On the possibility of using a hybrid approach in the recognition of potentially dangerous physiological conditions
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.
Fields of Study & Subjects
ECG Monitoring and Analysis
Non-Invasive Vital Sign Monitoring
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- INFORMACIONNYE TEHNOLOGII
- Volume
- 32
- Issue
- 3
- Pages
- 163–168
- Publication date
- 13 March 2026
- Language
- EN