CN108922609B - Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree - Google Patents
Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree Download PDFInfo
- Publication number
- CN108922609B CN108922609B CN201810778588.1A CN201810778588A CN108922609B CN 108922609 B CN108922609 B CN 108922609B CN 201810778588 A CN201810778588 A CN 201810778588A CN 108922609 B CN108922609 B CN 108922609B
- Authority
- CN
- China
- Prior art keywords
- patient
- examination
- optimal solution
- ant
- examined
- 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
Images
Classifications
-
- 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
- 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
- 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"
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Public Health (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Epidemiology (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Catching Or Destruction (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a single-machine medical examination scheduling method and system based on an ant colony algorithm under the consideration of deterioration degree, and a storage medium, wherein the method comprises the following steps: s100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the latest moment when each patient starts to be examined; s200, determining an optimal solution of the objective function by adopting a preset ant colony algorithm, and sequencing the examination patients of the stand-alone medical examination equipment according to the optimal solution. The objective function adopted by the invention is reasonable, the patient examination sequence obtained by solving the objective function can reduce the influence of the overall illness state deterioration of the patient caused by waiting, and simultaneously improve the medical service level of the hospital and the satisfaction degree of the patient.
Description
Technical Field
The invention relates to the technical field of intelligent medical treatment, in particular to a single-machine medical examination scheduling method and system based on an ant colony algorithm under the condition of considering the deterioration degree and a storage medium.
Background
At present, most medical examinations follow the principle of first-come first-serve, the severity of the illness state of patients is not considered in the method, different patients exceed the respective time limit for the same time, and the influence on subsequent treatment is different, so that a plurality of patients cannot obtain timely medical examinations according to the principle of first-come first-serve, the patients are injured, and the overall treatment effect of a hospital is reduced.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides a single-machine medical examination scheduling method, a single-machine medical examination scheduling system and a storage medium based on an ant colony algorithm under the consideration of the deterioration degree, which can provide a reasonable patient examination sequence, thereby reducing the influence of the deterioration of the condition of a patient caused by the overall waiting of the patient and simultaneously improving the medical service level of a hospital and the satisfaction degree of the patient.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
in a first aspect, the present invention provides an ant colony algorithm-based standalone medical examination scheduling method considering a deterioration degree, including:
s100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the latest moment when each patient starts to be examined; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
s200, determining an optimal solution of a target function by adopting a preset ant colony algorithm, and sequencing examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all examined patients as an optimization objective, and the deterioration degree of each patient is set according to a penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient;
the determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; the initial parameters at least comprise the number of ants, an initial value of the concentration of the path pheromone, the maximum iteration times and an initial value of a global optimal solution;
s202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
s203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
s204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
s205, updating the concentration of the path pheromone;
s206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
In a second aspect, the present invention provides an ant colony algorithm-based standalone medical examination scheduling system considering a degree of deterioration, comprising:
the acquisition module is used for executing S100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the time when each patient begins to be examined at the latest; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
the solving module is used for executing S200, determining an optimal solution of the objective function by adopting a preset ant colony algorithm, and sequencing the examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all examined patients as an optimization objective, and the deterioration degree of each patient is set according to a penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient;
the determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; the initial parameters at least comprise the number of ants, an initial value of the concentration of the path pheromone, the maximum iteration times and an initial value of a global optimal solution;
s202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
s203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
s204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
s205, updating the concentration of the path pheromone;
s206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
In a third aspect, the present invention provides a computer storage medium having stored thereon a computer program which, when executed by a processor, is operable to carry out the method described above.
(III) advantageous effects
The embodiment of the invention provides a single-machine medical examination scheduling method, a single-machine medical examination scheduling system and a single-machine medical examination scheduling storage medium based on an ant colony algorithm under the consideration of the degree of deterioration, wherein an objective function with the minimum total degree of deterioration of all examined patients as an optimization target is adopted, the degree of deterioration of each examined patient is determined according to a penalty factor of each patient, the latest moment when each patient starts to be examined and the examination duration of each examined patient, and the penalty factor is set according to the severity of the patient's disease.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating an ant colony algorithm-based standalone medical examination scheduling method considering a deterioration degree according to an embodiment of the present invention;
fig. 2 is a block diagram illustrating a stand-alone medical examination scheduling system based on an ant colony optimization considering a degree of deterioration in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In a first aspect, the present invention provides an ant colony algorithm-based standalone medical examination scheduling method considering a deterioration degree, as shown in fig. 1, the method including:
s100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the latest moment when each patient starts to be examined; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
understandably, the more severe the condition of the patient under examination, the greater the penalty factor.
It is understood that the time at which the patient starts to receive the examination at the latest is the latest time point in the examination period of the patient. The time at which the latest start of examination of the examination patient j is taken can be expressed as
j 1,2, N is the number of patients examined.
