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

RLID3 data classification method based on decision tree optimization rate

A data classification and decision tree technology, applied in the direction of instruments, character and pattern recognition, computer parts, etc., can solve the problem of low accuracy of decision tree data classification, and achieve the effect of simplifying the structure

Inactive Publication Date: 2016-11-09
HARBIN ENG UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0019] The purpose of the present invention is to solve the problem of low accuracy rate of existing decision tree data classification, and propose a kind of RLID3 data classification method based on decision tree optimization rate

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
  • RLID3 data classification method based on decision tree optimization rate
  • RLID3 data classification method based on decision tree optimization rate
  • RLID3 data classification method based on decision tree optimization rate

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0053] Specific implementation mode one: a kind of RLID3 data classification method based on the decision tree optimization rate of the present embodiment is specifically prepared according to the following steps:

[0054] Step 1: Optimizing the information gain to obtain the optimization rate of the decision tree, the formula is as follows:

[0055] D T O R ( S , A ) = G a i n ( S , A ) L e a f N u m ( S , A ) - - ...

specific Embodiment approach 2

[0058] Specific implementation mode two: the difference between this implementation mode and specific implementation mode one is: in the step one, the information gain is optimized to obtain the decision tree optimization rate; the specific process is:

[0059] The formula for calculating information gain is as follows:

[0060] Gain(S,A)=Entropy(S)-Entropy(S,A) (4)

[0061] In the formula, Gain(S,A) represents the information gain of attribute A on the training set S, Entropy(S) represents the information entropy of training set S, Entropy(S,A) represents the information entropy of attribute A, A is the attribute, S is the training set;

[0062] In the ID3 algorithm, information entropy can be understood as uncertainty. If Entropy(S) is understood as the uncertainty on the training set S, Entropy(S,A) is understood as the uncertainty of the A attribute on the training set S, and their difference represents the selection of the A attribute. , the reduction in uncertainty. ...

specific Embodiment approach 3

[0073] Specific implementation mode three: the difference between this implementation mode and specific implementation mode one or two is: the RLID3 algorithm is obtained based on the decision tree optimization rate in the said step two; the specific process is:

[0074] 2.1 RLID3 Algorithm

[0075] The category attribute refers to the attribute used to identify the category of the sample in the data set.

[0076] Non-category attributes refer to the attributes used to identify a certain aspect of the sample in the data set.

[0077] For example: In Table 1, outlook and humidity represent non-category attributes, and play represents category attributes. Examples of data sets are shown in Table 1.

[0078] Table 1 Data Set Example

[0079]

[0080] With the theoretical basis of the previous section, the proposed

[0081] The RLID3 algorithm is shown below.

[0082] Algorithm 1: makeRLID3Tree (training set)

[0083] Input the training set S, and output the decision tree...

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 an RLID3 data classification method based on a decision tree optimization rate, and relates to an RLID3 data classification method based on a decision tree optimization rate, for the purpose of solving the problem of low classification accuracy of a conventional decision tree. The concrete process comprises the following steps: step one, optimizing information gain to obtain the decision tree optimization rate; and step two, based on the decision tree optimization rate, obtaining an RLID3 algorithm, wherein the RLID3 algorithm involves converting the information gain into the decision tree optimization rate in the process of an ID3 algorithm. The method is applied to the field of classification.

Description

technical field [0001] The invention relates to an RLID3 data classification method based on decision tree optimization rate. Background technique [0002] Hong Jiarong and others proved that the following three problems need to be solved in order to find the optimal decision tree. [0003] (1) The number of generated leaves is the least; (2) The depth of each leaf is the smallest; (3) The number of generated decision tree leaves is the smallest and the depth of each leaf is the smallest. The ID3 algorithm is based on the above rule (2), that is, the depth of each leaf generated is the smallest, and a decision tree is generated. [0004] The principle of the ID3 algorithm is introduced below, and the ID3 algorithm is improved according to the above-mentioned rule (1), that is, the number of leaves generated is the least. The core idea of ​​ID3 algorithm is to use information gain to select candidate attributes. It is the most typical algorithm in the decision tree learnin...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/24323
Inventor 王红滨李华峰刘红丽冯梦园王世鹏刘广强张玉鹏杨楠刘天宇徐琳
Owner HARBIN ENG UNIV
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