SVM-based resident health level prediction method

Abstract

The invention relates to an SVM (Support Vector Machine)-based resident health level prediction method. The method comprises the following steps: step 1, determining multi-level indexes for reflectingthe health of all residents; step 2, respectively processing the first-level indexes and the third-level indexes to obtain corresponding scores; step 3, establishing an SVM model, performing dimension reduction processing on the three-level indexes by utilizing a principal component analysis method, then selecting part of numerical values as input characteristic values, taking scores corresponding to the first-level indexes as output characteristic values, collecting actual data corresponding to the indexes, and dividing the actual data into training data and test data; step 4, performing subsequent processing on the SVM model to obtain a trained model; step 5, inputting the trained model into a prediction function of the LIBSVM to obtain a prediction value of the test sample; and step 6,reversely normalizing the predicted value of the test sample, and drawing a picture to compare and analyze the true value and the predicted value of the test sample, so as to obtain a corresponding final resident health level prediction result. Compared with the prior art, the method has the advantages of accurate prediction, wide evaluation range and the like.

Description

technical field [0001] The invention relates to a method for evaluating the health level of residents, in particular to a method for predicting the health level of residents based on SVM. Background technique [0002] Nowadays, people are in a period of overnutrition, and chronic non-communicable diseases are not only increasing, but also tend to be younger. Industrialization and high-sugar and high-calorie foods are sweeping the country, and environmental pollution is also an important cause of other chronic diseases. Due to the use of various pesticides, there is also a large amount of pesticide residue pollution in food, which affects human health. In addition, air pollution is also an important cause of chronic respiratory diseases. [0003] Considering that social public health services, medical security and environmental conditions are the main factors affecting the health of residents, how to conduct continuous and dynamic quantitative assessment of the health of al...

AI Technical Summary

Problems solved by technology

Although these methods can better explain the nonlinear relationship of data, they still have great limitations for the

Images