S200, determining an optimal solution of a target function by adopting a preset ant colony algorithm, and sequencing examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all the examined patients as the optimization objective, and the deterioration degree of each patient is set according to the penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient.
It will be appreciated that N patients under examination need to be medically examined on 1 medical examination device, each patient under examination having a latest examination deadline, and a penalty factor given to the severity of the condition. The setting of the objective function relies on the following assumptions:
(1) interruption is not allowed in the checking process, and checking is not allowed to stop in the midway;
(2) disregarding deteriorating effects of the inspection apparatus;
(3) the medical examination apparatus does not malfunction.
The determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; wherein the initial parameters at least comprise the number of ants and the initial value tau of the concentration of the path pheromone0Maximum iteration times and initial values of the global optimal solution;
it is understood that the number of ants in a colony, i.e., the population-scale popsize, can be such that popsize > 2 XN.
It will be appreciated that the path is made up of adjacent examination patients, and that different examination patients or different pre-and post-examination sequences are different paths.
In fact, it is firstThe initial parameter may include, in addition to the above parameters, an initial number of first exams of each patient in the optimal solution, which is 1. For example, fj＝1,j＝1,2,...,N，fjTo examine the initial number of first exams of patient j in the optimal solution.
Of course, the initial parameters may also include an pheromone concentration parameter δ, a heuristic value parameter β, a current iteration number of 1, and a current optimal solution S*The initial value of global optimal solution gbest, etc.
S202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
in practical applications, the step S202 may be specifically implemented by the following steps, that is, for each ant, a feasible solution of the ant may be obtained through the following steps:
s2021, respectively appointing a first examination patient for each ant in the first N ants, wherein the first examination patients corresponding to any two ants in the first N ants are different; wherein N is the number of patients to be examined;
s2022, calculating the probability of the first examination of each examination patient according to a first formula, wherein the first formula comprises:
in the formula, PFjTo examine the probability of patient j first examination, fjThe current number of first exams in the optimal solution for exam patient j; n is the number of patients examined;
it can be understood that, in the first iteration process, because the number of times of the first examination of each examination patient in the optimal solution is 1, the probability of the first examination of each examination patient is the same and is 1/N. As the number of iterations increases, the probability of the first examination of one or more examined patients in the optimal solution also changes.
S2023, calculating the cumulative probability of the first examination of each examination patient according to a second formula, wherein the second formula comprises:
in the formula, QFjCumulative probability of first examination for examination patient j;
for example, when j is 1, the cumulative probability of examining patient j the first examination is PF1(ii) a When j is 2, the cumulative probability of examining patient j the first examination is PF1+PF2(ii) a When j is 3, the cumulative probability of examining patient j the first examination is PF1+PF2+PF3。
S2024, aiming at each ant in the later (popsize-N) ants, generating a random number within the range of [0,1], determining the minimum cumulative probability which is more than or equal to the random number, and taking the examination patient corresponding to the minimum cumulative probability as the patient to be examined first in the feasible solutions corresponding to the ant; wherein the popsize is the number of ants;
for example, for a certain ant, the generated random number is Rand; if Rand is less than or equal to QF1Then the patient 1 to be examined is taken as the patient to be examined first in the feasible solution corresponding to the ant; if QFk-1≤Rand≤QFkThen the patient k will be examined as the first examined patient in the feasible solution corresponding to the ant.
S2025, aiming at each ant, determining the state transition probability between the first patient to be examined and any patient to be examined in the next patient selectable set according to the pheromone concentration parameter, the heuristic value parameter, the latest moment of starting to receive examination of other patients except the first patient to be examined and the pheromone concentration between the patients, and determining the next patient to be examined after the first patient according to the state transition probability; the first patient is a patient for which an examination order has been determined;
in step S2024, a third formula may be specifically adopted to calculate a state transition probability between the inspection patient r and the inspection patient e in the kth ant, where the third formula includes:
in the formula etareTo examine the heuristic between patient r and patient e,
denotes the latest starting moment of the examination of the patient e, τreDenotes the pheromone concentration between patient r and patient e, delta is a heuristic parameter, beta is a pheromone concentration parameter, Jk(r) represents the next patient alternative after patient r,
the probability of examination e after the examination of the patient r in the kth ant is shown, namely the probability of state transition between the examination patient r and the examination patient e.
For example, when the patient for the first examination in the feasible solution corresponding to the k-th (k is greater than N) ant is determined according to steps S2022 to S2024, the state transition probability between the patient for the first examination and each of the patients for examination in the next patient selectable set formed by the other patients is calculated according to the third formula, and the patient corresponding to the maximum state transition probability is selected as the patient for the second examination in the feasible solution corresponding to the k-th ant. And then according to a third formula, the state transition probability between each patient in the next patient selectable set formed by the patient in the second examination and other patients except the patient in the first two examinations is selected, the patient corresponding to the maximum state transition probability is selected as the patient in the third examination in the feasible solution corresponding to the kth ant, and the like, and the examination sequence of the remaining N-3 patients in the feasible solution corresponding to the kth ant is determined.
