A multi-classifier fusion method based on PCA dimension reduction

A multi-classifier fusion and principal component technology, which is applied in the direction of instruments, character and pattern recognition, computer components, etc., can solve the problem of multi-dimensional feature space of user mouse behavior, achieve shortened modeling time, good experimental effect, The effect of high accuracy

Active Publication Date: 2019-03-08
XIAN UNIV OF TECH
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a multi-classifier fusion method based on PCA dimensionality reduction, which solves the problem that t

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
  • A multi-classifier fusion method based on PCA dimension reduction
  • A multi-classifier fusion method based on PCA dimension reduction
  • A multi-classifier fusion method based on PCA dimension reduction

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0032] The present invention will be described in detail below with reference to the drawings and specific embodiments.

[0033] The present invention is a multi-classifier fusion method based on PCA dimensionality reduction, such as figure 1 , figure 2 As shown, the specific implementation is as follows:

[0034] Step 1. Preprocessing mouse behavior data, including data cleaning and data transformation;

[0035] Step 2. Analyze the overall behavior and trajectory behavior of the mouse, and use the PCA method to reduce the dimensionality of the features to construct new and independent features. Among them, the overall behavior and trajectory behavior of the mouse are orthogonally transformed from the original 75-dimensional features, and the cumulative contribution is selected The principal component with a rate of 85% is used as the new mouse behavior feature, that is, the 26-dimensional new feature is selected to replace the original 75-dimensional feature, and the specific imple...

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-classifier fusion method based on PCA dimension reduction. A feature selection method is applied to the data feature set, involving (step-forward selection method and)a principal component analysis method, and the method constructs a few new features to replace the original features to model, and the stacking algorithm is also applied to the multi-classifier to obtain the optimal classification effect at present in the identity authentication experiment of the user mouse behavior. The multi-classifier fusion method solves the problem that the dimension of the characteristic space of the user mouse behavior is too much when the identity authentication based on the user mouse behavior exists in the prior art.

Description

technical field [0001] The invention belongs to the technical field of multi-classifier fusion, in particular to a multi-classifier fusion method based on PCA dimensionality reduction. Background technique [0002] Identity authentication is an important guarantee for information system security, but traditional identity authentication methods have defects such as easy disclosure and loss of authentication factors, so identity authentication based on user biometrics has gradually become a hot spot in the field of identity authentication research. When exploring and researching the identity authentication method of the user's mouse behavior characteristics, in order to improve the identity authentication performance and avoid the problems of over-fitting of a single classifier and insufficient classification accuracy, a multi-classifier based on PCA dimensionality reduction was invented. The fusion method performs dynamic continuous identity authentication tasks based on user...

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
CPCG06F18/2135G06F18/214G06F18/254
Inventor 姚全珠赵佳瑜费蓉颜丽菁
Owner XIAN UNIV OF TECH
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap