CN111932001A - Emergency medical resource allocation method based on multi-objective optimization - Google Patents

Emergency medical resource allocation method based on multi-objective optimization Download PDF

Info

Publication number
CN111932001A
CN111932001A CN202010738486.4A CN202010738486A CN111932001A CN 111932001 A CN111932001 A CN 111932001A CN 202010738486 A CN202010738486 A CN 202010738486A CN 111932001 A CN111932001 A CN 111932001A
Authority
CN
China
Prior art keywords
individual
emergency medical
high risk
resource allocation
medical resource
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.)
Granted
Application number
CN202010738486.4A
Other languages
Chinese (zh)
Other versions
CN111932001B (en
Inventor
杜占玮
高超
张池军
王春雨
原志路
白媛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Research Center Of Digital City Engineering
Original Assignee
Shenzhen Research Center Of Digital City Engineering
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shenzhen Research Center Of Digital City Engineering filed Critical Shenzhen Research Center Of Digital City Engineering
Priority to CN202010738486.4A priority Critical patent/CN111932001B/en
Publication of CN111932001A publication Critical patent/CN111932001A/en
Application granted granted Critical
Publication of CN111932001B publication Critical patent/CN111932001B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/12—Computing arrangements based on biological models using genetic models
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/20—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/80—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for detecting, monitoring or modelling epidemics or pandemics, e.g. flu

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Public Health (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • General Business, Economics & Management (AREA)
  • Biophysics (AREA)
  • Medical Informatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Primary Health Care (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Molecular Biology (AREA)
  • Epidemiology (AREA)
  • Genetics & Genomics (AREA)
  • Pathology (AREA)
  • Development Economics (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Databases & Information Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Bioinformatics & Cheminformatics (AREA)

Abstract

The invention provides an emergency medical resource allocation method based on multi-objective optimization; the method comprises the following steps: s1: randomly initializing individual distribution amount of a population; s2: constructing an optimization target according to the high risk group and the infection degree; s3: selecting an individual with a high risk group target value and a large infection severity adaptive value according to a roulette method; s4: selecting two individuals with high risk group target values and larger target values of the infection severity according to the roulette method of S3 to perform one-way crossing operation; s5: performing a mutation operation; s6: updating the individual distribution amount according to a particle swarm updating rule; s7: a non-dominated solution set of the individual allocation amounts is obtained. The invention sets two targets of high risk group and infection degree, balances the distribution of emergency medical resources in different regions by modeling the two targets, recommends a reasonable emergency medical resource distribution scheme for each region in the environment of emergent public health events, and helps the decision of disease prevention and control center and control the spread of potential COVID-19.

