CN105631211B - A kind of multiple target nutrition Optimum Decision Support System - Google Patents
A kind of multiple target nutrition Optimum Decision Support System Download PDFInfo
- Publication number
- CN105631211B CN105631211B CN201511000100.5A CN201511000100A CN105631211B CN 105631211 B CN105631211 B CN 105631211B CN 201511000100 A CN201511000100 A CN 201511000100A CN 105631211 B CN105631211 B CN 105631211B
- Authority
- CN
- China
- Prior art keywords
- subsystem
- nutrition
- value
- nutrient
- client
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G06F19/3475—
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Coloring Foods And Improving Nutritive Qualities (AREA)
Abstract
The invention discloses a kind of multiple target nutrition optimization method and DSS, this method is based on fuzzy mathematics membership function, analyzed for various nutrients, propose the multiple-objection optimization object module of a Weight, and overall assessment index, by seeking optimal solution to overall assessment index, optimal individual overall nutritional programs are obtained.The DSS proposed simultaneously includes one or more client's subsystems and a computing subsystem, and user inputs nutrient initial value by client's subsystem, and computer subsystem calculates the individual overall nutritional programs for obtaining optimization.
Description
Technical field
The invention belongs to trophic analysis and guidance technology field, more particularly to a kind of multiple target trophic model, optimization method
And DSS.
Background technology
Diet nutritional is the basis of human survival, and human body is required for obtaining daily a certain amount of various must seek from meals
Form point, to meet the biochemical reaction of a series of complex in life process.If in institute's dietary intake certain nutrient it is excessive or
Deficiency, nutrient imbalance will be produced.How to instruct and judge the various nutrients of human body intake whether rationally, it is necessary to establish a set of
Trophic model is trophic analysis, instructs to provide foundation.
The nutritional support that clinic largely uses at present is mostly to be based on empirical equation, and these are based on sex, age, height and body
The clinical formula of weight has about more than 160, and wherein Harris-Benedict formula (being referred to as H-B formula) are used in professional Medical Degree
Obtain at most.Comparatively same patient for being in the various disease stage, the energy consumption estimated by formula are
One quantitative, and estimate is inherently problematic as the foundation of nutritional support.These formula all do not account for other possibility
Influence energy requirement factor, as endocrine disturbance, body of gland (such as thyroid gland, adrenal gland) diacrisis, stress situation (heating,
Wound, Psychic stress state), moving situation, body into the antagonism relationship between isloation state and nutrient matrix, nutrient, sleep, face
The influence of many factors such as bed nursing, medicine, morbid state, neurotransmitter and cell factor and environment, this cause estimate and
Very big deviation between actual demand be present.There are some researches show the estimate after clinically using H-B formula to add correction factor
It is quite inaccurate to have 1/3.Or thus have more than 1/3 carries out patient's nutrition of nutritional supplementation not by H-B formula
Or good overnutrition, this clinically hides serious medical consequences
Nutrition curve analysis method used in current clinical maternal nutritional analysis system, because combining individual tissue feelings
Condition, can accurately analyze the demand of each nutrient of individual, but also fail to solve at present based on nutrition curve analysis method
How to integrate individual (including a variety of factors for influenceing human nutrition demand of morbid state, living environment, eating habit etc.) makes
Various nutrients including energy do not reach the overall optimum state of individual nutrition demand.
The content of the invention
For problem of the prior art, the present invention proposes a kind of multiple target trophic model and optimization method, bent in nutrition
On the basis of provision of on-line analysis methodology, comprehensive individual age, height, body weight, sex, moving situation, environment, individual body organization factorses, life
The antagonism, proportionate relationship etc. lived between custom, eating habit, disease condition, metabolism status, nutrient, has re-established one
The multiple target trophic model of individual Problem with Some Constrained Conditions, and appropriate optimization method is used, overall Nutritional solutions are provided for individual,
Further laid the first stone for diet nutritional science decision.
Preferably to obtain individual nutrition demand global optimization scheme, the present invention is established one and analyzed based on nutrition curve
The multiple objective function model of the multifactor constraints of method.When establishing the multiple objective function model of multifactor constraints,
Effect (synergy, antagonism) between nutrient, the proportionate relationship between nutrient are not only allowed for, is also taken into full account
Habits and customs, drug administration, environmental factor, individual primary metabolism status, body structural constituent, morbid state, different physiological periods
(such as：Old age, pregnancy period, teenager etc.) etc. to the Special Influences of some nutrients.Institute involved in model is nutritious in principle
Composition is all to need the target that optimizes, such as gross energy, protein, fat, carbohydrate, calcium, potassium, iron, zinc, phosphorus, sodium, various
Vitamin, dietary fiber etc.；The synergy between proportionate relationship, nutrient, antagonism between nutrient, life are practised
Used, drug administration, environmental factor etc. are to the Special Influences of some nutrients, and different physiological periods are to the spy of some nutrients
Different demand.An individual nutrition needs of problems actually complicated, huge many factors constraints and Multi-objective Decision Model.
Need to take into full account many factors and constraints for influenceing individual nutrition demand, and establish a multiple objective function and model,
The individual nutrition total optimization solution obtained by appropriate optimized algorithm.
Based on above-mentioned model and algorithm, the present invention also develops a set of multiple target nutrition Optimum Decision Support System, user
Can be by input system according to sex, age, Dietary, motion conditions, habits and customs, drug administration, environmental factor, difference
Physiological period, with reference to multiple objective function model parameters such as metabolism monitoring, the measurement of body tissue, motion and the monitorings of disease, pass through
Network analysis, user finally obtain the nutritional programs after global optimization.
Brief description of the drawings
Fig. 1：The structured flowchart of DSS of the present invention.
Embodiment
The present invention is changed based on existing nutrition curve analysis method to nutrition curve function and mathematical modeling
Enter, it is proposed that a multiple target nutrition Optimized model based on fuzzy mathematics membership function Problem with Some Constrained Conditions.The model includes
25 kinds of nutrients including energy, the intake of various nutrients is expressed using the membership function in fuzzy mathematics and individual is good for
Corresponding relation between health situation, if xiIt is the daily intaking amount (1≤i≤25) of i-th kind of nutrient, with being subordinate to for following L-R types
Curvilinear function represents the corresponding relation：
Wherein, R is real number field, and function allows to be divided into three sections on section (0, c) fuzzy, i.e., and (0, a), [a, b), [b, c),
A and b is predetermined fragmentation value, it is preferred that for different xi, different a/b/c values are had according to metabolism monitoring.Function FLWith
FRIt is left piecewise function and right piecewise function, both need not be symmetrical, and those skilled in the art can be according to specific nutrition
Element and individual health situation design FLAnd FR, some existing specific design methods in this area, here is omitted.The person in servitude
It is a regular convex function to belong to curvilinear function.
It is subordinate to curve by above-mentioned, establishes multiple target nutrition Optimized model, influences the n kinds battalion of the overall nutrition condition of individual
The n object function that foster element can regard multiobjective decision-making as (mainly considers in current Chinese food component list 2004 here
25 including the energy kind main nutrients listed).Remaining influences multifactor (age, the body of individual nutrition changes in demand
Height, body weight, sex, moving situation, environment, individual body organization factorses, habits and customs, eating habit, disease condition, metabolism shape
Antagonism, proportionate relationship etc. between condition, nutrient) then conversion cost model constraints, when being subordinate to for all nutrients
After curvilinear function and constraints determine, the acquisition of nutritional need optimal value has been converted to asking for the optimal value of multiple target
Take problem.
In order to ask for the optimal value of multiple target, it can be asked for and effectively solved, be i.e. Pareto optimal solutions.For the more of the present invention
Target nutrition Optimized model, its effective solution is found, it is necessary to set one to effective result appraisal index, and with satisfaction about
The virtual value of the nutrient of beam condition is closer to optimal value, and the index is also closest to maximum or minimum value.According to the present invention's
One embodiment, using overall assessment indexs of the following P as nutrition condition, i.e.,：
In above formulaRefer to fuzzy corresponding to actual average daily intake in the nutrition curve of i-th kind of nutrient
Value, n are the species numbers of nutrient for needing to consider in meals.Compensation in usual decision-making problem of multi-objective between desired value, it is
It is balanced that certain is obtained between best and the worst desired value, mean operator is often used to realize this conversion, but is occupied with China
People's nutrient is compared with reference to the average (arithmetic equal value, geometric mean and harmomic mean) of recommended intake, and P is closer minimum
Value, it characterizes logical "and"；IfThen P → 0, when illustrating using P evaluation Meal Nutrition Conditions, low degree of membership
Nutrient can to individual overall nutrition condition have strong influence, can objectively respond individual actual nutrition condition；It is approximate
In calculating, P is convex function, can obtain optimum value, can determine that whether a kind of nutritional status of diet structure is better than another meals
Eat the nutritional status of structure.Therefore P can be bent in the nutrition of various nutrients as the overall assessment index of individual nutrition situation
After line determines, the quality of the current nutrition intake situation of the individual can be relatively easily judged by P values.
