Blood glucose measuring device, data processing method thereof and storage medium

Abstract

The invention provides a blood glucose measuring device, a data processing method thereof and a storage medium. The method comprises the steps of: S1, physiological parameters are collected, wherein the physiological parameters comprise pulse wave signals; S2, the pulse wave signals in the physiological parameters are preprocessed; S3, feature extraction on the preprocessed pulse wave signals areconducted to obtain extracted features; S4, by taking the extracted features as input features, feature screening based on a genetic algorithm is performed to obtain screened features; and S5, model training on the screened features is carried out to obtain an optimization model. The collected pulse wave signals are subjected to preprocessing and feature extraction, and then extracted features arescreened through the genetic algorithm, so that dimensionality of feature values needed to be calculated in the model training process can be effectively reduced, and operation expenditure and time expenditure are reduced; meanwhile, the algorithm is more powerfully integrated into embedded equipment, and has high estimation accuracy.

Description

technical field [0001] The invention relates to the technical field of non-invasive blood sugar detection, in particular to a blood sugar measuring device, a data processing method and a storage medium thereof. Background technique [0002] Diabetes is a metabolic disease characterized by chronically elevated blood sugar levels. The main symptoms are polyphagia, polydipsia, frequent urination and weight loss. Diabetes is a chronic disease that occurs when the pancreas does not produce enough insulin or when the body cannot effectively use the insulin it produces. [0003] Since diabetes has no obvious symptoms in the early stage, when it is discovered, it has often caused complications and caused irreversible damage to other organs. Relying on existing medical methods, diabetes cannot be completely cured. Therefore, whether it is the early screening of high-risk groups of diabetes or the diagnosis and treatment of diabetic patients, blood glucose concentration, as an impo...

AI Technical Summary

Problems solved by technology

The traditional linear correlation analysis (including multiple linear regression analysis MLR, principal component regression analysis PCR, partial least square method PLS) widely used in near-infrared spectral analysis methods is not ideal for the detection of non-invasive blood glucose; nonlinear correlation analysis such as artificial Neural network (ANN) and support vector machine (SVM) can achieve better results, but the training process requires too many input features, the operation process is complex and time-consuming, and if the input features are not suitable, the estimation results will be seriously affected the accuracy of

Images