Test data verification method based on ensemble learning and decision threshold change

A technology of integrated learning and data verification, applied in the field of big data

Pending Publication Date: 2020-10-30
THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide an assay data verification method based on integrated learning and changing the decision threshold, which solves the technical problem of effectively verifying the classification accuracy of assay data

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
  • Test data verification method based on ensemble learning and decision threshold change
  • Test data verification method based on ensemble learning and decision threshold change

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] Such as Figure 1-Figure 2 An assay data verification method based on integrated learning and changing the decision threshold is shown, including the following steps:

[0032] Step 1: Establish several remote terminals and central server, and all remote terminals communicate with the central server through the Internet;

[0033] Establish a data acquisition module, a data cleaning module and a classification module in the remote terminal;

[0034] Establish a comparison data set and a multi-index evaluation module in the central server;

[0035] Step 2: The remote terminal obtains the body fluid test data through the data acquisition module, establishes the body fluid data set, and cleans the data in the body fluid data set in the data cleaning module, including the following steps:

[0036] Step S1: Process the missing values ​​and abnormal values ​​in the body fluid test data, eliminate abnormal data, and obtain the preprocessed data set;

[0037] Step S2: Convert ...

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 discloses a test data verification method based on ensemble learning and decision threshold change, and belongs to the field of big data; according to the invention, the clustering algorithm, the thought of ensemble learning and the method of changing the decision threshold are combined together to obtain a new strong classifier; the method also includes learning based on the existing test data to obtain a classification model; pre-classifying the new test data, thus increasing its accuracy, and solving the technical problem of effectively verifying the classification accuracy ofthe test data; according to the invention, four different single classifiers are combined, higher classification capacity is achieved, and for the problem of data imbalance in a disease data set, theclassification accuracy is improved by changing the decision threshold value in the final decision stage; the classification result is evaluated from multiple angles through multiple indexes, and theaccuracy of the classification result is better understood.

Description

technical field [0001] The invention belongs to the technical field of big data, and relates to an assay data verification method based on integrated learning and changing a decision threshold. Background technique [0002] The accuracy of traditional laboratory data depends on the experience of doctors and the external laboratory environment, and the interference of the external environment will also have a negative impact on the laboratory data. With the continuous development of machine learning, in recent years, some scholars have begun to study the accuracy verification method of laboratory data based on machine learning, but the types of data are various, and more and more complex and diverse. The verification of data can no longer guarantee the accuracy of its classification. Contents of the invention [0003] The purpose of the present invention is to provide an assay data verification method based on integrated learning and changing the decision threshold, which ...

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 Applications(China)
IPC IPC(8): G06F16/215G06F16/2458G06K9/62G06N20/20
CPCG06F16/215G06F16/2465G06N20/20G06F18/23211
Inventor 赵杰翟运开叶明石金铭陈昊天卢耀恩张旭李明原
Owner THE FIRST AFFILIATED HOSPITAL OF ZHENGZHOU UNIV
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