Description

Emergency medical resource allocation method based on multi-objective optimization
Technical Field
The invention belongs to the field of artificial intelligence and complex networks; in particular to an emergency medical resource allocation method based on multi-objective optimization.
Background
The risk of outbreaks of infectious diseases is difficult to control due to the variability of coronaviruses, uncertainty in the transmission process, and general lack of public protection awareness. And the rapidity of viral transmission also makes emergency medical resources in most hospitals under preparation in the early stages of an outbreak.
At present, new vaccines and antiviral drugs for coronary pneumonia are still under development. In addition, other medical treatments, such as plasma treatments and the like, are unlikely to be implemented on a large scale. Therefore, the use of personal protective equipment, such as hand lotions, medical masks, protective clothing, etc., is one of the major non-pharmaceutical measures to reduce the risk of infection. But in the presence of this major public health incident, the shortage of emergency medical resources and the allocation of medical resources are becoming a worldwide problem. Medical instruments, protective equipment, medicines, medical consumables and other resources of domestic hospitals are in short supply, and medical staff are exposed to infection risks due to the shortage of personal protective equipment in the global range. How to effectively allocate emergency medical resources is a problem to be solved.
Balancing the allocation of emergency medical resources among different regions is a difficult task, based on the participation of multiple risk factors and benefits. Two of the key factors are the high risk group and the severity of the infection. The key technology of the invention is to set two targets of high risk group and infection degree and model the two targets. The two targets are then balanced using a modified particle swarm algorithm. And the unidirectional crossing and variation operations are incorporated into a particle swarm optimization framework, the heterogeneity of high risk groups and the severity of infection are balanced, and a reasonable allocation strategy of emergency medical resources is generated. Therefore, in Shenzhen, the supply and allocation of emergency medical resources becomes an urgent priority.
Disclosure of Invention
The invention aims to provide an emergency medical resource allocation method based on multi-objective optimization.
In a first aspect, the invention is realized by the following technical scheme:
the invention relates to an emergency medical resource allocation method based on multi-objective optimization, which comprises the following steps:
s1: randomly initializing individual distribution quantity of population: with X ═ X1,x2,...,xnExpressing the individual distribution quantity of the population, wherein the position X of each individual in the population represents a solution, and the maximum total quantity of emergency resources is Max assuming n regions;
s2: an optimization target is constructed according to the high risk group and the infection degree:
the first objective is: calculating an optimal target value of the high risk group;
the second objective is: calculating an infection degree optimization target value;
s3: selecting the high risk group target value and the individual with larger infection severity adaptive value according to the roulette method: selecting a high risk group target value of each individual according to the data calculated by the formulas (1) and (2); calculating individual selection probability P (x) of each individuali) And cumulative probability Q (x)i)；
S4, selecting two individuals with high risk group target value and larger target value of infection severity according to the roulette method of S3 to perform one-way crossing operation; the aim is to retain genes between individuals with large fitness values.
S5: performing a mutation operation;
s6: updating the individual distribution amount according to a particle swarm updating rule;
s7: a non-dominated solution set of the individual allocation amounts is obtained.
Preferably, the specific steps of S1 are as follows: by randomly choosing a number between 0 and Max as x in an individualiAssignment, xiIndicating the emergency medical resource allocation amount of the ith area.
Preferably, in S2, the specific steps of calculating the high risk group optimization target value are as follows: high risk group in ith area is defined as OiA person of age greater than or equal to 65 years; the ith area has a general population of MiThen, the calculation process of the optimal target value of the high risk group in the ith area is shown as formula (1):
f1(x)＝∑ixi×Oi/Mi (1)
preferably, in S2, the infection degree optimization target value calculation includes the specific steps of:
mainly infected degree; the number of confirmed persons in the ith area is assumed to be IiThe number of affected persons per confirmed case is AiThen, the infection degree optimization target value of the ith area is calculated as shown in formula (2):
f2(x)＝∑ixi×Ai×Ii/Mi (2)
preferably, in S3, the individual selection probability P (x)i) The formula is shown as (3); the cumulative probability Q (x)i) The formula is shown as (4); in the interval [0,1]Randomly generating a number, judging which interval the number falls in, and if the number falls in a certain interval, selecting the interval;
Figure BDA0002605962020000031
Figure BDA0002605962020000032
preferably, the specific steps of S4 are as follows: assuming that individuals A and B cross unidirectionally, half x of individuals A are randomly selectediThen to the same location of individual B; the new individuals generated finally areIndividual B after being assigned a value.
Preferably, the specific steps of S5 are as follows: setting a mutation threshold value to be Mu, and if the random number is smaller than Mu, starting mutation operation; the mutation rule is x in the individualiA random value between 0 and Max is assigned.
Preferably, the specific steps of S6 are as follows:
after completing the mutation operation of the S5 particle group, the distribution amount of each individual is updated according to the following formula (5) and formula (6):
Figure BDA0002605962020000041
Figure BDA0002605962020000042
wherein, in the formula (5),
Figure BDA0002605962020000043
represents the individual optimum dispensing amount;
Figure BDA0002605962020000044
representing the global optimal distribution quantity of the population; c is a learning factor; r is1And r2Represents two random numbers between 0 and 1; ω is the inertial weight;
Figure BDA0002605962020000045
is an exclusive or operation that is performed,
Figure BDA0002605962020000046
operating to add the two velocity vectors to form a new velocity vector; specifically, assume that:
Figure BDA0002605962020000047
Figure BDA0002605962020000048
then
Figure BDA0002605962020000049
The detailed operation is defined as follows:
Figure BDA00026059620200000410
in equation (6): velocity vector and position vector pass
Figure BDA00026059620200000411
Forming a new position vector; suppose that:
Figure BDA00026059620200000412
Figure BDA00026059620200000413
then
Figure BDA00026059620200000414
The detailed operation is defined as follows:
Figure BDA00026059620200000415
wherein L isi＝{l1，l2，···，lkIs the set of neighbor nodes, if i equals j, then
Figure BDA00026059620200000416
If not, then,
Figure BDA00026059620200000417
preferably, the specific steps of S7 are as follows: in the multi-objective optimization algorithm, the objective function does not have the optimal solution which enables all the objective functions to reach the maximum or the minimum simultaneously. Then, after obtaining the global optimal allocation amount through S6, the non-dominated solution is sought. If any two solutions X1And X2Suppose for an arbitrary target X1Are all superior to X2We call X1Dominating X2. If a certain solution does not existIf the solution is dominated by any other solution, we call the solution a non-dominated solution. And selecting the first solution from all the non-dominant solutions as a final distribution result.
The method models the decision problem based on emergency resource allocation into a multi-objective optimization problem, and constructs two optimization objectives of high-risk population and infection degree. And then, an improved particle swarm algorithm is adopted, unidirectional crossing and variation operations are incorporated into a particle swarm optimization framework, heterogeneity and infection severity of high risk groups are balanced, and a reasonable allocation strategy of emergency medical resources is generated. The method increases the diversity of individuals and improves the characteristic that the particle swarm algorithm is easy to fall into local optimum.
The method of the invention has the following advantages:
(1) the invention relates to an emergency medical resource allocation method based on multi-objective optimization; solutions of all areas are generated randomly at the beginning, high-risk people and the infection degree are used as two optimization indexes, and the scheme with a higher optimization target value is subjected to one-way cross operation by using a roulette algorithm. Then, a mutation threshold is set, and mutation operation is performed if the random number is smaller than the threshold. And optimizing the solution subjected to genetic operation by using a particle swarm framework, and finally selecting the first solution in the non-dominated solution set as the resource allocation quantity of each region.
(2) The invention relates to an emergency medical resource allocation method based on multi-objective optimization, which sets two targets of high risk groups and infection degree, balances the allocation of emergency medical resources in different regions by modeling the two targets, recommends a reasonable emergency medical resource allocation scheme for each region in the environment of emergent public health events, and helps the decision of a disease prevention and control center and control the spread of potential COVID-19.
(3) The invention relates to an emergency medical resource allocation method based on multi-objective optimization, which adopts an improved particle swarm algorithm, incorporates unidirectional crossing and variation operations into a particle swarm optimization framework, balances the heterogeneity and the infection severity of high risk groups, and generates a reasonable allocation strategy of emergency medical resources. The method increases the diversity of individuals and improves the characteristic that the particle swarm algorithm is easy to fall into local optimum.
Drawings
FIG. 1 is a flow chart of the emergency medical resource allocation method based on multi-objective optimization according to the present invention;
FIG. 2 is a detailed diagram of the emergency medical resource allocation method based on multi-objective optimization according to the present invention;
