Informacionnye TehnologiiInformacionnye TehnologiiИнформационные технологии1684-6400New Technologies Publishing House70416010.17587/it.32.163-168Information technologies in biomedical systemsИнформационные технологии в биомедицинских системахReview ArticleOn the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditionsО возможности применения гибридного подхода при распознавании потенциально опасных физиологических состоянийBogdanovM. R.БогдановМ. Р.
Russian Federation

Cand. of Biol. Sc., Associate Professor

канд. биол. наук, доц.

bogdanov_marat@mail.ruShakhmametovaG. R.ШахмаметоваГ. Р.
Russian Federation

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

д-р техн. наук, проф., зав. кафедрой

shakhgouzel@mail.ruShaibakovI. S.ШайбаковИ. Ш.
Russian Federation

Cand. of Medic. Sc., Head of Department

канд. мед. наук, зав. отделением

sch1972@mail.ruIshakovA. R.ИсхаковА. Р.
Russian Federation

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

канд. физ.-мат. наук, доц. Института физики, математики, цифровых и нанотехнологий

intellab@mail.ruOskinN. N.ОськинН. Н.
Russian Federation

CEO

директор

nonik2@mail.ruUfa State University of Science and TechnologyУфимский университет науки и технологийM. Akmullah named after Bashkir State Pedagogical UniversityБашкирский государственный педагогический универитет им. М. АкмуллыRepublican Clinical Hospital No. 2Республиканская клиническая больница № 2Siberian Telemedicine CompanyСибирская телеметрическая компания13032026323Informacionnye TehnologiiИнформационные технологии1631681203202612032026Copyright ©; 2026, Informacionnye TehnologiiCopyright ©; 2026, Информационные технологии2026Informacionnye TehnologiiИнформационные технологииhttps://journals.eco-vector.com/1684-6400/article/view/704160

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.

Исследуется проблема распознавания потенциально опасных физиологических состояний. Предлагается преобразовывать в видеоряд одномерные сигналы, используемые в медицинской диагностике. Для распознавания видеоряда предлагается сочетать сверточную и рекуррентную нейронные сети. Проведено сравнение эффективности многоклассовой классификации различных физиологических состояний с помощью метода на основе использования совокупности сверточной и рекуррентной нейронных сетей, а также методов на основе использования рекуррентной сети и на основе использования сверточной нейронной сети. Показана высокая эффективность предложенного подхода.

Machine learningdigital signal processingvideo analyticsмашинное обучениецифровая обработка сигналоввидеоаналитикаThe work was carried out with the financial support of the Ministry of Science and Higher Education of the Russian Federation within the framework of the main part of the state task to higher educational institutions no. FEUE-2020-0007 and RNF 22-19-00471 decision support system for prevention and treatment of bronchopulmonary diseases and assessment of the risks of diseases and complications of their treatment in the tasks of personalized medicine based on data analysis methods and artificial intelligence.Исследование проведено при финансовой поддержке Министерства науки и высшего образования Российской Федерации в рамках основной части государственного задания для высших учебных заведений № ФЭУЭ-2020-0007 и РНФ 22-19-00471 "Система поддержки принятия решений по профилактике и лечению бронхолегочных заболеваний и оценке рисков заболеваний и осложнений их лечения в задачах персонализированной медицины на основе методов анализа данных и искусственного интеллекта".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.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. P. 962—965. DOI: 10.1109/ICACCCN51052.2020.9362900.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.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. P.1—6.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.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/s23094258Sreenu 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.Sreenu G., Durai S. Intelligent video surveillance: a review through deep learning techniques for crowd analysis // J Big Data. 2019. Vol. 6, N. 48. DOI: 10.1186/s40537-019-0212-5Nallola 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.Nallola S. R., Ayyasamy V. Twenty-five years of real-time surveillance video analytics: a bibliometric review // Multimed Tools Appl, 2024. Vol. 83. P. 69273—69306. DOI: 10.1007/s11042-024-18325-6Bhuiyan 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.Bhuiyan M. R., Abdullah J., Hashim N. Video analytics using deep learning for crowd analysis: a review // Multimed Tools Appl, 2022. Vol. 81. P. 27895—27922. DOI: 10.1007/s11042-022-12833-zMao 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.Mao M, Lee А, Hong M. Deep Learning Innovations in Video Classification: А Survey on Techniques and Dataset Evaluations // Electronics. 2024. Vol. 13, N. 2732. DOI: 10.3390/electronics13142732Wang 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.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.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.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.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.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.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.Lei Z., Zhang G., Wu L. А Multi-level Mesh Mutual Attention Model for Visual Question Answering // Data Sci. Eng. 2022. Vol. 7. P. 339—353. DOI: 10.1007/s41019-022-00200-9Kovalev 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.Kovalev A. K., Shaban M., Osipov E., Panov А. I. Vector Semiotic Model for Visual Question Answering // Cognitive Systems Research. 2022. Vol. 71. P. 52—63.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.Haoran W., Zhang Y., Xiaosheng Y. An Overview of Image Caption Generation Methods // Computational Intelligence and Neuroscience. 2020. P. 1—13. DOI: 10.1155/2020/3062706.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.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. P. 44—56. DOI: 10.4018/IJGCMS.2020040103.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.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. P. 3364—3368. DOI: 10.1109/ICIP.2016.7532983.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.Bohara K., Shakya A., 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_18You 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.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.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.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, N. 8. P. 1701—1726. DOI: 10.1162/neco_a_01509. PMID: 35798331.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.Chen L., Chen Y., Ouyang Z. Boosting adversarial transferability in vision-language models via multimodal feature heterogeneity // Sci Rep. 2025. Vol. 15, N. 7366. DOI: 10.1038/s41598-025-91802-6Chen 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.Chen X., Xie H., Tao X. Artificial intelligence and multimodal data fusion for smart healthcare: topic modeling and bibliometrics // Artif Intell Rev. 2024. Vol. 57, N. 91. DOI: 10.1007/s10462-024-10712-7Zhang 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.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, N. 12. P. 6772—6791. DOI: 10.3934/era.2024317Ertugrul 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.Ertugrul В. Improved Object Re-Identification via More Efficient Embeddings // Turkish Journal of Electrical Engineering and Computer Sciences. 2023. Vol. 31, N. 2. Article 4. DOI: 10.55730/1300-0632.3984. URL: https://journals.tubitak.gov.tr/elektrik/vol31/iss2/4Berdugo 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.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. P. 1806—1810.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.Ye M., Chen S., Li C. Transformer for Object Re-identification: А Survey // Int J Comput Vis. 2025. Vol. 133. P. 2410—2440. DOI: 10.1007/s11263-024-02284-4