique for healthcare services in IoMT. This model, referred to as the spatio-temporal graph convolutional network (STGCN), primarily aims at skeleton-based human-machine interfaces. By independently extracting spatial and temporal features, STGCN significantly reduces information loss. Spatio-temporal information is extracted independently of the exact spatial and temporal point, ensuring the extraction of useful features for HAR. Using only joint data and fewer parameters, we demonstrate that our proposed STGCN achieved 92.2% accuracy on the skeleton dataset. Unlike multi-channel methods, which use a combination of joint and bone data and have a large number of parameters, multi-channel methods use both joint and bone data. As a result, STGCN offers a good balance between accuracy, memory consumption, and processing time, making it suitable for detecting medical conditions.

Keywords: Internet of Medical Things (IoMT); graph convolutional network (GCN); healthcare; human action recognition (HAR).

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
A smart healthcare system for real-time patient monitoring.
Figure 2
Figure 2
The end-to-end pipeline of STGCN.
Figure 3
Figure 3
(a) Spatio-temporal graph of skeleton joints; (b) Mapping of different joints in the graph depending on their position.
Figure 4
Figure 4
Architecture of an adaptive graph convolutional layer.
Figure 5
Figure 5
A spatio-temporal graph convolutional block of STGCN.
Figure 6
Figure 6
The architecture of STGCN.
Figure 7
Figure 7
Visualization of feature extraction by STGCN. (a–c) represents the features extracted at different frames.
Figure 8
Figure 8
Performance measurement of the training and validation process. (a) Comparison between training loss and validation loss for the X-view subset. (b) Comparison between training and validation accuracy for X-view subset. (c) Comparison between training and validation loss for X-sub subset. (d) Comparison between training accuracy and validation accuracy for X-sub subset.
Figure 9
Figure 9
Comparisons between STGCN and other GCN-based models. (a) Comparison between STGCN and other GCN-based models with respect to the number of parameters. (b) Comparison between STGCN and other GCN-based models with respect to complexity.
Figure 10
Figure 10
Accuracy of STGCN for medical condition- related actions.
See this image and copyright information in PMC

References

    1. Papaioannou M., Karageorgou M., Mantas G., Sucasas V., Essop I., Rodriguez J., Lymberopoulos D. A survey on security threats and countermeasures in internet of medical things (IoMT) Trans. Emerg. Telecommun. Technol. 2022;33:e4049. doi: 10.1002/ett.4049. - DOI
    1. Su Y.S., Ding T.J., Chen M.Y. Deep learning methods in internet of medical things for valvular heart disease screening system. IEEE Internet Things J. 2021;8:16921–16932. doi: 10.1109/JIOT.2021.3053420. - DOI
    1. Yang L., Yu K., Yang S.X., Chakraborty C., Lu Y., Guo T. An intelligent trust cloud management method for secure clustering in 5G enabled internet of medical things. IEEE Trans. Ind. Inform. 2021;18:8864–8875. doi: 10.1109/TII.2021.3128954. - DOI
    1. Swarna Priya R.M., Maddikunta P.K.R., Parimala M., Koppu S., Gadekallu T.R., Chowdhary C.L., Alazab M. An effective feature engineering for DNN using hybrid PCA-GWO for intrusion detection in IoMT architecture. Comput. Commun. 2020;160:139–149. doi: 10.1016/j.comcom.2020.05.048. - DOI
    1. Xiong H., Jin C., Alazab M., Yeh K.H., Wang H., Gadekallu T.R., Wang W., Su C. On the Design of Blockchain-Based ECDSA With Fault-Tolerant Batch Verification Protocol for Blockchain-Enabled IoMT. IEEE J. Biomed. Health Inform. 2022;26:1977–1986. doi: 10.1109/JBHI.2021.3112693. - DOI - PubMed