25 object functions in the multiple target nutrition Optimized model of the present invention are asymmetric fuzzy membership curvilinear function, can
To be solved using cut set method.In cut set method, each nutrient x in nutrition curveiDegree of membership for obscuring tolerance interval (0, c)
φ(xi), represent " satisfaction " to fuzzy constraint.φ(xiDuring)=0, the constraints is unmet, φ (xiDuring)=1,
The constraints is strictly met, when 0<φ(xi)<When 1, the constraint portions are met.
Use amRepresent xmTo the satisfaction of fuzzy constraint, it is designated as：am=φ (xm) in fuzzy permission section (0, c), it is subordinate to
Spend φ (xm) >=λ section composition is the λ horizontal cut sets on number theory domain.
It is different such as pregnant to the demand of Different Nutrition element under proportionate relationship, various states between the model nutrition
Phase is not only different from common woman to demands such as calcium, iron, zinc, protein, dietary fiber, iodine, energy, folic acid, also as pregnant week
Change, same person can also change to the demand of some nutrients, and these factors are required in Optimized model and optimized
Paid attention in journey.25 kinds of nutritions including energy are all the target for needing to optimize in this model, between them
Blend proportion be also to need the target that optimizes.Other individual status includes the disease related to nutrition intake (fat, sugar
Urine disease, hypertension etc.), environmental factor, habits and customs (stay up late, take antibiotic, strenuous exercise, pressure big etc.), diet
Custom (based on partially oily, partially salty, carnivorous, based on vegetarian diet etc.), different phase (pregnancy, lactation, old man, the teenager of physiological status
Deng) individual needed for the ratio of gross energy shared by three big macroelements be not quite similar, the demands of some specific nutrients also with
Individual state has large change.Therefore these need designing a model, constraints and needing emphasis during overall evaluation index
The content of consideration.
Although P can as the overall assessment index of individual nutrition situation, after the nutrition curve of various nutrients determines,
Also the quality of the current nutrition intake situation of the individual can be relatively easily judged by P values.But can not take into account it is above-mentioned it is various because
Element, it is therefore desirable to redesigned to P.According to second embodiment of the present invention, Different Nutrition element under different situations is considered
Different significance levels in object module, for the difference of the situation demand of Different Individual, introduce weights omegajImprove nutrition
The overall assessment index of situation, new overall assessment index P ' are as follows：
And
WhereinIt is that i-th kind of nutrient allows section A fuzzyiOn membership function, ωiIt is its weight, n is
The species number of nutrient considered is needed in meals.
For new overall assessment index P ', optimal solution is asked for it, it is possible to obtain the optimal of multiple target nutrient and take the photograph
Enter solution.Specific algorithm is as follows：
(1) initialization step：Initial value is taken for n kind nutrientsIf iteration error is ε, order
Cyclic variable j=0, for each xi, have following L-R types is subordinate to curve
It is subordinate to curve according to above-mentioned, obtain allows section A fuzzyiIn membership function
(2) by membership functionFollowing global optimization Index Formula is substituted into,
WhereinωiIt is xiWeighted value, be previously set according to different situations.
(3) j increases by 1, if j=n, go to step (7)；
(4) willN value in array arranges from big to small according to weighted value, takes the value for coming jth position (to be assumed to be xi),
By xiValue increase a predetermined step value, so as to obtain new array, according to the new array, recalculate global excellent
Change index, obtain
(5) ifSet up, go to step (6), otherwise go to step (7)
(6) makeReturn to step (3)；
(7) judgeWhether set up, if set up, go to step (10)；
(8) if j=n, j=0 is made；
(9) step (3) is gone to；
(10) x is exportedλ’=[x1, x2... xn]TAndTerminate.
