Supercharge Your Innovation With Domain-Expert AI Agents!

Disease intelligent diagnosis technique based on neural network and confidence interval

A confidence interval, intelligent diagnosis technology, applied in the field of machine learning, can solve problems such as inability to classify data

Inactive Publication Date: 2019-07-12
HUNAN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Most machine learning algorithms are often unable to correctly classify data when diagnosing a single disease when the positive and negative sample attributes of the data are similar

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
  • Disease intelligent diagnosis technique based on neural network and confidence interval
  • Disease intelligent diagnosis technique based on neural network and confidence interval
  • Disease intelligent diagnosis technique based on neural network and confidence interval

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Such as figure 1 As shown, this embodiment includes the following steps:

[0020] Step 1: Preprocess and normalize the data. The processing method is: clean the data and convert the data into numerical values. The conversion formula used for data normalization is: where x max is the maximum value of the sample data, x min is the minimum value of the sample data, x is the original sample data, x * is the new normalized data.

[0021] Step 2: Perform PCA dimension reduction operation on the normalized data, the processing method is: center all samples and calculate the covariance matrix XX T And do eigenvalue decomposition, and then take the eigenvector w corresponding to the largest d′ eigenvalues 1 ,w 2 ,...,w d′ . The dimension d' of the low-dimensional space after dimension reduction is usually specified by the user in advance, and the present invention reduces the 32-dimensional attributes of the original data set to 10 dimensions.

[0022] Step 3: Use the ...

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 provides a disease intelligent diagnosis technique based on a neural network and a confidence interval. Firstly, preprocessing and normalization operation are performed on a training sample. Secondly, principal component analysis (PCA) is used for reducing a dimension number for obtaining an optimal characteristic. Then, a BP neural network is used for training the characteristic forobtaining a diagnosis model. Before the diagnosis model is used for predicting a predicating sample, a confidence interval of training sample output value distribution is obtained. Then a final predicting result is determined according to the confidence interval to which the predicted value belongs. According to the disease intelligent diagnosis technique, a BP neural network algorithm is combined with the confidence interval. Compared with a traditional detecting algorithm, the disease intelligent diagnosis technique has advantages of remarkably improving detection rate of malignant tumor, and realizing low false detection rate.

Description

technical field [0001] The invention relates to a technology in the field of machine learning, in particular to an intelligent disease diagnosis technology based on neural networks and confidence intervals. Background technique [0002] When using traditional methods to diagnose diseases, the diagnostic accuracy varies from person to person, and is greatly affected by subjective factors, and the overall medical level in different regions is uneven. [0003] The application of machine learning in the medical field has great potential. It can help doctors and researchers discover patterns from data sets, thereby improving the efficiency of medical diagnosis and improving the quality of medical services. [0004] At present, machine learning is developing rapidly in the field of medical diagnosis, which has improved the diagnostic efficiency of medical staff and improved the overall medical diagnosis level to a certain extent. [0005] Most machine learning algorithms often fa...

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): G16H50/20
CPCG16H50/20
Inventor 王森林周军海秦拯
Owner HUNAN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com