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

Miner nutrition metabolism evaluation method and system based on random forest and word2vec

A technology of nutrient metabolism and random forest, applied in the field of nutrient metabolism evaluation, can solve the problem that there is no professional, highly targeted, efficient and accurate detection device and its evaluation method

Pending Publication Date: 2020-09-01
ANHUI UNIV OF SCI & TECH +1
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At this stage, the detection of human nutrition metabolism is mostly developed based on the principle of indirect calorimetry, but for the detection of nutrition metabolism of miners, there is no professional, targeted, efficient and accurate detection device and its evaluation method

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
  • Miner nutrition metabolism evaluation method and system based on random forest and word2vec
  • Miner nutrition metabolism evaluation method and system based on random forest and word2vec
  • Miner nutrition metabolism evaluation method and system based on random forest and word2vec

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0075] In the step S1, the miner's nutritional metabolism analysis system includes a miner's inhaled gas collection module, a miner's exhaled gas detection module, a miner's personal information input module and a host computer, and the miner's inhaled gas collection module, miner's exhaled gas detection module, miner's personal The information obtained by the information input module is input into the upper computer for metabolic analysis processing.

Embodiment 2

[0077] In the step S2, the inhaled gas data A includes the oxygen content A 1 , carbon dioxide content A 2 and inhaled gas mass A 3 ; The exhaled gas data B includes oxygen content B 1 , carbon dioxide content B 2 and the quality of exhaled air B 3 ; The personal information data C includes name, gender, age, place of work, and past medical history, and the quantified representation of the metabolism Output is a value within 0-100.

Embodiment 3

[0079] In the step S3, the conversion step is as follows:

[0080] S31: Define the Skip-gram model in the known given word w t Under the premise of predicting the context w of the word ct , then the context w ct It can be expressed as:

[0081] w ct =w t-c ,...,w t-1 ,w t+1 ,...,w t+c (1)

[0082] where c is the given word w t The number of words before and after the

[0083] S32: Define the optimization objective function of the Skip-gram model as the logarithmic likelihood function of formula (2):

[0084]

[0085] Where C represents the corpus containing all words, and k represents the current word w t The window size of , that is, take k words before and after the current word;

[0086] S33: Combining the Hierachical Softmax algorithm and negative sampling for the conditional probability p(w t+c |w t ) is optimized to get:

[0087]

[0088] Among them, v w and v' w Respectively represent the input and output word vectors of the word w, and W represe...

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 miner nutrition metabolism evaluation method and system based on a random forest and word2vec, and relates to the technical field of nutrition metabolism evaluation. When nutrition metabolism of miners is analyzed, individual differences of miners are comprehensively considered, word vectors are prepared and extracted by utilizing word2vec, and the accuracy and reliability of metabolism evaluation of the miners are improved by virtue of an RF regression analysis method; and the metabolic condition is accurately and reliably evaluated, so that the body health state ofthe miner can be accurately and timely mastered. Nutrition metabolism detection evaluation is carried out on the special group of miners, accurate and real-time measurement and analysis of the body health state of the miners are achieved, early warning of part of occupational diseases is completed, and life health of the miners is guaranteed.

Description

technical field [0001] The invention relates to the technical field of nutrient metabolism evaluation, in particular to a miner nutrient metabolism evaluation method and system based on random forest and word2vec. Background technique [0002] With the continuous increase of coal mining depth, the underground operating environment conditions are gradually deteriorating. The dust pollution in the workplace is serious and the environment is harsh, and the possibility of miners suffering from occupational diseases is greatly increased. In order to realize the detection and evaluation of miners' physical conditions, to realize early judgment of occupational diseases, improve the early detection rate of occupational diseases, and deepen people's awareness of health , to reduce occupational diseases and the serious economic burden on miners. [0003] The three major nutrients refer to carbohydrates, fats, and proteins, the three essential nutrients for humans and animals. These ...

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): G16H50/30G16H20/60G06K9/62G06F17/18
CPCG16H50/30G16H20/60G06F17/18G06F18/24323G06F18/214
Inventor 周孟然马祖长胡锋陈炎炎卞凯闫鹏程
Owner ANHUI UNIV OF SCI & TECH
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

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