Referring to Fig. 1, inquired about in order to facilitate user and implement nutrition design, the present invention is based on above-mentioned multiple target nutrition optimization side
Method, it is proposed that a kind of multiple target nutrition Optimum Decision Support System, the system include one or more client's subsystems, Yi Jiyi
Individual computing subsystem.Wherein client's subsystem receives the various nutrients type and initial value of user's input, sends it to meter
Operator Systems, computing subsystem are calculated using the multiple target nutrition optimization method of the present invention, obtained individual according to above-mentioned input
Property nutritional programs, client's subsystem is returned to by the output result of calculating.
Below by one 32 years old, 159 centimetres of height, body weight 52.45kg, exemplified by pregnant early stage women.Coordinate its dietary survey,
Motion monitoring, the measurement of body tissue, and Model for Multi-Objective Optimization and optimized algorithm using this paper, obtain following personalized battalion
The scheme of supporting：
The embodiments of the present invention described above are not intended to limit the scope of the present invention.It is any in the present invention
Spirit and principle within the modifications, equivalent substitutions and improvements made etc., should be included in the claim protection model of the present invention
Within enclosing.
Claims (2)
1. a kind of multiple target nutrition Optimum Decision Support System, it is characterised in that the DSS includes one or more
Client's subsystem, and a computing subsystem, wherein
Client's subsystem receives the nutrient categories of user's input, and the initial value of nutrient
Wherein n is the species number of nutrient, xiIt is the daily intaking amount of i-th kind of nutrient, then client's subsystem inputs user
Information be sent to the computing subsystem；
The computing subsystem is calculated according to the information of reception, is exported the personalized nutritional scheme of the user, will be exported
Result return to client's subsystem, wherein the detailed process calculated is as follows：
(1) it is ε to make iteration error, makes cyclic variable j=0, for each xi, that establishes following L-R types is subordinate to curve,
Wherein, R is real number field, and be subordinate to curve allows section A fuzzyiIt is divided into three sections on=(0, c), a and b are predetermined segmentations
Value, function FLAnd FRIt is left piecewise function and right piecewise function；It is subordinate to curve according to above-mentioned, obtain allows section A fuzzyiIn
Membership function
(2) by membership functionFollowing global optimization Index Formula is substituted into, is obtained
WhereinωiIt is xiWeighted value；
(3) j increases by 1, if j=n, go to step (7)；
(4) willN value in array arranges from big to small according to weighted value, the value increase by one for coming jth position is predetermined
Step value, so as to obtain new array, according to the new array, global optimization index is recalculated, obtains Pη：
(5) ifSet up, go to step (6), otherwise go to step (7)；
(6) makeReturn to step (3)；
(7) judgeWhether set up, if set up, go to step (10)；
(8) if j=n, j=0 is made；
(9) step (3) is gone to；
(10) x is exportedλ'=[x1,x2,…xn]TAndTerminate.
2. multiple target nutrition Optimum Decision Support System according to claim 1, wherein it is a convex function to be subordinate to curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511000100.5A CN105631211B (en) | 2015-12-28 | 2015-12-28 | A kind of multiple target nutrition Optimum Decision Support System |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511000100.5A CN105631211B (en) | 2015-12-28 | 2015-12-28 | A kind of multiple target nutrition Optimum Decision Support System |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105631211A CN105631211A (en) | 2016-06-01 |
| CN105631211B true CN105631211B (en) | 2018-01-26 |
Family
ID=56046140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511000100.5A Active CN105631211B (en) | 2015-12-28 | 2015-12-28 | A kind of multiple target nutrition Optimum Decision Support System |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631211B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114121219B (en) * | 2022-01-24 | 2022-05-17 | 北京康爱医疗科技股份有限公司 | Nutrition management system and management method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605517A (en) * | 2013-11-13 | 2014-02-26 | 苏州天擎电子通讯有限公司 | Electronic software system capable of automatically collocating daily diets |
| CN104731846A (en) * | 2014-11-17 | 2015-06-24 | 陕西师范大学 | Individuation catering recommendation method and system based on multiple targets |
