Unlock instant, AI-driven research and patent intelligence for your innovation.

Diabetes detection method based on manifold regularization kernel extreme learning machine

A nuclear extreme learning machine and diabetes technology, applied in the field of bioinformatics, can solve the problems of high labor cost and long time for medical personnel, and achieve the effect of reducing knowledge requirements, low cost, and facilitating rapid technology upgrades

Pending Publication Date: 2019-12-20
XIANGTAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method solves the problem in the prior art that relies on the existing computer technology, such as the BP neural network algorithm, for a long time, while the traditional diabetes detection requires relatively high labor costs for medical personnel

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
  • Diabetes detection method based on manifold regularization kernel extreme learning machine
  • Diabetes detection method based on manifold regularization kernel extreme learning machine
  • Diabetes detection method based on manifold regularization kernel extreme learning machine

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0007] Specific implementation method: what this method adopts is the manifold regularization kernel extreme learning machine algorithm. The algorithm is actually a 3-layer neural network, which is improved based on the extreme learning machine algorithm. The structure of the extreme learning machine is as follows figure 1 As shown, the first layer is the input layer, the second layer is the hidden layer, and the third layer is the output layer.

[0008] Given N training samples (x j ,t j ), where x j =[x j1 ,x j2 ,...,x jn ] T ∈ R n is the input data, t j =[t j1 ,t j2 ,...,t jm ] T ∈ R m Output the value for the target. For an ELM network model with L hidden layer nodes, it can be expressed as

[0009]

[0010] where g(x) is the activation function, w i =[w i1 ,w i2 ,...,w in ] T is the input weight of the i-th hidden layer unit, b i is the bias of the i-th hidden layer unit, β i =[β i1 ,β i2 ,...,β im ] T is the output weight of the i-th hidden ...

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 belongs to the technical field of bioinformatics and relates to a novel diabetes detection method. An object of the present invention is to provide a method capable of detecting diabetesin a short time and at a low cost. By means of computer technology, the invention solves the long running time of a feedforward neural network algorithm in the prior art and the relatively high costof traditional diabetes detection. The method is an algorithm based on manifold regularization kernel extreme learning machine, and is obtained by improving an extreme learning machine algorithm. By adding a manifold regularization term and introducing a Laplacian matrix, the method enhances the fitting ability of the kernel extreme learning machine and obtains better results than an existing technical means.

Description

technical field [0001] The invention belongs to the technical field of biological information and relates to a novel diabetes detection method. Background technique [0002] In the current society, due to the improvement of living standards, a large number of elderly people and even middle-aged and young people have a large number of diabetic patients. Traditional hospitals rely on existing technologies, and it is difficult to meet the rapid detection of diabetes required by the majority of patient groups. At present, the problem of diabetes detection is a common technical problem in the medical field. Manual identification of diabetes requires a good medical knowledge reserve of medical personnel, but there is still the problem of inaccurate manual detection, which requires a large number of knowledgeable and experienced medical personnel. Relying on computers to detect diabetes, such as traditional neural network algorithms, takes a certain amount of time, which is not co...

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
IPC IPC(8): G16H50/20G06N3/04
CPCG16H50/20G06N3/044
Inventor 何春梅徐繁华康红宇刘亚琦李肖瑞
Owner XIANGTAN UNIV