Human body composition prediction method based on AIC and improved entropy weight method
A prediction method and body composition technology, applied in the field of bioinformatics, can solve problems such as high dimensionality, nonlinearity, and small samples, and achieve the effects of improving prediction accuracy, simplifying fitting models, and effective detection means
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0076] This embodiment provides a human body composition prediction method based on AIC and improved entropy weight method, including:
[0077] S1: Considering the differences in various parts of the human body, select a five-segment impedance model, collect data and construct an original feature set F of physiological information samples;
[0078] S2: Consider a series of other physiological parameters that affect body composition, add the original feature set F of the physiological information sample, and construct the first feature parameter and the second feature parameter;
[0079] At present, the five-segment human body impedance model is the most commonly used segmented impedance model, which takes into account the differences of various parts of the human body, and divides the human body into five segments of impedance: right upper limb, left upper limb, trunk, right lower limb, and left lower limb. In addition to considering the five-segment impedance value R in the m...
Embodiment 2
[0091] As a supplement to Example 1, the steps for solving the human body composition fitting model are as follows:
[0092] S51: Suppose the evaluation event has m objects, n parameters, x ij is the j-th indicator under the i-th object, then the decision matrix Y with m rows and n columns = {x ij} m×n Calculated according to the bigger the better index:
[0093]
[0094] Or the smaller the better index calculation:
[0095]
[0096] S52: Eliminate the different dimension units of different indicators of the object to form a unified matrix: In order to make ln(Y′ ij ) is meaningful, generally it can be assumed that: when Y′ ij =0, Y' ij ln(Y′ ij )=0. But Y' ij =1, ln(Y' ij ) is also equal to 0, which is obviously inconsistent with the reality and contrary to the meaning of entropy. Therefore, for Y′ ij to modify:
[0097] S53: Calculate the entropy value e in the formula j is the entropy value corresponding to the jth evaluation indicator; if Y′ ij = 0...
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