On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions
Informacionnye Tehnologii · 13.03.2026 · 32 (3) · 163-168
DOI: 10.17587/it.32.163-168 ↗Kurz gefasst
Fachartikel in der Zeitschrift Informacionnye Tehnologii, online erschienen am 13.03.2026. Verfasst von M. R. Bogdanov und 4 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Bogdanov, M. R., Shakhmametova, G. R., Shaibakov, I. S., Ishakov, A. R., & Oskin, N. N. (2026). On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions. Informacionnye Tehnologii, 32(3), 163-168. https://doi.org/10.17587/it.32.163-168
Vancouver
Bogdanov MR, Shakhmametova GR, Shaibakov IS, Ishakov AR, Oskin NN. On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions. Informacionnye Tehnologii. 2026;32(3):163-168. doi:10.17587/it.32.163-168
BibTeX
@article{Bogdanov2026,
author = {Bogdanov, M. R. and Shakhmametova, G. R. and Shaibakov, I. S. and Ishakov, A. R. and Oskin, N. N.},
title = {On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions},
journal = {Informacionnye Tehnologii},
year = {2026},
volume = {32},
number = {3},
pages = {163--168},
doi = {10.17587/it.32.163-168}
}
EUVIMED