Browse > Article
http://dx.doi.org/10.9708/jksci.2021.26.04.021

Deep Learning-based Pes Planus Classification Model Using Transfer Learning  

Kim, Yeonho (Graduate School of Business IT, Kookmin University)
Kim, Namgyu (Graduate School of Business IT, Kookmin University)
Abstract
This study proposes a deep learning-based flat foot classification methodology using transfer learning. We used a transfer learning with VGG16 pre-trained model and a data augmentation technique to generate a model with high predictive accuracy from a total of 176 image data consisting of 88 flat feet and 88 normal feet. To evaluate the performance of the proposed model, we performed an experiment comparing the prediction accuracy of the basic CNN-based model and the prediction model derived through the proposed methodology. In the case of the basic CNN model, the training accuracy was 77.27%, the validation accuracy was 61.36%, and the test accuracy was 59.09%. Meanwhile, in the case of our proposed model, the training accuracy was 94.32%, the validation accuracy was 86.36%, and the test accuracy was 84.09%, indicating that the accuracy of our model was significantly higher than that of the basic CNN model.
Keywords
Pes planus; Deep learning; Convolutional neural network(CNN); Transfer learning; Data Augmentation;
Citations & Related Records
Times Cited By KSCI : 3  (Citation Analysis)
연도 인용수 순위
1 S. Y. Oh and D. A. Suh, "Producing the insoles for flat feet of senior men using 3d systems based on 3d scanning, 3d modeling, and 3d printing," The Research Journal of the Costume Culture, Vol. 25, No. 3, pp. 270-284, Jun, 2017.   DOI
2 J. Joo and Y. Kim, "Effects of customized 3d-printed insoles on the kinematics of flat-footed walking and running," Korean Journal of Sport Biomechanics, Vol. 28, No. 4, pp. 237-244, Jan, 2018.   DOI
3 F. Chollet, "Deep learning from keras' creator," Gilbut, pp. 33-34, 199-218 , 2018.
4 K. P. Kim, H. J. Jeong and K. S. Ham, "Comparison of deep-learning algorithms for eeg-based eyewitness memory classification system," Journal of Scientific Criminal Investigation, Vol. 13, No. 2, pp. 95-101, Jun, 2019.   DOI
5 C. S. MA and J. C. Choi, "Machine learning & deep learning with a clear view of business," only book, pp. 123-128, 2019.
6 M. T. Bhoir, "Prevalence of flat foot among 18-25 years old physiotherapy students: cross sectional study," Indian Journal of Basic and Applied Medical Research, Vol. 3, No. 4, pp. 272-278, Sept, 2014.
7 E. Toullec, "Adult flatfoot," Orthopaedics & Traumatology: Surgery & Research, Vol. 101, No. 1, S11-S17, Jan, 2015.   DOI
8 E. S. Lee, "Impact of intrinsinc foot muscle training and navicular mobilization on flexible flatfeet to improve life-care," Journal of the Korea Entertainment Industry Association(JKEIA), Vol. 13, No. 5, pp. 195-201, July, 2019.   DOI
9 H. J. Hillstrom, J. S. Song, A. P. Kraszewski, J. F. Hafer, R. Mootanah, A. B. Dufour, B. S. Chow, and J. T. Deland, "Foot type biomechanics part 1: structure and function of the asymptomatic foot," Gait Posture, Vol. 37, No. 3, pp. 445-451, Mar, 2013.   DOI
10 M. C. Park, "The effect of low-dye taping on muscle activity during single-leg standing in people with flatfoot," Journal of the Korean Society of Physical Medicine, Vol. 8, No. 4, pp. 533-538, Nov, 2013.   DOI
11 S. K. Kim, Y. U. Ryu and H. D. Kim, "The effects of insole supporting medial longitudinal arch while walking in spastic cerebral palsy with pes planus," Journal of the Korean Society of Physical Medicine, Vol. 7, No. 4, pp. 471-480, Nov, 2012.   DOI
12 H. J. Lim, M. J. Kim and H. R. Kim, "Sound event classification using deep neural network based transfer learning," The Journal of the Acoustical Society of Korea, Vol. 35, No. 2, pp. 143-148, Mar, 2016.   DOI
13 Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural Computation, Vol. 1, No. 4, pp. 541-551, Dec, 1989.   DOI
14 J. J. Kim and T. Y. Choe, "Fast baseball player location detection system using convolutional neural networks for real time broadcast," KIISE Transactions on Computing Practices, Vol. 25, No 3, pp. 171-178, Mar, 2019.   DOI
15 M. Kim and N. Kim, "Text Augmentation Using Hierarchy-based word Replacement," Journal of The Korea Society of Computer and Information, Vol. 26, No. 1, pp. 57-67, Jan, 2020.   DOI
16 D. H. Seol, J. H. Oh and H. J. Kim, "Comparison of deep learning-based cnn models for crack detection," Journal of the Architectural Institute of Korea Structure & Construction, Vol. 36, No. 3, pp. 113-120, Mar, 2020.
17 Y. C. Lin, J. N. Mhuircheartaigh, J. Lamb, J. W. Kung, C. M. Yablon and J. S. Wu, "Imaging of adult flatfoot: correlation of radiographic measurements with mri," Musculoskeletal Imaging & Original Research, Vol. 204, No. 2, pp. 354-359, Feb, 2015.
18 N. S. Kim and W. H. Do, "Classification of elderly women's foot type," Journal of the Korean Society of Clothing and Textiles, Vol. 38, No. 3, pp. 305-320, Jun, 2014.   DOI
19 K. H. Han, K. H. Bae, H. G. Jung, M. S. Ha, D. Y. Choi, J. S. Lee, and M. S. Yang, "Comparison of plantar pressure and cop parameters in three types of arch support insole during stair descent in elderly with flatfoot," Journal of Oil & Applied Science, Vol. 35, No. 3, pp. 948-955, Sept, 2018.   DOI