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
. 2020 Aug 11;20(16):4481.
doi: 10.3390/s20164481.

A Deep-Learning Approach for Foot-Type Classification Using Heterogeneous Pressure Data

Jonghyeok Chae  1 , Young-Jin Kang  2 , Yoojeong Noh  1
Affiliations

A Deep-Learning Approach for Foot-Type Classification Using Heterogeneous Pressure Data

Jonghyeok Chae et al. Sensors (Basel). .

Abstract

The human foot is easily deformed owing to the innate form of the foot or an incorrect walking posture. Foot deformations not only pose a threat to foot health but also cause fatigue and pain when walking; therefore, accurate diagnoses of foot deformations are required. However, the measurement of foot deformities requires specialized personnel, and the objectivity of the diagnosis may be insufficient for professional medical personnel to assess foot deformations. Thus, it is necessary to develop an objective foot deformation classification model. In this study, a model for classifying foot types is developed using image and numerical foot pressure data. Such heterogeneous data are used to generate a fine-tuned visual geometry group-16 (VGG16) and K-nearest neighbor (k-NN) models, respectively, and a stacking ensemble model is finally generated to improve accuracy and robustness by combining the two models. Through k-fold cross-validation, the accuracy and robustness of the proposed method have been verified by the mean and standard deviation of the f1 scores (0.9255 and 0.0042), which has superior performance compared to single models generated using only numerical or image data. Thus, the proposed model provides the objectivity of diagnosis for foot deformation, and can be used for analysis and design of foot healthcare products.

Keywords: arch index; fine-tuned VGG16; heterogeneous pressure data; k-NN; stacking ensemble.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflicts of interest.

Figures

Figure 1
Figure 1
Experimental method and results. (a) Plantar pressure measurement, (b) numerical pressure data, (c) distribution of pressure image data.
Figure 2
Figure 2
Arch index calculation method.
Figure 3
Figure 3
Labeled results and histogram of arch index data. (a) Arch index method and labeled image data, (b) Distribution of the data.
Figure 4
Figure 4
Image data pre-processing.
Figure 5
Figure 5
Image positioning method.
Figure 6
Figure 6
Definition of rotation angle.
Figure 7
Figure 7
Steps in generating toe-less image.
Figure 8
Figure 8
Data augmentation method.
Figure 9
Figure 9
Correlation analysis results for features and arch index.
Figure 10
Figure 10
Scheme showing the proposed stacking ensemble model.
Figure 11
Figure 11
Results of learning models.
See this image and copyright information in PMC

References

    1. Michaud T.C. Human Locomotion: The Conservative Management of Gait-Related Disorders. 1st ed. Netwon Biomechanics; Newton, MA, USA: 2011.
    1. Menz H.B., Dufour A.B., Riskowski J.L., Hillstrom H.J., Hannan M.T. Association of planus foot posture and pronated foot function with foot pain: The Framingham foot study. Arthritis Rheum. 2013;65:1991–1999. doi: 10.1002/acr.22079. - DOI - PMC - PubMed
    1. Iii D.S.W., McClay I.S., Hamill J. Arch structure and injury patterns in runners. Clin. Biomech. 2001;16:341–347. - PubMed
    1. Williams D.S., McClay I.S., Hamill J., Buchanan T.S. Lower extremity kinematic and kinetic differences in runners with high and low arches. J. Appl. Biomech. 2001;17:153–163. doi: 10.1123/jab.17.2.153. - DOI
    1. Zuil-Escobar J.C., Martínez-Cepa C.B., Martín-Urrialde J.A., Gómez-Conesa A. Medial longitudinal arch: Accuracy, reliability, and correlation between navicular drop test and footprint parameters. J. Manip. Physiol. Ther. 2018;41:672–679. doi: 10.1016/j.jmpt.2018.04.001. - DOI - PubMed