FIG. 3 is an emergency medical resource allocation diagram of 10 regions in Shenzhen City estimated on 14 days in 2020 in the embodiment. The middle right insert represents the pareto boundary for two goals of high risk population and infection level; wherein (a) is an emergency medical resource prediction map based on the maximum high risk group target value; (b) an emergency medical resource prediction graph based on a maximum infection schedule target value.
Detailed Description
The present invention will be described in detail with reference to specific examples. It should be noted that the following examples are only illustrative of the present invention, but the scope of the present invention is not limited to the following examples.
Examples
The embodiment relates to an emergency medical resource allocation method based on multi-objective optimization, and the process is shown in the attached figure 1: the method comprises the following steps:
s1: randomly initializing individual distribution quantity of population: with X ═ X1,x2,...,xnExpressing the individual distribution quantity of the population, wherein the position X of each individual in the population represents a solution, and the maximum total quantity of emergency resources is Max assuming n regions;
s2: an optimization target is constructed according to the high risk group and the infection degree:
the first objective is: calculating an optimal target value of the high risk group;
the second objective is: calculating an infection degree optimization target value;
s3: selecting the high risk group target value and the individual with larger infection severity adaptive value according to the roulette method: selecting a high risk group target value of each individual according to the data calculated by the formulas (1) and (2); calculating individual selection probability P (xi) and cumulative probability Q (xi) of each individual;
s4, selecting two individuals with high risk group target value and larger target value of infection severity according to the roulette method of S3 to perform one-way crossing operation; the aim is to retain genes between individuals with large fitness values.
S5: performing a mutation operation;
s6: updating the individual distribution amount according to a particle swarm updating rule;
s7: a non-dominated solution set of the individual allocation amounts is obtained.
The specific steps of S1 are as follows: by randomly choosing a number between 0 and Max as x in an individualiAssignment, xiIndicating the emergency medical resource allocation amount of the ith area.
In S2, the specific steps of calculating the high risk group optimization target value are as follows: the high-risk people group in the ith area is defined as OiA person of age greater than or equal to 65 years; the ith area has a general population of MiThen, the calculation process of the optimal target value of the high risk group in the ith area is shown as formula (1):
f1(x)＝∑ixi×Oi/Mi (1)
in S2, the specific step of calculating the infection degree optimization target value is:
mainly infected degree; the number of confirmed persons in the ith area is assumed to be IiThe number of affected persons per confirmed case is AiThen, the infection degree optimization target value of the ith area is calculated as shown in formula (2):
f2(x)＝∑ixi×Ai×Ii/Mi (2)
at S3, the individual selection probability P (x)i) The formula is shown as (3); the cumulative probability Q (x)i) The formula is shown as (4); in the interval [0,1]Randomly generating a number, judging which interval the number falls in, and if the number falls in a certain interval, selecting the interval;
Figure BDA0002605962020000071
Figure BDA0002605962020000072
the specific steps of S4 are as follows: assuming that individuals A and B cross unidirectionally, half x of individuals A are randomly selectediThen to the same location of individual B; the new individual generated finally is the individual B to which the value is assigned.
The specific steps of S5 are as follows: setting a mutation threshold value to be Mu, and if the random number is smaller than Mu, starting mutation operation; the mutation rule is x in the individualiA random value between 0 and Max is assigned.
The specific steps of S6 are as follows:
after completing the mutation operation of the S5 particle group, the distribution amount of each individual is updated according to the following formula (5) and formula (6):
Figure BDA0002605962020000073
Figure BDA0002605962020000074
wherein, in the formula (5),
Figure BDA0002605962020000075
represents the individual optimum dispensing amount;
Figure BDA0002605962020000076
representing the global optimal distribution quantity of the population; c is a learning factor; r is1And r2Represents two random numbers between 0 and 1; ω is the inertial weight;
Figure BDA0002605962020000077
is an exclusive or operation that is performed,
Figure BDA0002605962020000078
operating to add the two velocity vectors to form a new velocity vector; specifically, assume that:
Figure BDA0002605962020000079
Figure BDA00026059620200000710
then
Figure BDA00026059620200000711
The detailed operation is defined as follows:
Figure BDA00026059620200000712
in equation (6): velocity vector and position vector pass
Figure BDA0002605962020000081
Forming a new position vector; suppose that:
Figure BDA0002605962020000082
Figure BDA0002605962020000083
then
Figure BDA0002605962020000084
The detailed operation is defined as follows:
Figure BDA0002605962020000085
wherein L isi＝{l1，l2，···，lkIs the set of neighbor nodes, if i equals j, then
Figure BDA0002605962020000086
If not, then,
Figure BDA0002605962020000087
