A Symptom Correlation Early Warning Method Based on Exponentially Weighted Moving Average

An exponential weighting and moving average technology, applied in the field of big data analysis, to achieve the effect of accurate correlation coefficient and good early warning effect

Active Publication Date: 2022-02-08
KUNMING UNIV OF SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

There is no mathematical basis for symptom correlation analysis, combined with reality, the number of symptoms will have a temporal impact, but traditional correlation analysis does not add these covariates

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Symptom Correlation Early Warning Method Based on Exponentially Weighted Moving Average
  • A Symptom Correlation Early Warning Method Based on Exponentially Weighted Moving Average
  • A Symptom Correlation Early Warning Method Based on Exponentially Weighted Moving Average

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] Embodiment 1: as Figure 1-3 Shown, a kind of symptom correlation warning method based on exponential weighted moving average, described specific method steps are as follows:

[0029] Step 1: Obtain the database established by the symptom table of a patient in a certain area for three months. The symptom incidence information table includes: number, visit time, symptom type and the number of symptoms corresponding to the symptom;

[0030] Step2: Symptom data preprocessing: Screen the collected symptom type information fields, compare the symptom type information fields with the symptoms required for research, and eliminate symptom data irrelevant to the research and useless symptom data that cannot be identified. The symptom incidence information collected in the database is sorted out to get Table 1: Symptom incidence information table:

[0031]

[0032] Table 1: Symptom morbidity information table

[0033] Step3: Calculate exponentially weighted moving average of...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a symptom correlation early warning algorithm based on exponentially weighted moving average, which belongs to the field of big data analysis. Specifically, the present invention establishes a symptom incidence database, screens the collected symptom information, and eliminates symptoms that are not included in it according to the requirements of well-known symptoms. The traditional correlation algorithm only calculates the basic average value of the number of symptom onset, ignoring the influence of the symptom data before and after time. The symptom correlation early warning algorithm based on exponentially weighted moving average proposed in this paper intends to use the mean value obtained after exponential weighting as the basis of the correlation algorithm, so that the historical retrospective data and current data are combined to make the obtained correlation coefficient It is more accurate, and then compare the data according to the obtained correlation coefficient to find out the abnormality of the data, and obtain the time point of the early warning and the source of the early warning data, so as to achieve a better early warning effect.

Description

technical field [0001] The invention relates to a symptom correlation early warning method based on an exponentially weighted moving average, which belongs to the field of big data analysis. Background technique [0002] With the development of society, various infectious diseases are ravaging the human body, bringing great pain to countless families, and with the progress of society, the level and speed of personnel mobility are gradually increasing, which also makes infectious diseases spread among people. The spread of infectious diseases has been intensified, so many departments have implemented plans for early warning of infectious disease outbreaks. There is no mathematical basis for the symptom correlation analysis, combined with reality, the number of symptoms will have a temporal impact, but the traditional correlation analysis does not add these covariates. Contents of the invention [0003] The technical problem to be solved by the present invention is to provi...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G16H50/80
CPCG16H50/80
Inventor 粘冬晓杜庆治龙华邵玉斌
Owner KUNMING UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products