A METHOD FOR CLASSIFYING ECG SIGNALS WITH DIFFERENT POSSIBLE STATES ON A MULTILAYER PERCEPTRON
To automatically determine the state of the cardiovascular system based on the recorded ECG signals, an artificial neural network is trained to classify signals into various possible states. At the same time, the parameters of heart rate variability (HRV) were extracted from the ECG signals and used as input functions for the neural network. HRV is the fluctuation in the time intervals between adjacent heartbeats. For this, the architecture of a neural network based on a multilayer perceptron and a method for obtaining the necessary parameters in the learning process have been developed, and the classification efficiency has been checked and evaluated
Сведения
- Опубликовано
- 2020 · Т. 2020, № 4, С. 71-78
- Язык
- Английский
- ISSN
- 2181-0400 · 2181-1180
- Издатель
- Tashkent State Technical University named after Islam Karimov