Physiological state prediction method, computer device and storage medium

Abstract

The invention provides a physiological state prediction method, which comprises the following steps that: collecting n samples, wherein each sample in the n samples comprises N parts of physiological signal data; projecting the N parts of physiological signal data included in each sample to a space of a B-spline function, and estimating a track of each sample; estimating a slope variance function based on the estimated trajectory of each of the n samples; estimating a characteristic function based on the estimated oblique variance function, and obtaining an estimated value of a principal component corresponding to each sample based on the estimated characteristic function; and based on the estimated value of the principal component corresponding to each sample, utilizing a preset prediction model to predict the physiological state corresponding to each sample. The invention further provides a computer device and a storage medium for implementing the physiological state prediction method. The method can improve the prediction accuracy while simplifying the calculation burden.

Description

technical field [0001] The invention relates to the technical field of physiological state monitoring, in particular to a physiological state prediction method, a computer device and a storage medium. Background technique [0002] Traditional physiological state prediction methods usually require tens of thousands of measurements of physiological signals such as brain voltage. However, due to the often small number of experimental subjects (only a few hundred in most cases), traditional physiological state prediction fails. In addition, the collected physiological signal data may also be affected by many factors, such as the thickness of the scalp, the volume of EEG paste, etc., so that the collected physiological signal contains huge noise, while obtaining noise-free physiological signals such as EEG Signals are very difficult. [0003] Traditional physiological state prediction methods usually include manually extracting physiological features (such as frequency, spectra...

AI Technical Summary

Problems solved by technology

In addition, in the process of implementing the present invention, the inventor found that using a recurrent neural network (RNN) to achieve prediction requires a large sample size, which is inconsistent with the actual situation of physiological signal data collection such as EEG.

Images