Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multi-modal feature selection and classification method based on hypergraph

A feature selection and classification method technology, applied in the field of neuroimaging and computer science, can solve the problems of only considering the paired relationship of samples, ignoring the high-order relationship of samples, etc., and achieve the effect of reducing information loss

Inactive Publication Date: 2016-12-07
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current feature selection algorithms only consider the pairwise relationship between samples, while ignoring the high-order relationship between samples.

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
  • Multi-modal feature selection and classification method based on hypergraph
  • Multi-modal feature selection and classification method based on hypergraph
  • Multi-modal feature selection and classification method based on hypergraph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0032] Such as figure 1 As shown, the specific implementation process includes five steps:

[0033] The first step is to construct a hypergraph. First, choose a sample in the brain image, and calculate the Euclidean distance between the sample and other samples; then sort the calculated Euclidean distances, and select the k samples with the closest Euclidean distance; The k samples of are connected into a hyperedge; for all other samples, similar processing is done. After the hypergraph is constructed, the corresponding correlation matrix, degree of vertices, degree of hyperedges and Laplacian matrix are calculated.

[0034] The second step is feature selection. Bring the calculated Laplacian matrix into the objective formula of (4) for optimization solution, and APG algorithm can be used for solution. The sparsity of the final weight matrix W is distributed in rows. The two columns w in the W matrix 1 ,w 2 Corresponding to the weight matrices of the two modes respectiv...

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 multi-modal feature selection and classification method based on a hypergraph. The hypergraph can be used for effectively carrying out modeling on the high-order information of data. In the method disclosed by the invention, firstly, the hypergraph is independently constructed for the sample of each modal, and the Lapras matrix of the hypergraph is calculated; then, each group of modals is taken as one group of tasks, and a 12,1 norm is used for carrying out feature selection to guarantee that the characteristics of the same cerebral region of different modals can be selected. In addition, a hypergraph regularization term is used for describing high-order information between data samples so as to fully utilize a distribution prior in each group of modal data. Finally, a multi-core support vector machine is used for carrying out fusion classification on selected characteristics. By use of the method, the feature selection and classification can be effectively carried out.

Description

technical field [0001] The invention discloses a hypergraph-based multimodal feature selection and classification method. The invention relates to neuroimaging and computer science, and aims to reduce the dimension of high-dimensional features, select more discriminative features, and then classify . Background technique [0002] With the development and progress of neuroimaging technology, more and more researchers are studying the brain based on neuroimaging data. For example, structural magnetic resonance imaging (MRI) can display the structure of the brain; positron emission tomography (PET) can display the metabolism of the brain and so on. Generally speaking, the feature dimension of neuroimaging is relatively large, which will increase the complexity and computational complexity of the model when used to train the model. And in neuroimaging, the number of samples is relatively small, which is a typical "small sample" problem, which requires us to reduce dimensionali...

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): G06K9/62
CPCG06F18/2411
Inventor 张道强彭瑶祖辰
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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
Eureka Blog
Learn More
PatSnap group products