I.V. Stepanyan1, S.S. Grokhovsky2, O.V. Kubryak3

1 Mechanical Engineering Research Institute of the Russian Academy of Sciences (Moscow, Russia)

2 Research Center MERA (Moscow, Russia)

3 Research Institute of Normal Physiology named after P.K. Anokhin (Moscow, Russia)

Stabilometry is a modern method for assessing the functional state of a person by the ability to maintain a stable balance of an upright posture. Technically, the implementation of the stabilometry method consists in measuring, with the help of specialized devices, the values that make up the support reaction, with the subsequent determination, according to these measurements, of the coordinates of the center of body pressure on the support. The nature of the migrations of the center of pressure during the stabilometric study is a source of information about the features of the processes of postural regulation. At the same time, up to the present time, there is a problem of the correct interpretation of the results of stabilometry. The adequacy of the conclusions is largely determined by the human factor, i.e. qualification of a specialist analyzing stabilometry data. Thus, in our opinion, the task of objectifying the assessment of stabilometry results is urgent.

The aim of this work is to study the possibility of applying the neurocluster method using self-organizing neural networks to objectify the analysis of stabilometry data. 

The authors proposed a technique for analyzing the structure of individual and group stabilometric data by clustering them using selforganizing Kohonen neural maps with Euclidean metrics.

Neuroclusterization of stabilometric data allows in automatic mode (without human intervention) to identify the type of group of subjects corresponding to the norm or pathology, various types of pathologies, as well as individual biometric characteristics of the subjects. The subsequent analysis of the individual characteristics of the data of the subjects, grouped in this way, makes it possible to detect deviations indicating the presence of abnormalities or the formation of various pathological conditions, which can be useful for the early diagnosis of diseases.

Stepanyan I.V., Grokhovsky S.S., Kubryak O.V. Neuroclusterization method of stabilometric data. Neurocomputers. 2021. V. 23. № 3.  Р. 15−24. DOI: https://doi.org/10.18127/j19998554-202103-02 (in Russian).

1. Ivanova G.E. i dr. Formirovaniye konsensusa spetsialistov v primenenii stabilometrii i bioupravleniya po opornoy reaktsii. Vestnik vosstanovitelnoy meditsiny. 2019. № 1. S. 16–21.
2. Babanov N.D. i dr. Dinamika parametrov maloamplitudnykh dvizheniy ruk pri povtoryayushcheysya dvigatelno-kognitivnoy zadache. Rossiyskiy fiziologicheskiy zhurnal im. I.M. Sechenova. 2020. T. 106. № 11. S. 1370–1384.
3. Duarte M., Zatsiorsky V.M. Patterns of center of presure migration during prolonged unconstrained standing. Motor Control. 1999. V. 3.  № 1. P. 12–27.
4. Hansen C. et al. Center of pressure based segment inertial parameters validation. PloS one. 2017. V. 12. № 6. Article E0180011.
5. Stepanyan I.V., Mekler A. A. Chaotic Algorithms of Analysis of Cardiovascular Systems and Artificial Intelligence. International Conference of Artificial Intelligence, Medical Engineering, Education. Springer, Cham. 2019. P. 231–240.
6. Paillard T., Noé F. Techniques and methods for testing the postural function in healthy and pathological subjects. BioMed research international. 2015. V. 2015. Article ID 891390.
7. Fey A., Sommer D., Golz M. Comparison of Time and Spectral Domain Features on Postural Signals Utilizing Neural Networks. Proc 1st Int Workshop Biosignal Processing and Classification. 2005. P. 42–49.
8. Golz M. et al. Discriminance analysis of postural sway trajectories with neural networks. Proceedings of the 8th World Multi-Conference on Systemics, Cybernetics and Informatics, Orlando, Florida USA. 2004. V. 7. P. 151–155.
9. Peterka R.J. Postural control model interpretation of stabilogram diffusion analysis. Biological cybernetics. 2000. V. 82. № 4. P. 335–343.
10. Garkavenko V.V. et al. Modifications of the stabilogram during upright standing posture under conditions of inclines of the support surface. Neurophysiology. 2012. V. 44. №. 2. P. 131–137.
11. Tokita T. et al. Classification of stabilograms in healthy subjects using neural network. Equilibrium Research. 2001. V. 60. № 3. P. 181–187.
12. Tokita T. et al. Discrimination of Stabilograms by a Neural Network in Patients with Equilibrium Disturbances. Equilibrium Research. 1997. V. 56. № 6. P. 542–549.
13. Araujo E., Bentes G.E.F., Zangaro R. Body sway and global equilibrium condition of the elderly in quiet standing posture by using competitive neural networks. Applied Soft Computing. 2018. V. 69. P. 625–633.
14. Kohonen T. Self-organizing maps. Springer Science & Business Media. 2012. V. 30.
15. Sola J., Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Transactions on nuclear science. 1997. V. 44. № 3. P. 1464–1468.
16. Shkundin S., Stepanian I. Detecting dust occupational lung pathology by neural network algorithms for acoustical spirometry data recognition. 12th Internat. Symposium on Environmental Issues and Waste Management in Energy and Mineral Production (SWEMP 2010). Prague, Czech Republic. P. 494–505.