the specific steps of S7 are as follows: in the multi-objective optimization algorithm, the objective function does not have the optimal solution which enables all the objective functions to reach the maximum or the minimum simultaneously. Then, after obtaining a globally optimal allocation amount through S6, a non-dominant solution is sought. If any two solutions X1And X2Suppose for an arbitrary target X1Are all superior to X2We call X1Dominating X2. If a solution is not dominated by any other solution, we call the solution a non-dominated solution. And selecting the first solution from all the non-dominant solutions as a final distribution result.
The method models the decision problem based on emergency resource allocation into a multi-objective optimization problem, and constructs two optimization objectives of high-risk population and infection degree. And then, an improved particle swarm algorithm is adopted, unidirectional crossing and variation operations are incorporated into a particle swarm optimization framework, heterogeneity and infection severity of high risk groups are balanced, and a reasonable allocation strategy of emergency medical resources is generated. The method increases the diversity of individuals and improves the characteristic that the particle swarm algorithm is easy to fall into local optimum.
The multi-objective optimization-based emergency medical resource allocation method is applied to Shenzhen. The demographic information and the number of infected persons of 10 regions in Shenzhen city are shown in Table 1:
TABLE 1
Figure BDA0002605962020000088
Figure BDA0002605962020000091
The invention relates to emergency medical resource allocation prediction of a maximum high risk group target value and a maximum infection degree target value, which is illustrated in the attached figure 2 in detail, and is mainly based on an improved particle swarm algorithm, and comprises three parts: random initialization, genetic manipulation, and particle swarm optimization frameworks. Specifically, solutions of all areas are generated randomly at the beginning, high-risk people and infection degrees are used as two optimization indexes, and the scheme with a high optimization target value is subjected to one-way cross operation by using a roulette algorithm. Then, a mutation threshold is set, and mutation operation is performed if the random number is smaller than the threshold. And optimizing the solution subjected to genetic operation by using a particle swarm framework, and finally selecting the first solution in the non-dominated solution set as the resource allocation quantity of each region.
The data presented in table 1 represent emergency medical resource allocation results obtained by the improved particle swarm algorithm with respect to two target high risk groups and the infection degree. Each pareto frontier solution shown in fig. 3 represents one feasible allocation. Different solutions may lead to different target function values for high risk groups and for prioritization of the degree of infection. The high risk group has a priority value of 4.1% to 5.0% and the infection level has a priority value of 2.5% to 3.1%. The maximum value for emergency medical material availability for the elderly or affected individuals is 7.53%. With the maximum high risk group as a target, the optimal configuration of 10 regions in Shenzhen city is estimated, and the range is from 3 per mill in the Baoan region to 705 per mill in the southern mountain region. If the infection level is targeted, the distribution ranges from 3% o of the photopic region to 705% o of the fuda region. The elderly population and the diagnosed cases in the Futian central area and the Nanshan central area are the most, and the two areas are the areas with priority for emergency medical material allocation.
Furthermore, the invention relates to an emergency medical resource allocation method based on multi-objective optimization; solutions of all areas are generated randomly at the beginning, high-risk people and infection degrees are used as two optimization indexes, and the scheme with a high optimization target value is subjected to one-way cross operation by using a roulette algorithm. Then, a mutation threshold is set, and mutation operation is performed if the random number is smaller than the threshold. And optimizing the solution subjected to genetic operation by using a particle swarm framework, and finally selecting the first solution in the non-dominated solution set as the resource allocation quantity of each region. The invention relates to an emergency medical resource allocation method based on multi-objective optimization, which sets two targets of high risk group and infection degree, balances the allocation of emergency medical resources in different regions by modeling the two targets, recommends a reasonable emergency medical resource allocation scheme for each region in the environment of emergent public health events, and helps the decision of disease prevention and control center and control the spread of potential COVID-19. The invention relates to an emergency medical resource allocation method based on multi-objective optimization, which adopts an improved particle swarm algorithm, incorporates unidirectional crossing and variation operations into a particle swarm optimization framework, balances the heterogeneity and the severity of infection of high risk groups, and generates a reasonable allocation strategy of emergency medical resources. The method increases the diversity of individuals and improves the characteristic that the particle swarm algorithm is easy to fall into local optimum.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without affecting the spirit of the invention.

