On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

The paper is devoted to the recognition of potentially dangerous physiological conditions. It is proposed to convert one-dimensional signals used in medical diagnostics into a video sequence. To recognize a video sequence, it is proposed to combine a convolutional and recurrent neural network. The effectiveness of multiclass classification of various physiological conditions is compared using a method combining recurrent and convolutional neural networks (accuracy metric is 0.98) with recurrent (0.53) and convolutional neural networks (0.41). The high efficiency of the proposed approach is shown.

Full Text

Restricted Access

About the authors

M. R. Bogdanov

Ufa State University of Science and Technology; M. Akmullah named after Bashkir State Pedagogical University

Author for correspondence.
Email: bogdanov_marat@mail.ru

Cand. of Biol. Sc., Associate Professor

Russian Federation, Ufa, 450000; Ufa, 450000

G. R. Shakhmametova

Ufa State University of Science and Technology

Email: shakhgouzel@mail.ru

Dr. of Tech. Sc., Professor, Head of Department

Russian Federation, Ufa, 450000

I. S. Shaibakov

Republican Clinical Hospital No. 2

Email: sch1972@mail.ru

Cand. of Medic. Sc., Head of Department

Russian Federation, Ufa, 450000

A. R. Ishakov

M. Akmullah named after Bashkir State Pedagogical University

Email: intellab@mail.ru

Cand. of Phys. and Math. Sc., Associate Professor

Russian Federation, Ufa, 450000

N. N. Oskin

Siberian Telemedicine Company

Email: nonik2@mail.ru

CEO

Russian Federation, Penza, 440000

References

  1. Kulkarni V., Talele K. Video Analytics for Face Detection and Tracking, 2020 2nd International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida, India, 2020, pp. 962—965, doi: 10.1109/ICACCCN51052.2020.9362900.
  2. Shah A., Kudalkar D., Shah J., Katre N. Proposed Methodology for Real-Time Pistol Detection System, 2023 International Conference on Advanced Computing Technologies and Applications (ICACTA), 2023, pp. 1—6.
  3. Kulbacki M., Segen J., Chaczko, Z., Rozenblit J. W., Kulbacki M., Klempous R., Wojciechowski K. Intelligent Video Analytics for Human Action Recognition: The State of Knowledge, Sensors, 2023, vol. 23, p. 4258, doi: 10.3390/s23094258.
  4. Sreenu G., Durai S. Intelligent video surveillance: a review through deep learning techniques for crowd analysis, J Big Data, 2019, vol. 6, no. 48, doi: 10.1186/s40537-019-0212-5.
  5. Nallola S. R., Ayyasamy V. Twenty-five years of real-time surveillance video analytics: a bibliometric review, Multimed Tools Appl, 2024, vol. 83, pp. 69273—69306, doi: 10.1007/s11042-024-18325-6.
  6. Bhuiyan M. R., Abdullah J., Hashim N. Video analytics using deep learning for crowd analysis: a review, Multimed Tools Appl, 2022, vol. 81, pp. 27895—27922, doi: 10.1007/s11042-022-12833-z.
  7. Mao M, Lee А, Hong M. Deep Learning Innovations in Video Classification: А Survey on Techniques and Dataset Evaluations, Electronics, 2024, vol. 13, no. 2732, doi: 10.3390/electronics13142732.
  8. Wang J., Tsao R., Wang X., Wang X., Feng F., Tian Sh., Poria S. Action-guided prompt tuning for video grounding, Information Fusion, 2025, vol. 113, p. 102577, doi: 10.1016/j.inffus.2024.102577.
  9. Xu H., Ling Z., Yuan X., Wang Y. А video object detector with Spatio-Temporal Attention Module for micro UAV detection, Neurocomputing, 2024, vol. 597, doi: 10.1016/j.neucom.2024.127973.
  10. Panpan G., Hanxu S., Gang C., Ruiquan W., Minggang L. Visual Question Answering for Intelligent Interaction, Mobile Information Systems, 2022, doi: 10.1155/2022/4232968.
