Continuous attribute discretization method based on Chi2 statistics
A discretization and attribute technology, applied in complex mathematical operations and other directions, can solve problems such as inconsistency, achieve high precision, and avoid unfair interval selection.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0037] 1. The specific process of Rec-Chi2 algorithm is as follows:
[0038] Step1: Initialization. Let the significance level α=0.5. Calculate the information system inconsistency rate Incon_rate.
[0039] Step2: Sort the data for each attribute and calculate the χ of all adjacent intervals according to formula (1) 2 Value, find out the χ 2 corresponding Value, then calculate the difference
[0040] Step3: Merge
[0041] while (intervals that can be combined)
[0042] {Find the largest breakpoint of D′ to merge;
[0043] if(Incon_rate increases)
[0044] {Undo the merge; goto Step4;}
[0045] else goto Step2;
[0046] }
[0047] Step4: if (α is the last level)
[0048] {Exit the program, discretization is complete;}
[0049] else{α 0 =α; downgrade to α; goto Step2;}
[0050] Step5: Discretization of a single attribute.
[0051] For each attribute
[0052] {Calculate the difference D′;
[0053] α=α 0 ;
[0054] Flag = 0;
[0055] ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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