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
. 2024 Nov 19;24(22):7370.
doi: 10.3390/s24227370.

AI-Aided Gait Analysis with a Wearable Device Featuring a Hydrogel Sensor

Saima Hasan  1 , Brent G D'auria  1 , M A Parvez Mahmud  2 , Scott D Adams  1 , John M Long  1 , Lingxue Kong  3 , Abbas Z Kouzani  1
Affiliations

AI-Aided Gait Analysis with a Wearable Device Featuring a Hydrogel Sensor

Saima Hasan et al. Sensors (Basel). .

Abstract

Wearable devices have revolutionized real-time health monitoring, yet challenges persist in enhancing their flexibility, weight, and accuracy. This paper presents the development of a wearable device employing a conductive polyacrylamide-lithium chloride-MXene (PLM) hydrogel sensor, an electronic circuit, and artificial intelligence (AI) for gait monitoring. The PLM sensor includes tribo-negative polydimethylsiloxane (PDMS) and tribo-positive polyurethane (PU) layers, exhibiting extraordinary stretchability (317% strain) and durability (1000 cycles) while consistently delivering stable electrical signals. The wearable device weighs just 23 g and is strategically affixed to a knee brace, harnessing mechanical energy generated during knee motion which is converted into electrical signals. These signals are digitized and then analyzed using a one-dimensional (1D) convolutional neural network (CNN), achieving an impressive accuracy of 100% for the classification of four distinct gait patterns: standing, walking, jogging, and running. The wearable device demonstrates the potential for lightweight and energy-efficient sensing combined with AI analysis for advanced biomechanical monitoring in sports and healthcare applications.

Keywords: 1D CNN; conductive hydrogel; gait analysis; strain sensor; triboelectric nanogenerator; wearable device.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Schematic circuit diagram of the wearable device.
Figure 2
Figure 2
Photographs of the enclosure with the electronic circuit. (a) Enclosed. (b) and (c) Internal components. (d) Weight (19 g).
Figure 3
Figure 3
Knee brace. (a) Illustration of a human body wearing the knee brace. (b) Photograph of the knee brace with the wearable device. (c) Weight of the wearable device.
Figure 4
Figure 4
Preparation of the PLM sensor. (a) Preparation of the PLM hydrogel (left); internal morphology of the hydrogel (right). (b) PDMS preparation (left); assembly of the PLM sensor (right).
Figure 5
Figure 5
Working mechanism of the PLM sensor-based gait monitoring system. (a) Working principle of the PLM sensor during a stretch–release cycle. (b) System-level block diagram of the gait monitoring system, showing analog signals from the four activities (blue), processing and wireless transmission (green), the digital signal output, and the machine learning algorithm run by the computer (yellow).
Figure 6
Figure 6
Mechanical and electrical performance of the PLM sensor. (a) Tensile stress–strain characteristics. (b) Generated voltage signals with different tensile strains (20%, 40%, 60%, 80%, and 100%). (c) Generated voltage signals at different stretching rates (from 100 to 500 mm min−1) at a fixed strain of 80%. (d) Mechanical durability test for up to 1000 continuous stretch–release cycles at 80% strain.
Figure 7
Figure 7
Gait identification using the 1D CNN model. (a) Voltage acquisition from four gait patterns: standing, walking, jogging, and running. (b) Model structure. (c) Model accuracy. (d) Model loss. (e) Confusion map of the accuracy prediction for the four activities.
See this image and copyright information in PMC

References

    1. Gu C., Lin W., He X., Zhang L., Zhang M. IMU-based motion capture system for rehabilitation applications: A systematic review. Biomim. Intell. Robot. 2023;3:100097. doi: 10.1016/j.birob.2023.100097. - DOI
    1. Manupibul U., Tanthuwapathom R., Jarumethitanont W., Kaimuk P., Limroongreungrat W., Charoensuk W. Integration of force and IMU sensors for developing low-cost portable gait measurement system in lower extremities. Sci. Rep. 2023;13:10653. doi: 10.1038/s41598-023-37761-2. - DOI - PMC - PubMed
    1. Larracy R., Phinyomark A., Scheme E. Gait Representation: From Vision-Based to Floor Sensor-Based Gait Recognition; Proceedings of the 2023 IEEE Sensors Applications Symposium (SAS); Ottawa, ON, Canada. 18–20 July 2023; Piscataway, NJ, USA: IEEE; 2023. pp. 1–6. - DOI
    1. Mao Y., Ogata T., Ora H., Tanaka N., Miyake Y. Estimation of stride-by-stride spatial gait parameters using inertial measurement unit attached to the shank with inverted pendulum model. Sci. Rep. 2021;11:1391. doi: 10.1038/s41598-021-81009-w. - DOI - PMC - PubMed
    1. Qi M., Zhang D., Guo Y., Zhang H., Shao J., Ma Y., Yang C., Mao R. A flexible wearable sensor based on anti-swelling conductive hydrogels for underwater motion posture visualization assisted by deep learning. J. Mater. Chem. A. 2024;12:16839–16853. doi: 10.1039/D4TA02979H. - DOI

MeSH terms

LinkOut - more resources