Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Multi-modal data classification method based on feature selection

A feature selection and data classification technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problem of not being able to effectively reveal the high-order correlation of multi-modal data features, so as to improve classification accuracy and eliminate noise and negative factors, the effect of low hardware requirements

Inactive Publication Date: 2019-02-19
XIAN UNIV OF POSTS & TELECOMM
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a multi-modal data classification method based on feature selection, which not only makes full use of multi-modal It can effectively identify the most closely related features from massive data sets, and finally achieve better classification results.

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 data classification method based on feature selection
  • Multi-modal data classification method based on feature selection
  • Multi-modal data classification method based on feature selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] In order to solve the above problems, the present invention provides a multi-modal classification method based on high-dimensional feature selection, including the following steps:

[0046] Step 1: Preprocess the images from the ADNI data set and the Office data set to obtain the data including training samples and test samples.

[0047] Specifically, the ADNI data set has a total of 103 subjects under three modal data (ie, MRI, PET, and CSF), including 51 AD patients and 52 healthy controls. The multi-modal information includes image features and non-image features. The category features of the image include: MRI images and PET images, and the non-image features include: CSF. Image processing of multi-modal data yields 103*189. For each subject, the MRI image contains 93-dimensional features, the PET image contains 93-dimensional features, and the biomarker CSF contains 3-dimensional features.

[0048] The images of the Office data set come from: Amazon (that is, images dow...

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 multimodal data classification method based on feature selection, The method comprises the following steps of: collecting and processing multimodal data, expanding and representing the data by nonlinear kernel explicit expansion, obtaining combined high-order disease features, quickly identifying key features in high-dimensional feature space by feature selection method, constructing ensemble learning model, and performing image classification. The method provided by the invention can fully utilize the data information in each mode, and improves the classification accuracy.

Description

Technical field [0001] The present invention belongs to the technical field of computer image processing, and more specifically, relates to a multimodal data classification method based on feature selection. Background technique [0002] With the rapid development of information technology, the number of digital images has increased rapidly. Image classification is one of the hot issues in the field of computer vision and image processing. The main purpose of image classification is to recognize images and distinguish different types of images. However, due to the huge differences in image quality and content, image features of multiple data types are generated. Therefore, how users can effectively find the same type of image in image data under different modalities has become a research hotspot. [0003] In the Internet era, a large amount of data exists in different modalities in people's daily life every day, such as images, videos, texts and so on. Due to the different statis...

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
CPCG06F18/285G06F18/24G06F18/214
Inventor 邓万宇刘丹陈琳
Owner XIAN UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com