  11. Lei Z., Zhang G., Wu L. А Multi-level Mesh Mutual Attention Model for Visual Question Answering. Data Sci. Eng., 2022, vol. 7, pp. 339—353, doi: 10.1007/s41019-022-00200-9.
  12. Kovalev А. K., Shaban M., Osipov E., Panov А. I. Vector Semiotic Model for Visual Question Answering. Cognitive Systems Research, 2022, vol. 71, pp. 52—63.
  13. Haoran W., Zhang Y., Xiaosheng Y. An Overview of Image Caption Generation Methods, Computational Intelligence and Neuroscience, 2020, pp. 1—13, doi: 10.1155/2020/3062706.
  14. Velleangiri V., Balasubramaniam S., Sennan S., Ramasubbareddy S. А Deep Structured Model for Video Captioning, International Journal of Gaming and Computer-Mediated Simulations, 2020, vol. 12, pp. 44—56, doi: 10.4018/IJGCMS.2020040103.
  15. Shin A., Ohnishi K., Harada T. Beyond caption to narrative: Video captioning with multiple sentences, 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, 2016, pp. 3364—3368, doi: 10.1109/ICIP.2016.7532983.
  16. Bohara K., Shakya А., Debb Pande В. Fine-Tuning of RoBERTa for Document Classification of ArXiv Dataset, Mobile Computing and Sustainable Informatics. Lecture Notes on Data Engineering and Communications Technologies, 2023, vol. 166, Springer, Singapore, doi: 10.1007/978-981-99-0835-6_18.
  17. You L., Han F., Peng J., Jin H., Claramunt C. ASK-RoBERTa: А pretraining model for aspect-based sentiment classification via sentiment knowledge mining, Knowledge-Based Systems, 2022, vol. 253, doi: 10.1016/j.knosys.2022.109511.
  18. Forest S., Quinton J. C., Lefort M. А Dynamic Neural Field Model of Multimodal Merging: Application to the Ventriloquist Effect, Neural Comput., 2022, Jul 14, vol. 34, no. 8, pp. 1701—1726, doi: 10.1162/neco_a_01509. PMID: 35798331.
  19. Chen L., Chen Y., Ouyang Z. Boosting adversarial transferability in vision-language models via multimodal feature heterogeneity, Sci Rep, 2025, vol. 15, no. 7366, doi: 10.1038/s41598-025-91802-6.
  20. Chen X., Xie Н., Tao X. Artificial intelligence and multimodal data fusion for smart healthcare: topic modeling and bibliometrics. Artif Intell Rev, 2024, vol. 57, no. 91, doi: 10.1007/s10462-024-10712-7.
  21. Zhang B., Song Z., Huang X., Qian J., Cai C. А practical object detection-based multiscale attention strategy for person reidentification. Electronic Research Archive, 2024, vol. 32, no. 12, pp. 6772—6791, doi: 10.3934/era.2024317.
  22. Ertugrul В. Improved Object Re-Identification via More Efficient Embeddings," Turkish Journal of Electrical Engineering and Computer Sciences, 2023, vol. 31, no. 2, art. 4, doi: 10.55730/1300-0632.3984, available at: https://journals.tubitak.gov.tr/elektrik/vol31/iss2/4.
  23. Berdugo G., Soceanu O., Moshe Y., Rudoy D., Dvir I. Object reidentification in real world scenarios across multiple non-overlapping cameras, 2010 18th European Signal Processing Conference, Aalborg, Denmark, 2010, pp. 1806—1810.
  24. Ye M., Chen S., Li C. Transformer for Object Re-identification: А Survey. Int J Comput Vis, 2025, vol. 133, pp. 2410—2440, doi: 10.1007/s11263-024-02284-4.

Supplementary files

Supplementary Files
Action
1. JATS XML
Download
2. Fig. 1. One-second fragment of an ECG of a normal sinus rhythm (below is an ECG graph with an axis of 0-500 ms or a similar scale, the color bar at the top is probably the color scale of the amplitude, and the marks 0, 5, 10, 15, 20, 25)

Download (11KB)
Indexing metadata
3. Fig. 2. An image obtained by converting a one-dimensional array containing 784 elements into a two-dimensional array (28x28)

Download (12KB)
Indexing metadata

Copyright (c) 2026 Informacionnye Tehnologii


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № 77 - 15565 от 02 июня 2003 г.