It will be appreciated that for each leechAnd the ant forms a feasible solution corresponding to the ant after determining the examination sequence of the N examination patients. For example, a feasible solution constructed for the jth ant is:
the patient of the ith examination in the feasible solution corresponding to the jth ant is shown.
S203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
in practical application, the deterioration degree of the feasible solution corresponding to each ant can be calculated through the following steps:
s2031, calculating the time when each patient starts to receive examination in the feasible solution corresponding to the ant by adopting a fourth formula, wherein the fourth formula comprises:
i＝1,2,...,N，j＝1,2,...,popsize
in the formula (I), the compound is shown in the specification,
representing the ith patient to be checked in the feasible solution corresponding to the jth ant;
the moment when the ith patient to be checked starts to be checked in the feasible solution corresponding to the jth ant is shown;
representing the examination duration of the ith patient to be examined in the feasible solution corresponding to the jth ant, wherein the popsize is the number of ants, and the N is the number of patients to be examined;
for example, for the jth ant, the time when the patient in the first examination starts to receive the examination is the initial time and is set to 0; when the patient in the first examination finishes the examination, the patient in the second examination starts to receive the examination, so that the moment when the patient in the second examination starts to receive the examination is the initial moment + the examination duration of the patient in the first examination; when the second examined patient finishes the examination, the third examined patient starts to be examined, so that the moment when the third examined patient starts to be examined is the initial moment + the examination duration of the first examined patient + the examination duration of the second examined patient; by analogy, the time when each patient starts to receive the examination in the feasible solution corresponding to the jth ant can be obtained.
S2032, calculating the deterioration degree of each patient in the feasible solution corresponding to the ant by adopting a fifth formula, wherein the fifth formula comprises:
in the formula (I), the compound is shown in the specification,
represents the moment when the ith patient in the feasible solution corresponding to the jth ant begins to receive the examination at the latest,
represents the penalty factor corresponding to the ith patient to be checked in the feasible solution corresponding to the jth ant,
representing the deterioration degree of the ith patient to be checked in the feasible solution corresponding to the jth ant;
as can be seen from the fifth formula, when the time when the patient starts to receive the examination is earlier than the time when the patient starts to receive the examination at the latest, the degree of deterioration of the patient is 0. When the time when the patient starts to receive the examination is later than the time when the patient starts to receive the examination at the latest, the patient is overdue examination, and the condition of the patient may be deteriorated, so that the deterioration degree is not 0, and the product of the penalty factor and the overdue time is used as the deterioration degree of the patient. Therefore, the degree of deterioration not only takes the time-out period into consideration, but also takes the severity of the illness of the patient into consideration, and is more practical.
S2033, accumulating the deterioration degree of each inspection patient in the feasible solution corresponding to the ant to obtain the deterioration degree of the feasible solution corresponding to the ant.
For example, the total deterioration degree of all patients under the feasible solution is obtained by summing the deterioration degrees of the patients in the feasible solution corresponding to the kth ant, which can also be referred to as the deterioration degree corresponding to the kth ant.
In practical application, the following formula can be used to calculate the deterioration degree W of the feasible solution corresponding to the jth antT(Sj)：
In the above formula, the first and second carbon atoms are,
and (5) the worsening procedure of the ith examination patient in the feasible solution corresponding to the jth ant.
After the deterioration degree of the feasible solution corresponding to each ant is obtained, the feasible solution with the lowest deterioration degree can be selected as the current optimal solution.
S203+1, performing neighborhood change search on the current optimal solution to find ant codes with the deterioration degree lower than that of the current optimal solution in the neighborhood of the current optimal solution, and updating the current optimal solution into the ant codes.
It can be understood that the ant code is a solution obtained by performing some transformation on the current optimal solution, and may be referred to as an ant code, so that the fine adjustment of the patient examination sequence corresponding to the current optimal solution can be realized.
Here, a variable neighborhood search is performed on the current optimal solution, thereby obtaining a solution in which the current optimal solution is less deteriorated in the neighborhood.
When the number of neighborhoods is set to 2, step S203+1 may specifically be implemented by:
a1, defining a neighborhood structure NkK is 1 or 2; initializing k to 1;
a2, x is 1, y is 2; if k is 1, go to step a 3; if k is 2, go to step a 7;
it will be appreciated that when k is 1, the neighborhood structure N can be entered1Searching; when k is 2, the neighborhood structure N can be entered2To perform a search.
A3, moving the value of the x place in the current optimal solution to the y place, and then moving the value from the x +1 place to the original y place to the x place to the y-1 place to obtain a new ant code;
for example, if the current optimal solution is (1, 2, 3, 4, 5, 6), x is 2, y is 5, the new ant is coded as (1, 3, 4, 5, 2, 6).