Claims (9)

1. An emergency medical resource allocation method based on multi-objective optimization is characterized by comprising the following steps:
s1: randomly initializing individual distribution quantity of population: with X ═ X1,x2,...,xnExpressing the distribution quantity of individual population, wherein the position X of each individual in the population represents a solution, and the maximum total quantity of emergency resources is Max assuming n regions;
s2: an optimization target is constructed according to the high risk group and the infection degree:
the first objective is: calculating an optimal target value of the high risk group;
the second objective is: calculating an infection degree optimization target value;
s3: selecting the target value of the high risk group and the individual with larger infection severity adaptive value according to the roulette method: selecting a high risk group target value of each individual according to the data calculated by the formulas (1) and (2); calculating individual selection probability P (x) of each individuali) And cumulative probability Q (x)i)；
S4, selecting two individuals with high risk group target value and larger target value of infection severity according to the roulette method of S3 to perform one-way crossing operation;
s5: performing a mutation operation;
s6: updating the individual distribution amount according to a particle swarm updating rule;
s7: a non-dominated solution set of the individual allocation amounts is obtained.
2. The multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein the specific steps of S1 are as follows: by randomly choosing a number between 0 and Max as x in an individualiAssignment, xiIndicating the emergency medical resource allocation amount of the ith area.
3. The multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein in step S2, the calculation of the high risk group optimal target value comprises the following specific steps: high risk group in ith area is defined as OiA person of age greater than or equal to 65 years; the ith area has a general population of MiThen, the calculation process of the optimal target value of the high risk group in the ith area is shown as formula (1):
f1(x)＝∑ixi×Oi/Mi (1)
4. the multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein in S2, the specific steps of calculating the infection degree optimization target value are:
mainly infected degree; the number of confirmed persons in the ith area is assumed to be IiThe number of affected persons per confirmed case is AiThen, the infection degree optimization target value of the ith area is calculated as shown in formula (2):
f2(x)＝∑ixi×Ai×Ii/Mi (2)
5. the multi-based of claim 1Target-optimized emergency medical resource allocation method, characterized in that in S3, the individual selection probability P (x)i) The formula is shown as (3); the cumulative probability Q (x)i) The formula is shown as (4); in the interval [0,1]Randomly generating a number, judging which interval the number falls in, and if the number falls in a certain interval, selecting the interval;
Figure FDA0002605962010000021
Figure FDA0002605962010000022
6. the multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein the specific steps of S4 are as follows: assuming that individuals A and B cross unidirectionally, half x of individuals A are randomly selectediThen to the same location of individual B; the new individual generated finally is the individual B after being assigned with the value.
7. The multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein the specific steps of S5 are as follows: setting a mutation threshold value to be Mu, and if the random number is smaller than Mu, starting mutation operation; the mutation rule is x in the individualiA random value between 0 and Max is assigned.
8. The multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein the specific steps of S6 are as follows:
after completing the mutation operation of the particle group at S5, updating the allocation amount of each individual according to the following formula (5) and formula (6):
Figure FDA0002605962010000023
Figure FDA0002605962010000024
wherein, in the formula (5),
Figure FDA0002605962010000025
represents the optimal dispensing amount of the individual;
Figure FDA0002605962010000026
representing the global optimal distribution quantity of the population; c is a learning factor; r is1And r2Represents two random numbers between 0 and 1; ω is the inertial weight;
Figure FDA0002605962010000031
is an exclusive or operation that is performed,
Figure FDA0002605962010000032
operating to add the two velocity vectors to form a new velocity vector; specifically, assume that:
Figure FDA0002605962010000033
Figure FDA0002605962010000034
then
Figure FDA0002605962010000035
The detailed operation is defined as follows:
Figure FDA0002605962010000036
in equation (6): velocity vector and position vector pass
Figure FDA0002605962010000037
Form aA new position vector; suppose that:
Figure FDA0002605962010000038
Figure FDA0002605962010000039
v＝{v1，v2，…，vn}, then
Figure FDA00026059620100000310
The detailed operation is defined as follows:
Figure FDA00026059620100000311
wherein L isi＝{l1，l2，…，lkIs the set of neighbor nodes, if i equals j, then
Figure FDA00026059620100000312
If not, then,
Figure FDA00026059620100000313
9. the multi-objective optimization-based emergency medical resource allocation method according to claim 1, wherein the specific steps of S7 are as follows: after obtaining a global optimal allocation amount through S6, seeking a non-dominated solution; if any two solutions X1And X2Suppose for an arbitrary target X1Are all superior to X2Balance X1Dominating X2(ii) a If a solution is not dominated by any other solution, the solution is a non-dominated solution. And selecting the first solution from all the non-dominant solutions as a final distribution result.
CN202010738486.4A 2020-07-28 2020-07-28 Emergency medical resource allocation method based on multi-objective optimization Active CN111932001B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010738486.4A CN111932001B (en) 2020-07-28 2020-07-28 Emergency medical resource allocation method based on multi-objective optimization

