Obesity prediction system based on BP neural network

Abstract

The invention discloses an obesity prediction system based on a BP neural network, and the system comprises a data collection module which collects the fat thickness of the biceps brachii muscle and abdomen of a testee through a diasonograph, and obtains the testee physique information corresponding to the fat thickness; an influence factor screening module which constructs a BP neural network, takes a training set and a reference set constructed by the fat thickness and the testee physique information as input, obtains the weight of each index in the training set and the reference set by adopting a back propagation method, and screens the indexes to obtain obesity influence factors; and a model construction and prediction module which carries out weighted reconstruction on the obesity influence factors, constructs a fat thickness prediction model, carries out fat thickness prediction on the obtained to-be-measured data, and obtains an obesity prediction result according to comparisonof a fat thickness prediction value and a fat thickness threshold. The relationship between the indexes and obesity is clearly indicated, the influence degree of each influence factor on the prediction result can be obtained, and the prediction accuracy is improved.

Description

technical field [0001] The disclosure relates to the technical field of medical data processing, in particular to an obesity prediction system based on a BP neural network. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Obesity itself is not only an independent chronic disease, but also an important risk factor for other chronic diseases such as cardiovascular and cerebrovascular diseases, tumors, and diabetes. The risk assessment of obesity in the population is carried out, and the risk factors related to obesity are quantitatively analyzed by multi-factor methods. Help individuals understand the risk of obesity so as to prevent and control the occurrence of obesity; however, the inventors found that using traditional statistical methods to study the relationship between various factors and body weight can only obtain a vague result, an...

AI Technical Summary

Problems solved by technology

[0003] Obesity itself is not only an independent chronic disease, but also an important risk factor for other chronic diseases such as cardiovascular and cerebrovascular diseases, tumors, and diabetes. The risk assessment of obesity in the population is carried out, and the risk factors related to obesity are quantitatively analyzed by multi-factor methods. Help individuals understand the risk of obesity so as to prevent and control the occurrence of obesity; however, the inventors found that using traditional statistical methods to study the relationship between various factors and body weight can only get a vague result, and cannot clearly show that each There is a direct relationship between factors and obesity, and there are many factors that affect obesity. If only one factor is analyzed separately, it has certain limitations. In multi-factor analysis, the factors that affect obesity and each The degree of influence of the impact factor on the forecast results is beyond the reach of the existing forecast models

Images