A4, judging whether y is equal to the number N of patients to be examined:
if yes, making y equal to x + 2;
otherwise, add 1 to y and return to step A3;
a5, adding 1 to x, and judging whether x is smaller than N: if yes, returning to the step A3; otherwise, go to step A6;
a6, calculating the deterioration degree of all newly generated ant codes, and judging whether the lowest deterioration degree in the deterioration degrees corresponding to each newly generated ant code is lower than the deterioration degree of the current optimal solution:
if yes, updating the current optimal solution to the ant code corresponding to the lowest deterioration degree, and returning to the step A3;
otherwise, let k be 2, and return to step A2;
a7, exchanging the values of the x place and the y place in the current optimal solution to obtain a new ant code;
for example, if the current optimal solution is (1, 2, 3, 4, 5, 6), x is 2, y is 5, the new ant is coded as (1, 5, 3, 4, 2, 6).
A8: determining whether y is equal to the number of examined patients N:
if yes, the step b is executed to enable y to be x +2, and the step b is executed to step a 9;
otherwise, adding 1 to y and returning to the step A7;
a9, adding 1 to x, and judging whether x is less than the number N of patients to be examined:
if yes, returning to the step A7;
otherwise, go to step A10;
a10, calculating the deterioration degrees corresponding to all newly generated ant codes, and judging whether the lowest deterioration degree in the deterioration degrees corresponding to each newly generated ant code is lower than the deterioration degree of the current optimal solution:
if yes, updating the current optimal solution to the ant code corresponding to the lowest deterioration degree, enabling k to be 1, and returning to the step A2;
otherwise, ending the variable neighborhood searching process.
And when the solution with lower deterioration degree cannot be searched in the two neighborhood structures, ending the neighborhood variation searching process.
It is understood that for the basic purpose of the present invention, the step of performing the variable neighborhood search on the current optimal solution is not necessary, and therefore, the step of S203+1 may not be included in some embodiments.
S203+2, adding 1 to the number of times of the first examination of the patient in the current optimal solution;
here, the number of first exams of the patient in the optimal solution is updated, and only the patient for the first exam in the current optimal solution is updated.
When the patient for the first examination in the ant feasible solution is not determined according to the number of times that the patient performs the first examination in the optimal solution in step S202, the initial number of times that each patient performs the first examination in the optimal solution may not be included in the initial parameters, and step S203+2 is not necessarily included.
S204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
generating a current optimal solution in each iteration process, and replacing the global optimal solution with the current optimal solution if the deterioration degree of the current optimal solution is lower than that of the global optimal solution; of course, if the degree of deterioration of the current optimal solution is higher than or equal to the degree of deterioration of the global optimal solution, it is not necessary to update the global optimal solution. Through the above process, a best solution, i.e. a global optimal solution, generated from the first iteration process to the current iteration process can be obtained.
S205, updating the concentration of the path pheromone;
since the concentration of the path pheromone does not always remain the same, the concentration of the path pheromone needs to be updated, but the concentration of the pheromone in different paths changes differently, so that the concentration of the path pheromone can be updated by the following steps:
s2051, performing pheromone volatilization operation on each path in the non-volatilization-prohibited path set by adopting a sixth formula, wherein the sixth formula comprises the following steps:
wherein E' is a set of non-forbidden volatilization paths, τijConcentration of pheromone for the pathway between the ith and jth examination patient, τi'jFor the concentration after the volatilization operation of the pheromone of the pathway between the ith patient and the jth patient, ρ is a volatilization parameter and is [0,1]]Within the range;
in step S2051, the pheromone volatilization operation is performed only on the paths in the set of non-volatilization-prohibited paths, but actually, the pheromone volatilization operation may be performed on all the paths, then the volatilization-prohibited paths are screened out, and then the pheromone recovery operation is performed on the volatilization-prohibited paths, that is, how much volatilization has been performed before for the volatilization-prohibited paths, which is recovered, for example, by using the following formula:
and A is a set of volatilization forbidding paths, and the pheromone concentration of the volatilization forbidding paths can be recovered through the formula.
S2052, performing pheromone increasing operation on the path corresponding to the current optimal solution by adopting a seventh formula, wherein the seventh formula comprises the following steps:
in the formula, s*For the current optimal solution, WT(s*) For the degree of deterioration of the current optimal solution, E*For the path set corresponding to the current optimal solution, τ* ijIs E*The concentration of pheromone in the pathway between the ith and jth examination patients, τ** ijIs pair E*The concentration of the pheromone of the path between the ith examination patient and the jth examination patient after the increasing operation is performed, and theta is a positive constant;
here, the pheromone increasing operation is performed on the path in the current optimal solution, so that the pheromone concentration of the path in the current optimal solution can be increased.
