CO poisoning prediction method based on meteorological and atmospheric pollutant data

Abstract

The invention provides a CO poisoning prediction method based on meteorological and atmospheric pollutant data. The CO poisoning prediction method comprises the following steps: acquiring historical meteorological and atmospheric pollutant data and CO poisoning case number of a to-be-predicted region; dividing the CO poisoning case number into k levels; selecting significant correlation effectivefeatures by using parson correlation analysis and partial correlation analysis; constructing an ordered multi-classification Logistic regression model of the CO poisoning risk level y and a probability model corresponding to the regression model according to the selected effective feature set X; and obtaining and substituting meteorological and atmospheric pollutant data of a to-be-predicted region at the required prediction time into the probability model to calculate the probability Pj of each CO poisoning risk level, wherein the j value corresponding to the maximum value max (p) of the Pj is the predicted CO poisoning risk level. According to the CO poisoning prediction method based on meteorological and atmospheric pollutant data, the CO poisoning risk grade can be predicted, and the prediction of CO poisoning is more accurate and scientific due to the combination of meteorological factors and environmental protection factors.

Description

technical field [0001] The invention relates to a method for predicting CO poisoning, in particular to a method for predicting CO poisoning based on meteorological and atmospheric pollutant data. Background technique [0002] The Beijing Professional Meteorological Observatory used weather forecast factors and derived factors to build a non-occupational CO (carbon monoxide) poisoning prediction model in Beijing. 1418 samples of CO poisoning cases, corresponding to the local meteorological conditions, using the quasi-multiple regression index probability classification technology, established the CO poisoning index (4 grades) forecast and the corresponding risk level assessment model. The schema is designed as follows: In the formula, Y i is the regression fitting value of the meteorological index of CO poisoning, defined as the daily average number of CO poisoning cases per 10 million people; is the background harmonic value of CO poisoning person-times, X j is the pre...

AI Technical Summary

Problems solved by technology

The schema is designed as follows: In the formula, Y i is the regression fitting value of the meteorological index of CO poisoning, defined as the daily average number of CO poisoning cases per 10 million people; is the background harmonic value of CO poisoning person-times, X j is the predictor factor entering the equation, B j (i=0, 1, 2, ..., m) is the corresponding regression coefficient, m and n respectively identify the number of factors entering the equation and the maximum number of samples in the forecast year, but this forecasting model has its limitations: 1. The poisoning data only come from 16 emergency centers in the urban area of ​​Beijing. In fact, many poisoned patients went directly to the hospital without going through the emergency station. The research data may be significantly less than the actual data; 2. Only the weather forecast in this area is used Factors and derived factors are not used in the prediction of environmental protection factors. As we all know, many years ago, the smog in the northern region was severe, and the environmental protection conditions need to be improved. Therefore, it is not a comprehensive and multi-dimensional research.

Images