| CN104866954A (en) * | 2015-04-27 | 2015-08-26 | 天津师范大学 | Resident diet balance quantification analysis method based on intelligent information processing terminal, and system thereof |
-
2015
- 2015-12-28 CN CN201511000100.5A patent/CN105631211B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103605517A (en) * | 2013-11-13 | 2014-02-26 | 苏州天擎电子通讯有限公司 | Electronic software system capable of automatically collocating daily diets |
| CN104731846A (en) * | 2014-11-17 | 2015-06-24 | 陕西师范大学 | Individuation catering recommendation method and system based on multiple targets |
| CN104866954A (en) * | 2015-04-27 | 2015-08-26 | 天津师范大学 | Resident diet balance quantification analysis method based on intelligent information processing terminal, and system thereof |
Non-Patent Citations (3)
| Title |
|---|
| 多目标优化的粒子群算法及其应用研究;陈绍新;《中国优秀硕士学位论文全文数据库信息科技辑》;20080515;I138-25 * |
| 带约束的多目标进化算法及其营养膳食模型的研究;孙艳平;《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》;20110615;B025-1 * |
| 模糊多目标遗传算法及其在营养决策中的应用;王高平等;《河南工业大学学报(自然科学版)》;20061031;第27卷(第5期);62-65 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105631211A (en) | 2016-06-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Meyers et al. | Dietary reference intakes: the essential guide to nutrient requirements | |
| US20170116879A1 (en) | Diet adherence system | |
| JP7319930B2 (en) | Systems and methods for calculating, displaying, modifying, and using a single food intake score that reflects optimal quantity and quality of ingestibles | |
| Crozier et al. | Maternal vitamin D status in pregnancy is associated with adiposity in the offspring: findings from the Southampton Women’s Survey | |
| Arcand et al. | Evaluation of 2 methods for sodium intake assessment in cardiac patients with and without heart failure: the confounding effect of loop diuretics | |
| WO2015058729A1 (en) | Comprehensive health evaluation system and method | |
| CN103678874B (en) | A kind of personal health meals and kinergety management of balance method | |
| CN105260594A (en) | Individual nutrition evaluation system | |
| Sakamoto et al. | Relationship of vitamin D levels to blood pressure in a biethnic population | |
| JP2023060289A (en) | Health management system | |
| Nightingale et al. | Validation of triple pass 24-hour dietary recall in Ugandan children by simultaneous weighed food assessment | |
| Fairweather-Tait et al. | Approaches used to estimate bioavailability when deriving dietary reference values for iron and zinc in adults | |
| CN109461492A (en) | It is a kind of for alleviating the intelligent pantry and dietary management method of gout | |
| CN105631211B (en) | A kind of multiple target nutrition Optimum Decision Support System | |
| Zhai et al. | Validation of the nutrient-rich foods index estimated by 24-h dietary recall method among adults in Henan province of China | |
| Starkweather et al. | Estimating impacts of the nuclear family and heritability of nutritional outcomes in a boat‐dwelling community | |
| Bandyopadhyay et al. | Assessment of energy balance against the nutritional status of women carriers in the brickfields of West Bengal | |
| KR20230120581A (en) | Personalized Food Recommendation System and Method | |
| CN108615553B (en) | Meal making method and device and storage medium | |
| Abu-Saad et al. | Bread type intake is associated with lifestyle and diet quality transition among Bedouin Arab adults | |
| Gregory-Mercado et al. | Ethnicity and nutrient intake among Arizona WISEWOMAN participants | |
| JP3895746B2 (en) | Mixing determination device, mixing determination method and program | |
| Kunvik et al. | Effects of home-delivered meals on older people’s protein intake, physical performance, and health-related quality of life: the power meals randomized controlled trial | |
| Carson | White and Black Weight by Socioeconomic Status and Residence: Revaluating Nineteenth-Century Health during the Institutional Change to Free Labor | |
| CN201207188Y (en) | Meal nutrition evaluating health guidance apparatus |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201130 Address after: 1409, building 4, 209 Zhuyuan Road, high tech Zone, Suzhou City, Jiangsu Province Patentee after: Suzhou Kangzhi Medical Co.,Ltd. Address before: 100836 No. 5, No. 59, South District, No. 19 West Third Ring Road, Beijing, Haidian District, 9 Patentee before: Wang Ping |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230403 Address after: East of 1st floor, No.36 Haidian Street, Haidian District, Beijing, 100000 Patentee after: BEIJING KANGPING TECHNOLOGY Co.,Ltd. Address before: Room 1409, Building 4, No. 209, Zhuyuan Road, High tech Zone, Suzhou City, Jiangsu Province, 215000 Patentee before: Suzhou Kangzhi Medical Co.,Ltd. |