S3053, screening out the lowest concentration value of the pheromone concentrations among all paths, and screening out the lowest concentration value
The concentration of pheromone at the position is forbidden concentration; wherein N is the number of patients to be examined;
here, the pheromone concentrations between all paths may be sorted to obtain the lowest concentration value among them.
Means a maximum integer no greater than N (N-1) x 0.7.
It will be appreciated that,
pheromone concentration at a location is referred to in the global optimal solution
Pheromone concentration at the site.
S3054, judging whether a path with the pheromone concentration larger than the forbidden concentration exists in the volatilization-forbidden path set or not, and if so, removing the path with the pheromone concentration larger than the forbidden concentration from the volatilization-forbidden path set;
that is, when the pheromone concentration of the path in the volatilization-inhibited path set is greater than the forbidden concentration, the pheromone is removed from the volatilization-inhibited path set to become a non-volatilization-inhibited path.
S3055, judging whether the number of ants corresponding to the current optimal solution is larger than the number of ants corresponding to the current optimal solution
popsize is the number of ants:
if yes, performing negative feedback regulation on the pheromone concentration of the path corresponding to the current optimal solution by adopting an eighth formula, emptying the volatilization prohibition path set, and adding the path corresponding to the current optimal solution into the volatilization prohibition path set; the eighth formula includes:
in the formula, tauijIs to tau** ijPheromone concentration, tau, after negative feedback adjustmentminIs the lowest concentration value;
otherwise, ending the updating process of the path pheromone concentration.
It can be understood that after convergence, most of the feasible solutions corresponding to the ants are the current optimal solutions, and only a few of the feasible solutions corresponding to the ants are not the current optimal solutions. Here, the number of ants corresponding to the current optimal solution is the number of ants converging in the current optimal solution.
That is to say, when the number of ants converging at the current optimal solution exceeds a certain number, the concentration of the path pheromone of the current optimal solution is reduced, the volatilization-prohibited path set is emptied, and the path corresponding to the current optimal solution is added to the volatilization-prohibited path set.
It can be understood that a general ant colony algorithm is easy to fall into the problem of local optimum, but the ant colony algorithm provided by the invention designs a pheromone negative feedback regulation mechanism, thereby not only effectively improving the convergence speed and the diversity of solution of the algorithm, but also strengthening the local convergence capability at the end of the algorithm to a certain extent. The ant colony algorithm provided by the invention is an algorithm with high efficiency on the convergence speed and the convergence result, and by the algorithm, the problem of medical examination scheduling is solved, the influence of disease deterioration of patients caused by unreasonable examination sequence is reduced, and the overall treatment effect of hospitals is improved.
S206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
The sequencing method provided by the invention adopts an objective function which takes the minimum total deterioration degree of all examined patients as an optimization target, and the deterioration degree of each examined patient is determined according to a penalty factor of each patient, the latest moment when each patient starts to be examined and the examination duration of each examined patient, wherein the penalty factor is set according to the disease severity of the patient, so that the objective function adopted by the sequencing method is reasonable, the influence of the disease deterioration of the patient caused by the whole waiting of the patient can be reduced through the examination sequence of the patient obtained by solving the objective function, and the medical service level of a hospital and the satisfaction degree of the patient are improved.
In a second aspect, the present invention provides an ant colony algorithm-based standalone medical examination scheduling system considering a degree of deterioration, as shown in fig. 2, the system comprising:
the acquisition module is used for executing S100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the time when each patient begins to be examined at the latest; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
the solving module is used for executing S200, determining an optimal solution of the objective function by adopting a preset ant colony algorithm, and sequencing the examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all examined patients as an optimization objective, and the deterioration degree of each patient is set according to a penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient;
the determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; the initial parameters at least comprise the number of ants, an initial value of the concentration of the path pheromone, the maximum iteration times and an initial value of a global optimal solution;
s202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
s203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
s204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
s205, updating the concentration of the path pheromone;
s206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
In some embodiments, before comparing the deterioration degrees of the current optimal solution and the global optimal solution, the solving module may further perform a variable neighborhood search on the current optimal solution to find an ant code in a neighborhood of the current optimal solution, where the deterioration degree of the ant code is lower than the deterioration degree of the current optimal solution, and update the current optimal solution to the ant code.
It can be understood that the sorting system provided by the present invention corresponds to the sorting method, and the explanation, examples, specific embodiments, beneficial effects, and other contents of the related contents thereof can refer to the related contents in the sorting method, and are not described herein again.
In a third aspect, the present invention provides a computer storage medium having a computer program stored thereon, which when executed by a processor, implements the method provided by the first aspect.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A single machine medical examination scheduling method based on an ant colony algorithm under the consideration of deterioration degree is characterized by comprising the following steps:
s100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the latest moment when each patient starts to be examined; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
s200, determining an optimal solution of a target function by adopting a preset ant colony algorithm, and sequencing examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all examined patients as an optimization objective, and the deterioration degree of each patient is set according to a penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient;
the determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; the initial parameters at least comprise the number of ants, an initial value of the concentration of the path pheromone, the maximum iteration times and an initial value of a global optimal solution;
s202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
s203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
s204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
s205, updating the concentration of the path pheromone;
s206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
2. The method of claim 1, wherein prior to comparing the degree of deterioration of the current optimal solution with the global optimal solution, the method further comprises:
and performing variable neighborhood search on the current optimal solution to find ant codes with the deterioration degree lower than that of the current optimal solution in the neighborhood of the current optimal solution, and updating the current optimal solution into the ant codes.
3. The method as claimed in claim 2, wherein the performing a variable neighborhood search on the current optimal solution to find an ant code whose deterioration degree is lower than that of the current optimal solution in the neighborhood of the current optimal solution and update the current optimal solution to the ant code specifically comprises:
a1, defining a neighborhood structure NkK is 1 or 2; initializing k to 1;
a2, x is 1, y is 2; if k is 1, go to step a 3; if k is 2, go to step a 7;
a3, moving the value of the x place in the current optimal solution to the y place, and then moving the value from the x +1 place to the original y place to the x place to the y-1 place to obtain a new ant code;
a4, judging whether y is equal to the number N of patients to be examined:
if yes, making y equal to x + 2;
otherwise, add 1 to y and return to step A3;
a5, adding 1 to x, and judging whether x is smaller than N: if yes, returning to the step A3; otherwise, go to step A6;
a6, calculating the deterioration degree of all newly generated ant codes, and judging whether the lowest deterioration degree in the deterioration degrees corresponding to each newly generated ant code is lower than the deterioration degree of the current optimal solution:
if yes, updating the current optimal solution to the ant code corresponding to the lowest deterioration degree, and returning to the step A3;
otherwise, let k be 2, and return to step A2;
a7, exchanging the values of the x place and the y place in the current optimal solution to obtain a new ant code;
a8: determining whether y is equal to the number of examined patients N:
if yes, the step b is executed to enable y to be x +2, and the step b is executed to step a 9;
otherwise, adding 1 to y and returning to the step A7;
a9, adding 1 to x, and judging whether x is less than the number N of patients to be examined:
if yes, returning to the step A7;
otherwise, go to step A10;
a10, calculating the deterioration degrees corresponding to all newly generated ant codes, and judging whether the lowest deterioration degree in the deterioration degrees corresponding to each newly generated ant code is lower than the deterioration degree of the current optimal solution:
if yes, updating the current optimal solution to the ant code corresponding to the lowest deterioration degree, enabling k to be 1, and returning to the step A2;
otherwise, ending the variable neighborhood searching process.
4. The method of claim 1, wherein the initial parameters further include an initial number of first exams in the optimal solution, a pheromone concentration parameter, and a heuristic value parameter for each patient; wherein the initial number of times is 1;
correspondingly, generating an examination order of each examination patient for each ant to obtain a corresponding feasible solution, including:
s2021, respectively appointing a first examination patient for each ant in the first N ants, wherein the first examination patients corresponding to any two ants in the first N ants are different; wherein N is the number of patients to be examined;
s2022, calculating the probability of the first examination of each examination patient according to a first formula, wherein the first formula comprises:
in the formula, PFjTo examine the probability of patient j first examination, fjThe current number of first exams in the optimal solution for exam patient j; n is the number of patients examined;
s2023, calculating the cumulative probability of the first examination of each examination patient according to a second formula, wherein the second formula comprises:
in the formula, QFjCumulative probability of first examination for examination patient j;
s2024, aiming at each ant in the later (popsize-N) ants, generating a random number within the range of [0,1], determining the minimum cumulative probability which is more than or equal to the random number, and taking the examination patient corresponding to the minimum cumulative probability as the patient to be examined first in the feasible solutions corresponding to the ant; wherein the popsize is the number of ants;
s2025, aiming at each ant, determining the state transition probability between the first examination patient and any examination patient in the next patient selectable set according to the pheromone concentration parameter, the heuristic value parameter, the latest examination starting time of other examination patients except the first examination patient and the pheromone concentration among the patients, and determining the next examination patient after the first examination patient according to the state transition probability; the first examination patient is a patient for which an examination order has been determined;
correspondingly, before comparing the deterioration degree of the current optimal solution with the global optimal solution, the method further comprises: adding 1 to the number of first exams in the optimal solution of the patient of the first exam in the current optimal solution.
5. The method as claimed in claim 4, wherein the probability of state transition between the examined patient r and the examined patient e in the kth ant is calculated using a third formula, the third formula comprising:
in the formula etareTo examine the heuristic between patient r and patient e,
denotes the latest starting moment of the examination of the patient e, τreDenotes the pheromone concentration between patient r and patient e, delta is a heuristic parameter, beta is a pheromone concentration parameter, Jk(r) represents the next patient alternative after patient r,
the probability of examination e after the examination of the patient r in the kth ant is shown, namely the probability of state transition between the examination patient r and the examination patient e.
6. The method as claimed in claim 1, wherein the determining the degree of deterioration corresponding to the feasible solution corresponding to each ant comprises:
s2031, calculating the time when each patient starts to receive examination in the feasible solution corresponding to the ant by adopting a fourth formula, wherein the fourth formula comprises:
in the formula (I), the compound is shown in the specification,
representing the ith patient to be checked in the feasible solution corresponding to the jth ant;
the moment when the ith patient to be checked starts to be checked in the feasible solution corresponding to the jth ant is shown;
representing the examination duration of the ith patient to be examined in the feasible solution corresponding to the jth ant, wherein the popsize is the number of ants, and the N is the number of patients to be examined;
s2032, calculating the deterioration degree of each patient in the feasible solution corresponding to the ant by adopting a fifth formula, wherein the fifth formula comprises:
in the formula (I), the compound is shown in the specification,
represents the moment when the ith patient in the feasible solution corresponding to the jth ant begins to receive the examination at the latest,
represents the penalty factor corresponding to the ith patient to be checked in the feasible solution corresponding to the jth ant,
representing the deterioration degree of the ith patient to be checked in the feasible solution corresponding to the jth ant;
s2033, accumulating the deterioration degree of each inspection patient in the feasible solution corresponding to the ant to obtain the deterioration degree of the feasible solution corresponding to the ant.
7. The method of claim 1, wherein the updating the concentration of the way pheromone comprises:
s2051, performing pheromone volatilization operation on each path in the non-volatilization-prohibited path set by adopting a sixth formula, wherein the sixth formula comprises the following steps:
wherein E' is a set of non-forbidden volatilization paths, τijConcentration of pheromone, τ ', of the pathway between the ith and jth examination patients'ijIn order to obtain the concentration of the pheromone after the volatilization operation of the path between the ith patient and the jth patient, rho is a volatilization parameter and is in [0,1]]Within the range;
s2052, performing pheromone increasing operation on the path corresponding to the current optimal solution by adopting a seventh formula, wherein the seventh formula comprises the following steps:
in the formula, s*For the current optimal solution, WT(s*) For the degree of deterioration of the current optimal solution, E*For the path set corresponding to the current optimal solution, τ* ijIs E*The concentration of pheromone in the pathway between the ith and jth examination patients, τ** ijIs pair E*The concentration of the pheromone of the path between the ith examination patient and the jth examination patient after the increasing operation is carried out, and theta is a positive constant;
s3053, screening out the lowest concentration value of the pheromone concentrations among all paths, and screening out the lowest concentration value
The concentration of pheromone at the position is forbidden concentration; wherein N is the number of patients to be examined;
s3054, judging whether a path with the pheromone concentration larger than the forbidden concentration exists in the volatilization-forbidden path set or not, and if so, removing the path with the pheromone concentration larger than the forbidden concentration from the volatilization-forbidden path set;
s3055, judging whether the number of ants corresponding to the current optimal solution is larger than the number of ants corresponding to the current optimal solution
popsize is the number of ants:
if yes, performing negative feedback regulation on the pheromone concentration of the path corresponding to the current optimal solution by adopting an eighth formula, emptying the volatilization prohibition path set, and adding the path corresponding to the current optimal solution into the volatilization prohibition path set; the eighth formula includes:
in the formula, tauijIs to tau** ijPheromone concentration, tau, after negative feedback adjustmentminIs the lowest concentration value;
otherwise, ending the updating process of the path pheromone concentration.
8. A standalone medical examination scheduling system based on ant colony algorithm considering a degree of deterioration, comprising:
the acquisition module is used for executing S100, acquiring the number of patients to be examined of the stand-alone medical examination equipment, the examination duration of each patient to be examined, a penalty factor corresponding to each patient to be examined and the time when each patient begins to be examined at the latest; wherein the penalty factor is set according to the disease severity of the corresponding examination patient;
the solving module is used for executing S200, determining an optimal solution of the objective function by adopting a preset ant colony algorithm, and sequencing the examination patients of the stand-alone medical examination equipment according to the optimal solution; the objective function takes the total deterioration degree of all examined patients as an optimization objective, and the deterioration degree of each patient is set according to a penalty factor corresponding to the patient, the time when the patient starts to be examined at the latest and the examination duration of each examined patient;
the determining the optimal solution of the objective function by adopting the preset ant colony algorithm includes:
s201, setting initial parameters of the ant colony algorithm; the initial parameters at least comprise the number of ants, an initial value of the concentration of the path pheromone, the maximum iteration times and an initial value of a global optimal solution;
s202, aiming at each ant, generating an inspection sequence of each inspection patient to obtain a corresponding feasible solution;
s203, determining the deterioration degree corresponding to the feasible solution corresponding to each ant according to the number of the examination patients, the examination duration of each examination patient, the penalty factor corresponding to each examination patient and the latest moment when each patient starts to be examined, and taking the feasible solution with the lowest deterioration degree as the current optimal solution;
s204, comparing the deterioration degree of the current optimal solution with the deterioration degree of the global optimal solution, and if the deterioration degree of the current optimal solution is lower than the deterioration degree of the global optimal solution, updating the global optimal solution into the current optimal solution;
s205, updating the concentration of the path pheromone;
s206, judging whether the current iteration times are less than the maximum iteration times:
if yes, adding 1 to the current iteration number, and returning to the step S202;
otherwise, the global optimal solution is used as the optimal solution of the objective function.
9. The system as claimed in claim 8, wherein the solving module further performs a variable neighborhood search on the current optimal solution before comparing the degrees of deterioration of the current optimal solution and the global optimal solution to find ant codes in the neighborhood of the current optimal solution, the ant codes having a degree of deterioration lower than that of the current optimal solution, and updates the current optimal solution to the ant codes.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, is adapted to carry out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810778588.1A CN108922609B (en) | 2018-07-16 | 2018-07-16 | Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810778588.1A CN108922609B (en) | 2018-07-16 | 2018-07-16 | Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108922609A CN108922609A (en) | 2018-11-30 |
| CN108922609B true CN108922609B (en) | 2021-08-10 |
Family
ID=64412986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810778588.1A Active CN108922609B (en) | 2018-07-16 | 2018-07-16 | Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108922609B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113555096B (en) * | 2021-06-10 | 2023-06-30 | 合肥工业大学 | Operating room scheduling method and system considering doctor scheduling condition |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103246811A (en) * | 2013-04-25 | 2013-08-14 | 中山大学 | Medical system admission scheduling method based on ant colony optimization |
| CA2961538A1 (en) * | 2014-09-19 | 2016-03-24 | Mayank GOYAL | Systems and methods for obtaining and displaying medical data to assist decision making during a medical emergency |
| CN106485355B (en) * | 2016-10-12 | 2019-11-26 | 创业软件股份有限公司 | A kind of medical treatment route optimization method based on outpatient service big data analysis |
| CN107799182A (en) * | 2017-10-16 | 2018-03-13 | 陈昕 | The evaluation method and electronic equipment of complication and complication factor of influence |
-
2018
- 2018-07-16 CN CN201810778588.1A patent/CN108922609B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN108922609A (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Abellán et al. | Bagging schemes on the presence of class noise in classification | |
| Soto et al. | Using autonomous search for generating good enumeration strategy blends in constraint programming | |
| Thakkar et al. | Health care decision support system for swine flu prediction using naïve bayes classifier | |
| CN109726819B (en) | Method and device for realizing event reasoning | |
| Battiti et al. | Local search with memory: Benchmarking RTS | |
| CN108922609B (en) | Individual medical examination scheduling method based on ant colony algorithm under consideration of deterioration degree | |
| CN113096806A (en) | Disease prediction system based on medical image algorithm and block chain | |
| CN112085157A (en) | Prediction model establishing method and device based on neural network and tree model | |
| CN115032541B (en) | Lithium ion battery capacity degradation prediction method and device | |
| Kukar et al. | Machine learning in prognosis of the femoral neck fracture recovery | |
| CN113689943A (en) | Clinic hospital recommendation method, device, equipment and medium based on artificial intelligence | |
| CN116129988B (en) | Model construction method, device, equipment and medium | |
| CN112652405A (en) | Method, device and equipment for mining clinical path and storage medium | |
| Karthikeyan et al. | Learning accurate decision trees with bandit feedback via quantized gradient descent | |
| Rossi et al. | Inferring fisheries stock status from competing hypotheses | |
| Sheng et al. | Cost-sensitive test strategies | |
| Kamarudin et al. | Prediction of COVID-19 cases in Malaysia by using machine learning: A preliminary testing | |
| Xiao et al. | A branching heuristic for SAT solvers based on complete implication graphs | |
| Olmo et al. | Association rule mining using a multi-objective grammar-based ant programming algorithm | |
| CN113657594A (en) | Soft filter pruning method, device and system | |
| CN116013522A (en) | Prediction method and system for postherpetic neuralgia | |
| Molina et al. | Applying memetic algorithm with improved L-SHADE and local search pool for the 100-digit challenge on single objective numerical optimization | |
| Kao et al. | Cost-sensitive decision tree induction with label-dependent late constraints | |
| CN110211701B (en) | Model generation method, data processing method and corresponding device | |
| Pradhan et al. | Multilayer perceptron network in HIV/AIDS application |
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 |