Method for building multi-classification support vector machine classifier based on Bhattacharyya distance and directed acyclic graph

A directed acyclic graph and support vector machine technology, applied in the field of pattern recognition, can solve the problems of not being able to use different prior information on the separability between categories, large amount of calculation, slow training speed, etc., to achieve good learning effect, The effect of fast calculation and reduced data input

Active Publication Date: 2011-07-13
哈尔滨工业大学高新技术开发总公司
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the traditional multi-classification strategy cannot use prior information with different separability between categories due to its fixed structure, and the training speed slows down wit

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
  • Method for building multi-classification support vector machine classifier based on Bhattacharyya distance and directed acyclic graph
  • Method for building multi-classification support vector machine classifier based on Bhattacharyya distance and directed acyclic graph
  • Method for building multi-classification support vector machine classifier based on Bhattacharyya distance and directed acyclic graph

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0018] Specific implementation mode one: the following combination figure 1 This embodiment is described. In this embodiment, a multi-classifier based on a directed acyclic graph structure is assisted by Bhattacharyian distance, so that categories with relatively large differences in separability are prioritized for discrimination, and the topology is redundant. The same The samples of the category can have different classification paths, and this path shunting reduces the amount of data input to the sub-classifier, making the calculation faster and the learning effect better.

[0019] The purpose of the present invention is achieved through the following technical solutions: estimate the separability distribution properties between various training data by calculating the Bhattacharyachian distance, establish an initial operation form, arrange all possible categories of the sample in a certain order in the form, and re- Combine the node order of the directed acyclic graph, an...

specific Embodiment approach 2

[0049] Specific embodiment two: this embodiment describes a specific embodiment of the present invention in conjunction with the servo motor system identification data in the UCI (University of California, Irvine) machine learning public database:

[0050] In the servo motor system data set of the UCI machine learning public database, the recorded output value is the adjustment time, that is, the time for the system to respond to the step command and run in place when the system is in a set position. According to the time value, it can be equal It is divided into 5 categories, which are described by four attributes: motor type, guide rail thread type, position loop proportional gain and speed loop proportional gain. The data set contains 167 samples, 84 of which are taken as training samples, and the remaining 83 as a test sample.

[0051] Execution step 1: For the 5-category servo motor system objects, calculate the Bhattacharyachian distance between any two categories of tra...

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 method for building a multi-classification support vector machine classifier based on the Bhattacharyya distance and a directed acyclic graph, belonging to the field of mode identification. The method aims to solve the problems that the training speed is lowered when the number of training samples or the number of classes is increased and the calculation amount is large because the traditional multi-classification strategy can not utilize prior information with different separabilities among classes because of the fixed structure. The method disclosed by the invention comprises the following steps: 1. respectively calculating the Bhattacharyya distance between every two classes in a training sample for a multi-classification object; 2. building an initial operation form according to the Bhattacharyya distance between the every two classes in the training sample, which is obtained in the step 1; 3. according to the initial operation form obtained in the step 2, building a multiple classifier based on the directed acyclic graph structure; and 4. adopting a support vector machine as a binary classifier, and carrying out multi-classification based on the directed acyclic graph structure.

Description

technical field [0001] The invention relates to a method for constructing a multi-category support vector machine classifier based on Bhattacharydi distance and a directed acyclic graph, which belongs to the field of pattern recognition. Background technique [0002] As a powerful machine learning method, the Support Vector Machine (SVM) proposed by Viadimir N. Vapnik and his colleagues has been successfully applied in pattern recognition, especially in the field of fault diagnosis and classification. SVM adopts the Structural Risk Minimization Principle based on statistical learning theory, which can effectively solve problems such as nonlinearity, limited samples and high dimensions, and usually provides good learning ability and generalization ability. The support vector machine was originally proposed for binary classification problems and cannot be directly used for multi-class classification problems. Most of the fault diagnosis problems are multi-class classification ...

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
Inventor 张淼沈毅王强
Owner 哈尔滨工业大学高新技术开发总公司
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