- 11
- Using recurrent neural networks for orthopedic data sequences’processing
- Smirnov E. E., Kostyleva V. V., Murtazina A. R. Using recurrent neural networks for orthopedic data sequences’ processing. Technologies & Quality. 2026. No 3(73). P. 70–76. (In Russ.) https://doi.org/ 10.34216/2587-6147-2026-3-73-70-77.
- DOI: https://doi.org/10.34216/2587-6147-2026-3-73-70-76
- УДК: 685.34
- EDN: FVVYKS
- Publish date: 2026-07-02
- Annotation: Personalization of orthopedic products increases the comfort of their use by patients, but requires a lot of resources. High-quality production of such a product is associated with a number of surveys, which are characterized by a large amount of output data. The use of recurrent architecture neural networks can reduce the time spent on their processing and analysis. However, the principles of building such networks and evaluating their effectiveness vary significantly from task to task. This article discusses auxiliary criteria that enhance the objectivity of choosing the appropriate architecture.
- Keywords: Neural networks, orthopedic shoes, orthopedic insoles, podograph, recurrent neural networks, machine learning, mask
- Literature list: 1. Dolganov D. V., Dolganova T. I., Teplen’kii M. P., Oleinikov E. V. Diagnostics and correction of postural disorders due dysplasia of the hip in children. Genij ortopedii [The genius of orthopedics]. 2013;1:40–43. (In Russ.) 2. Baindurashvili A. G., Solov’eva K. S., Zaletina A. V. Disability of Russia children population due to injuries and diseases of the locomotor system. Genij ortopedii [The genius of orthopedics]. 2013;1:5–8. (In Russ.) 3. Skriabin E. G., Durov M. F., Prokopiyev N. Ya. A new safe method for diagnostics of the spine deformities and a system of non-medicamentous treatment of the pain vertebrogenic syndrome in pregnant women. Genij ortopedii [The genius of orthopedics]. 2003;1:14–16. (In Russ.). 4. Isaeva A. S., Denisenko M. A., Kots I. N. Testing the layout of the rail condition monitoring system using LSTM recurrent neural networks. St. Petersburg State Polytechnical University Journal. Physics and Mathematics. 2022;15,S3.2:51–55. 5. Brokarev I. A., Farkhadov M.P., Vaskovskii S. V. Recurrent neural networks to analyze the quality of natural gas. Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitel’naya tekhnika i informatika [Tomsk State University Journal. Control and Computer Science]. 2021;55:11–17. 6. Murav’eva N. V. Diagnosis and correction of postural disorders in patients with hemihypoplasia. Abstract Cand. Med. Sci. dis. Moscow, 2015. 22 p. (In Russ.) 7. Smirnov E. E., Kostyleva V. V., Murtazina A. R., Razin I. B., Sergeev V. A. Determining the position of the feet in the image using a convolutional neural network. Kostyumologiya [Journal of Clothing Science]. 2023;8(3):29TLKL323. URL: https://kostumologiya.ru/PDF/29TLKL323.pdf (accessed 10.03.2026). (In Russ.) 8. Training of Recurrent Neural Networks (RNN) in TensorFlow. URL: https://www.geeksforgeeks.org/ deep-learning/training-of-recurrent-neural-networks-rnn-in-tensorflow (accessed 26.09.2025).
