High-dimensional data function selection algorithm based on reverse elimination method and application thereof in medical treatment
A technology for high-dimensional data and selection algorithms, applied in special data processing applications, electrical digital data processing, computing, etc., to achieve the effect of reducing prediction errors
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0036] First of all, the high-dimensional data function selection algorithm based on the backward dropping method and its application in medical treatment of the present invention are based on two basic tools: influence measure and backward dropping algorithm.
[0037] A. Measuring Influence
[0038] In order to explain the influence measure clearly, assume that the dependent variable is dichotomous (only takes the value 0 or 1, for example, 0 means no cancer, 1 has cancer. Depending on the problem, it can be a continuous variable or a discrete variable with more values). All covariates (such as the expression levels of various genes in genetically predicting disease) are discrete. Consider splitting yes a subset of covariates . If all variables in this subset are dichotomous, then this split has 2
[0039] possible values. definition For when the split value is Time number of observations. Assume that the covariates of this split set are the same as it doe...
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