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010738486.4A CN111932001B (en) 2020-07-28 2020-07-28 Emergency medical resource allocation method based on multi-objective optimization

Publications (2)

Publication Number Publication Date
CN111932001A true CN111932001A (en) 2020-11-13
CN111932001B CN111932001B (en) 2022-06-21

Family

ID=73314656

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010738486.4A Active CN111932001B (en) 2020-07-28 2020-07-28 Emergency medical resource allocation method based on multi-objective optimization

Country Status (1)

Country Link
CN (1) CN111932001B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113096787A (en) * 2021-04-19 2021-07-09 大连理工大学 Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation
CN117290200A (en) * 2023-11-23 2023-12-26 奇点数联(北京)科技有限公司 Abnormality degree analysis system

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160070864A1 (en) * 2014-09-08 2016-03-10 Douglas Bernard Dotan Healthcare hazard detection and early warning system
CN108133758A (en) * 2017-12-22 2018-06-08 涓ユ不 A kind of first aid Tele-consultation System
CN110782087A (en) * 2019-10-24 2020-02-11 大连海事大学 Offshore emergency material optimal scheduling method and system
CN113096787A (en) * 2021-04-19 2021-07-09 大连理工大学 Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160070864A1 (en) * 2014-09-08 2016-03-10 Douglas Bernard Dotan Healthcare hazard detection and early warning system
CN108133758A (en) * 2017-12-22 2018-06-08 涓ユ不 A kind of first aid Tele-consultation System
CN110782087A (en) * 2019-10-24 2020-02-11 大连海事大学 Offshore emergency material optimal scheduling method and system
CN113096787A (en) * 2021-04-19 2021-07-09 大连理工大学 Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
贾庭芳: "基于粒子群优化的离散多目标优化算法", 《中国优秀硕士论文学位论文全文数据库》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113096787A (en) * 2021-04-19 2021-07-09 大连理工大学 Combined decision-making system and method for data-driven epidemic situation detection and medical resource allocation
CN117290200A (en) * 2023-11-23 2023-12-26 奇点数联(北京)科技有限公司 Abnormality degree analysis system
CN117290200B (en) * 2023-11-23 2024-01-23 奇点数联(北京)科技有限公司 Abnormality degree analysis system

Also Published As

Publication number Publication date
CN111932001B (en) 2022-06-21

Similar Documents

Publication Publication Date Title
Elmousalami et al. Day level forecasting for Coronavirus Disease (COVID-19) spread: analysis, modeling and recommendations
Chen et al. The introduction of population migration to SEIAR for COVID-19 epidemic modeling with an efficient intervention strategy
Vadyala et al. Prediction of the number of COVID-19 confirmed cases based on K-means-LSTM
Kuo et al. Forecasting TAIFEX based on fuzzy time series and particle swarm optimization
Kabir et al. Vaccination strategies in a two-layer SIR/V–UA epidemic model with costly information and buzz effect
CN111932001B (en) Emergency medical resource allocation method based on multi-objective optimization
Miller et al. Effective vaccination strategies for realistic social networks
Meng et al. Analysis of epidemic vaccination strategies on heterogeneous networks: Based on SEIRV model and evolutionary game
Zhao et al. A binary particle swarm optimizer with priority planning and hierarchical learning for networked epidemic control
Shi et al. Intervention optimization for crowd emotional contagion
Minoza et al. COVID-19 agent-based model with multi-objective optimization for vaccine distribution
Zandavi et al. Forecasting the spread of Covid-19 under control scenarios using LSTM and dynamic behavioral models
Gao et al. Modeling covid-19 with mean field evolutionary dynamics: Social distancing and seasonality
Sun et al. A complex network-based vaccination strategy for infectious diseases
Wang et al. An agent-based simulation model of pedestrian evacuation based on bayesian nash equilibrium
Yanez et al. Towards the Control of Epidemic Spread: Designing Reinforcement Learning Environments.
Armaou et al. Designing social distancing policies for the COVID-19 pandemic: A probabilistic model predictive control approach
CN106127427A (en) Multiple target transport path combined optimization method based on plague Epidemic Model
Purwandari et al. Forecasting model of COVID-19 pandemic in Malaysia: An application of time series approach using neural network
Lee et al. Online indoor fire evacuation system
CN106600100A (en) Reason analysis method for danger source based on weighted multi-population particle swarm optimization (PSO)
CN106126897A (en) Multiple target transport path optimization method based on HIV Infectious Dynamics
Zhang et al. A new insight in medical resources scheduling of physical examination with adaptive collaboration
Li et al. Multi-objective fuzzy surgical scheduling during post-disaster with Nash equilibrium
Liu et al. Imitation and memory-based self-organizing behaviors under voluntary vaccination

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant