CN110349675A - A kind of pre- measurement equipment of cardiovascular disease and device - Google Patents
A kind of pre- measurement equipment of cardiovascular disease and device Download PDFInfo
- Publication number
- CN110349675A CN110349675A CN201910641128.9A CN201910641128A CN110349675A CN 110349675 A CN110349675 A CN 110349675A CN 201910641128 A CN201910641128 A CN 201910641128A CN 110349675 A CN110349675 A CN 110349675A
- Authority
- CN
- China
- Prior art keywords
- drosophila
- population
- parameter
- cardiovascular disease
- algorithm
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- 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
- 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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
This application discloses a kind of pre- measurement equipment of cardiovascular disease and devices, can be optimized based on parameter of the drosophila algorithm to random forests algorithm, obtain optimized parameter；And random forest prediction model is constructed according to optimized parameter；History cardiovascular disease data are finally inputted into random forest prediction model, obtain cardiovascular disease prediction result.In above process, the application dynamically adjusts the strategy of optimizing step-length based on odorousness value change rate, balances the local search of drosophila algorithm and the ability of global search；In addition, introducing Cauchy function aiming at the problem that drosophila algorithm is easy to appear local optimum and being disturbed to the iteration searching process of drosophila algorithm；Finally, using the parameter of improved drosophila algorithm optimization Random Forest model, subjectivity interference existing for traditional parameters selection algorithm is avoided.Therefore, the application has time-consuming feature short, precision of prediction is high during cardiovascular disease is predicted.
Description
Technical field
This application involves disease forecasting field, in particular to the pre- measurement equipment of a kind of cardiovascular disease and device.
Background technique
Currently, the number of patients scale of cardiovascular disease and its lethality all sharp rise, and high-quality medical resource
It is in short supply cause people to be unable to get satisfaction to the Newly diagnosed demand of cardiovascular disease, cause the state of an illness of patient continuous worsening.
It is that urgently those skilled in the art solve as it can be seen that how to realize the accurate screening to cardiovascular disease in early days
Problem.
Summary of the invention
The purpose of the application is to provide a kind of pre- measurement equipment of cardiovascular disease and device, to solve due to lacking at present
The problem of early stage realizes the scheme of accurate screening to cardiovascular disease, and patient is caused to miss excellent diagnostics period.
In order to solve the above technical problems, this application provides a kind of pre- measurement equipments of cardiovascular disease, comprising:
Memory: for storing computer program；
Processor: for executing the computer program, to perform the steps of
It is optimized based on parameter of the drosophila algorithm to random forests algorithm, obtains optimized parameter；According to the optimal ginseng
Number constructs random forest prediction model；History cardiovascular disease data are inputted into the random forest prediction model, obtain painstaking effort
Pipe disease forecasting result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, respectively
A iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control
It makes the drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；
Cauchy function is carried out to the drosophila in the elite drosophila population, the optimal drosophila in elite drosophila population after definitive variation,
Using as the optimal drosophila during current iteration.
Preferably, the processor is also used to:
Binary coding is carried out to scale, the size of attributive character subset of decision tree, obtains initial drosophila；According to described
Initial drosophila is optimized using parameter of the drosophila algorithm to random forests algorithm.
Preferably, the optimizing step-length of drosophila is adjusted in the odorousness value change rate according to drosophila population
In the process, the processor is specifically used for:
Determine the average smell concentration value of drosophila population；According to the average smell concentration value, determine that odorousness value becomes
Rate；Determine that optimizing step-length updates weight according to the odorousness value change rate；Weight pair is updated according to the optimizing step-length
Optimizing step-length is adjusted.
Preferably, during elite drosophila population in the determination drosophila population, the processing implement body
For:
According to fitness decision function, the fitness decision content of each drosophila in the drosophila population is determined；Described in determination
Fitness decision content is greater than the sub- drosophila population of preset threshold；Determine the maximum present count of fitness value in the sub- drosophila population
The drosophila of amount, using as elite drosophila population.
Preferably, in the determination sub- drosophila population the maximum preset quantity of fitness value drosophila, using as
During elite drosophila population, the processor is specifically used for:
Each drosophila in the sub- drosophila population is decoded, the corresponding random forest parameter of the drosophila is obtained；
Random Forest model based on the random forest parameter is trained, the outer error of bag of the Random Forest model is obtained,
Using the fitness value as the drosophila；The drosophila for determining the maximum preset quantity of fitness value, using as elite drosophila population.
Preferably, the history cardiovascular disease includes following any one or more attribute: diastolic pressure, systolic pressure, sky
Abdomen blood glucose value, blood oxygen saturation, heart rate, cholesterol value.
In addition, present invention also provides a kind of cardiovascular disease prediction meanss, comprising:
Parameter optimization module: for optimizing based on parameter of the drosophila algorithm to random forests algorithm, optimal ginseng is obtained
Number；
Prediction model constructs module: for constructing random forest prediction model according to the optimized parameter；
Prediction module: for history cardiovascular disease data to be inputted the random forest prediction model, angiocarpy is obtained
Disease forecasting result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, respectively
A iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control
It makes the drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；
Cauchy function is carried out to the drosophila in the elite drosophila population, the optimal drosophila in elite drosophila population after definitive variation,
Using as the optimal drosophila during current iteration.
The pre- measurement equipment of a kind of cardiovascular disease provided herein and device, can be based on drosophila algorithm to random forest
The parameter of algorithm optimizes, and obtains optimized parameter；And random forest prediction model is constructed according to optimized parameter；Finally by history
Cardiovascular disease data input random forest prediction model, obtain cardiovascular disease prediction result.Wherein, drosophila algorithm is being utilized
When optimizing random forests algorithm parameter, in each iterative process, the application is according to the odorousness value change rate of drosophila population
The optimizing step-length of drosophila is adjusted, after determining elite drosophila in searching process for the first time, Cauchy is executed to elite drosophila
Mutation operation, and then execute secondary optimization.
As it can be seen that being directed to cardiovascular disease forecasting problem, the application dynamically adjusts optimizing based on odorousness value change rate
The strategy of step-length balances the local search of drosophila algorithm and the ability of global search；In addition, being easy to appear for drosophila algorithm
The problem of local optimum, introduces Cauchy function and disturbs to the iteration searching process of drosophila algorithm；Finally, improved fruit is utilized
The parameter of fly algorithm optimization Random Forest model avoids subjectivity interference existing for traditional parameters selection algorithm.Therefore, this Shen
Please during cardiovascular disease is predicted, has time-consuming feature short, precision of prediction is high.
Detailed description of the invention
It, below will be to embodiment or existing for the clearer technical solution for illustrating the embodiment of the present application or the prior art
Attached drawing needed in technical description is briefly described, it should be apparent that, the accompanying drawings in the following description is only this Shen
Some embodiments please for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the structural schematic diagram that a kind of cardiovascular disease provided herein predicts apparatus embodiments；
Fig. 2 is a kind of flow diagram of the prediction process of the pre- measurement equipment of cardiovascular disease provided herein；
Fig. 3 shows for the process of step S201 during a kind of prediction of the pre- measurement equipment of cardiovascular disease provided herein
It is intended to；
Fig. 4 shows for the process of step S204 during a kind of prediction of the pre- measurement equipment of cardiovascular disease provided herein
It is intended to；
Fig. 5 shows for the process of step S205 during a kind of prediction of the pre- measurement equipment of cardiovascular disease provided herein
It is intended to；
A kind of functional block diagram of cardiovascular disease prediction meanss embodiment Fig. 6 provided herein.
Specific embodiment
The core of the application is to provide a kind of pre- measurement equipment of cardiovascular disease and device, and it is pre- to be obviously improved cardiovascular disease
The efficiency and reliability of survey realizes the early screening to cardiovascular disease.
In order to make those skilled in the art more fully understand application scheme, with reference to the accompanying drawings and detailed description
The application is described in further detail.Obviously, described embodiments are only a part of embodiments of the present application, rather than
Whole embodiments.Based on the embodiment in the application, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall in the protection scope of this application.
A kind of cardiovascular disease prediction apparatus embodiments provided by the present application are introduced below, referring to Fig. 1, embodiment
One includes:
Memory 100: for storing computer program；
Processor 200: for executing the computer program, to perform the steps of
It is optimized based on parameter of the drosophila algorithm to random forests algorithm, obtains optimized parameter；According to the optimal ginseng
Number constructs random forest prediction model；History cardiovascular disease data are inputted into the random forest prediction model, obtain painstaking effort
Pipe disease forecasting result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, respectively
A iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control
It makes the drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；
Cauchy function is carried out to the drosophila in the elite drosophila population, the optimal drosophila in elite drosophila population after definitive variation,
Using as the optimal drosophila during current iteration.
Specifically, the history cardiovascular disease may include following any one or more attribute: diastolic pressure, contraction
Pressure, fasting blood sugar, blood oxygen saturation, heart rate, cholesterol value；Above-mentioned cardiovascular disease prediction result can be probability of illness,
Two-value type whether can also being illness is not as a result, the present embodiment limits this.
As a kind of specific embodiment, the processor 200 is also used to:
Binary coding is carried out to scale, the size of attributive character subset of decision tree, obtains initial drosophila；According to described
Initial drosophila is optimized using parameter of the drosophila algorithm to random forests algorithm.
As a kind of specific embodiment, drosophila is sought according to the odorousness value change rate of drosophila population described
During excellent step-length is adjusted, the processor 200 is specifically used for:
Determine the average smell concentration value of drosophila population；According to the average smell concentration value, determine that odorousness value becomes
Rate；Determine that optimizing step-length updates weight according to the odorousness value change rate；Weight pair is updated according to the optimizing step-length
Optimizing step-length is adjusted.
As a kind of specific embodiment, the process of the elite drosophila population in the determination drosophila population
In, the processor 200 is specifically used for:
According to fitness decision function, the fitness decision content of each drosophila in the drosophila population is determined；Described in determination
Fitness decision content is greater than the sub- drosophila population of preset threshold；Determine the maximum present count of fitness value in the sub- drosophila population
The drosophila of amount, using as elite drosophila population.
As a kind of specific embodiment, the maximum present count of fitness value in the determination sub- drosophila population
The drosophila of amount, using as during elite drosophila population, the processor 200 is specifically used for:
Each drosophila in the sub- drosophila population is decoded, the corresponding random forest parameter of the drosophila is obtained；
Random Forest model based on the random forest parameter is trained, the outer error of bag of the Random Forest model is obtained,
Using the fitness value as the drosophila；The drosophila for determining the maximum preset quantity of fitness value, using as elite drosophila population.
Above-mentioned memory 100 include at least a type of readable storage medium storing program for executing, the readable storage medium storing program for executing include flash memory,
Hard disk, multimedia card, card-type memory (for example, SD or DX memory etc.), magnetic storage, disk, CD etc..Memory
100 can be the internal storage unit of the pre- measurement equipment of cardiovascular disease in some embodiments, such as cardiovascular disease prediction is set
Standby hard disk.Memory 100 is also possible to the External memory equipment of the pre- measurement equipment of cardiovascular disease, example in further embodiments
Such as the plug-in type hard disk being equipped on the pre- measurement equipment of cardiovascular disease, intelligent memory card (Smart Media Card, SMC), safety
Digital (Secure Digital, SD) card, flash card (Flash Card) etc..Further, memory 100 can also both include
The internal storage unit of the pre- measurement equipment of cardiovascular disease also includes External memory equipment.Memory 100 can be not only used for storing
It is installed on the application software and Various types of data, such as the code of computer program etc. of the pre- measurement equipment of cardiovascular disease, can also be used
In temporarily storing the data that has exported or will export.
Processor 200 can be in some embodiments a central processing unit (Central Processing Unit,
CPU), controller, microcontroller, microprocessor or other data processing chips, the program for being stored in run memory 100
Code or processing data, such as execute computer program etc..
Bus for connecting memory 100 and processor 200 can be Peripheral Component Interconnect standard (peripheral
Component interconnect, abbreviation PCI) bus or expanding the industrial standard structure (extended industry
Standard architecture, abbreviation EISA) bus etc..The bus can be divided into address bus, data/address bus, control always
Line etc..Only to be indicated with a thick line in Fig. 1, it is not intended that an only bus or a type of bus convenient for indicating.
In the present embodiment, a kind of above-mentioned pre- measurement equipment of cardiovascular disease can be PC (Personal Computer, it is a
People's computer), it is also possible to smart phone, tablet computer, palm PC, portable computer, intelligent router, mine machine, network and deposits
Store up equipment, terminal device.
The present embodiment provides a kind of pre- measurement equipment of cardiovascular disease, for cardiovascular disease forecasting problem, is based on smell
Concentration value change rate dynamically adjusts the strategy of optimizing step-length, balances the local search of drosophila algorithm and the energy of global search
Power；In addition, introducing iteration optimizing of the Cauchy function to drosophila algorithm aiming at the problem that drosophila algorithm is easy to appear local optimum
Cheng Jinhang disturbance；Finally, it using the parameter of improved drosophila algorithm optimization Random Forest model, avoids traditional parameters selection and calculates
Subjectivity interference existing for method.Therefore, the equipment is during cardiovascular disease is predicted, have it is time-consuming it is short, precision of prediction is high
Feature.
The building of random forest prediction model in the pre- measurement equipment of cardiovascular disease provided by the present application is highlighted below
Journey, referring to fig. 2, the process specifically include:
S200, initialization control parameter；
Control parameter setting: drosophila population scale popsize, elite drosophila scale z, the maximum number of iterations of drosophila algorithm
Maxgen, the attributive character number M of data set, Cauchy function step parameter λ.To the scale T of decision tree, attributive character subset
Size N carries out binary coding, is formed initial candidate solution X=(T, N), shown in odorousness function Func such as formula (1):
As a kind of specific embodiment, control parameter is arranged in the present embodiment as follows: drosophila population scale
Popsize=20, elite drosophila scale z=5, the attribute of the maximum number of iterations maxgen=200 of drosophila algorithm, data set are special
Levy number M=10, Cauchy function step parameter λ=0.12.Two are carried out to the scale T of decision tree, the size N of attributive character subset
Scale coding is formed initial candidate solution X=(200,3).
S201, control drosophila carry out optimizing search by smell, dynamically adjust optimizing according to odorousness value change rate
Step-length；
S202, the fitness decision content S for calculating each drosophila individuali, and calculate its corresponding sigmod functional value；
Wherein, the calculation formula of fitness decision content is as follows:
S203, judge sigmod (Si) value whether be greater than preset threshold, if so, jumping to S204, otherwise jump to
S201；
As a kind of specific embodiment, preset threshold can be set to 0.5 in the present embodiment, that is to say, that above-mentioned
Step judges whether following conditions are true: sigmod (Si) > 0.5.
S204, its fitness value is calculated；
S205, elite drosophila in contemporary drosophila population is sought, and Cauchy function is carried out to it；
S206, secondary optimization is carried out to the elite group after variation and finds out the optimal drosophila individual of wherein fitness value；
Shown in process such as formula (3):
[bestSmell, bestIndex]=max (Smelli) (3)
In formula, bestSmell represents the odorousness value of current optimal drosophila individual, and bestIndex represents current optimal
The number of drosophila individual.
S207, the fitness value and its position coordinates for saving current optimal drosophila individual, are better than in current fitness extreme value
When the fitness extreme value of last time, all drosophila individuals fly to optimal drosophila individual by vision positioning；
Shown in detailed process such as formula (4):
S208, judge whether to reach maximum number of iterations maxgen, obtain optimal drosophila X if judging to set upb=(Tb,
Nb), otherwise jump to S201；
S209, optimized parameter T is utilizedb、NbConstruct optimal stochastic forest model；
S210, to the data to be predicted of established mode input cardiovascular disease, obtain cardiovascular disease prediction result.
Specifically, above-mentioned data to be predicted and prediction result can be as shown in table 1, wherein data to be predicted include multinomial
The attributive character of cardiovascular disease data, such as diastolic pressure, systolic pressure, fasting blood-glucose, blood oxygen saturation, the rhythm of the heart；Prediction result
For two-value type as a result, 1 indicates illness, 0 indicates non-illness.
Table 1
As shown in figure 3, above-mentioned steps S201 specifically includes following procedure:
S301, the odorousness average value for calculating the n-th generation population
Specific calculation formula is as follows:
In formula, popsize is the scale of drosophila population, Func (Si) be i-th drosophila n for when odorousness value.
S302, it calculates drosophila population and is averaged the change rate R of smell concentration value；
Specific calculation formula is as follows:
S303, optimizing step-length update weight α is calculated:
Specific calculation formula is as follows:
Wherein, parameter area is by experiment gained.
S304, the optimizing route that weight α updates drosophila individual is updated according to step-length；
As shown in formula (8):
As shown in figure 4, above-mentioned steps S204 specifically includes following procedure:
S401, drosophila is decoded, obtains random forest parameter T, N；
S402, the Random Forest model based on the random forest parameter is trained；
S403, random forest mode the outer error OOB of bag and be stored in Smell group:
Specifically, the present embodiment calculates the outer error of bag by formula (9):
OOB=Q/P (9)
In formula, P is the sample total of the outer data of bag, and Q is in statistical classification result by the sample number of mistake classification.This implementation
In example, using error outside the bag of the random forest prediction model based on random forest parameter corresponding with drosophila as the suitable of the drosophila
Answer angle value.
As shown in figure 5, above-mentioned steps S205 specifically includes following procedure:
S501, the fitness value of contemporary drosophila individual is ranked up, using the drosophila individual of z before preceding ranking as elite
Body；
S502, Cauchy function is carried out to elite individual respectively；
Cauchy function is shown below:
In formula, Xbest_j,Ybest_jFor the position of the elite individual in contemporary population, δ is that rectangle point is submitted on [0,1]
The stochastic variable of cloth, λ are the parameter of control variation step-length.
As it can be seen that the pre- measurement equipment of a kind of cardiovascular disease provided in this embodiment is proposed for cardiovascular disease forecasting problem
The strategy for dynamically adjusting based on odorousness value change rate optimizing step-length balances the local search of drosophila algorithm and global
The ability of search；And aiming at the problem that drosophila algorithm is easy to appear local optimum, Cauchy function is introduced to the iteration of drosophila algorithm
Searching process is disturbed；Followed by the parameter selection of improved drosophila algorithm optimization Random Forest model, to avoid
Subjectivity interference existing for traditional parameters selection algorithm.As it can be seen that the cardiovascular disease prediction technique based on the equipment, calculates speed
Degree is fast, precision of prediction is quasi-, has good prediction effect in cardiovascular disease prediction.
Cardiovascular disease prediction meanss provided by the embodiments of the present application are introduced below, angiocarpy disease described below
Disease forecasting device can correspond to each other reference with the cardiovascular disease prediction process based on the pre- measurement equipment of above-mentioned cardiovascular disease.
Referring to Fig. 6, which includes:
Parameter optimization module 601: it for being optimized based on parameter of the drosophila algorithm to random forests algorithm, obtains optimal
Parameter；
Prediction model constructs module 602: for constructing random forest prediction model according to the optimized parameter；
Prediction module 603: for history cardiovascular disease data to be inputted the random forest prediction model, painstaking effort are obtained
Pipe disease forecasting result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, respectively
A iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control
It makes the drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；
Cauchy function is carried out to the drosophila in the elite drosophila population, the optimal drosophila in elite drosophila population after definitive variation,
Using as the optimal drosophila during current iteration.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with it is other
The difference of embodiment, same or similar part may refer to each other between each embodiment.For being filled disclosed in embodiment
For setting, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method part
Explanation.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
Scheme provided herein is described in detail above, specific case used herein is to the application's
Principle and embodiment is expounded, the present processes that the above embodiments are only used to help understand and its core
Thought；At the same time, for those skilled in the art, according to the thought of the application, in specific embodiment and application range
Upper there will be changes, in conclusion the contents of this specification should not be construed as limiting the present application.
Claims (7)
1. a kind of pre- measurement equipment of cardiovascular disease characterized by comprising
Memory: for storing computer program；
Processor: for executing the computer program, to perform the steps of
It is optimized based on parameter of the drosophila algorithm to random forests algorithm, obtains optimized parameter；According to the optimized parameter, structure
Build random forest prediction model；History cardiovascular disease data are inputted into the random forest prediction model, obtain cardiovascular disease
Disease forecasting result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, Ge Gesuo
Stating iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control institute
It states drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；To institute
It states the drosophila in elite drosophila population and carries out Cauchy function, the optimal drosophila in elite drosophila population after definitive variation, to make
For the optimal drosophila during current iteration.
2. equipment as described in claim 1, which is characterized in that the processor is also used to:
Binary coding is carried out to scale, the size of attributive character subset of decision tree, obtains initial drosophila；According to described initial
Drosophila is optimized using parameter of the drosophila algorithm to random forests algorithm.
3. equipment as described in claim 1, which is characterized in that in the odorousness value change rate pair according to drosophila population
During the optimizing step-length of drosophila is adjusted, the processor is specifically used for:
Determine the average smell concentration value of drosophila population；According to the average smell concentration value, odorousness value change rate is determined；
Determine that optimizing step-length updates weight according to the odorousness value change rate；Weight is updated according to the optimizing step-length to walk optimizing
Length is adjusted.
4. equipment as described in claim 1, which is characterized in that the elite drosophila population in the determination drosophila population
During, the processor is specifically used for:
According to fitness decision function, the fitness decision content of each drosophila in the drosophila population is determined；Determine the adaptation
Spend the sub- drosophila population that decision content is greater than preset threshold；Determine the maximum preset quantity of fitness value in the sub- drosophila population
Drosophila, using as elite drosophila population.
5. equipment as claimed in claim 4, which is characterized in that fitness value is maximum in the determination sub- drosophila population
Preset quantity drosophila, using as during elite drosophila population, the processor is specifically used for:
Each drosophila in the sub- drosophila population is decoded, the corresponding random forest parameter of the drosophila is obtained；To base
It is trained in the Random Forest model of the random forest parameter, the outer error of bag of the Random Forest model is obtained, to make
For the fitness value of the drosophila；The drosophila for determining the maximum preset quantity of fitness value, using as elite drosophila population.
6. equipment as claimed in claim 5, which is characterized in that the history cardiovascular disease includes following any one or more
Item attribute: diastolic pressure, systolic pressure, fasting blood sugar, blood oxygen saturation, heart rate, cholesterol value.
7. a kind of cardiovascular disease prediction meanss characterized by comprising
Parameter optimization module: for optimizing based on parameter of the drosophila algorithm to random forests algorithm, optimized parameter is obtained；
Prediction model constructs module: for constructing random forest prediction model according to the optimized parameter；
Prediction module: for history cardiovascular disease data to be inputted the random forest prediction model, cardiovascular disease is obtained
Prediction result；
Wherein, described to be optimized based on parameter of the drosophila algorithm to random forests algorithm, including multiple iterative process, Ge Gesuo
Stating iterative process includes: to be adjusted according to the odorousness value change rate of drosophila population to the optimizing step-length of drosophila；Control institute
It states drosophila and optimizing operation is executed according to optimizing step-length adjusted；Determine the elite drosophila population in the drosophila population；To institute
It states the drosophila in elite drosophila population and carries out Cauchy function, the optimal drosophila in elite drosophila population after definitive variation, to make
For the optimal drosophila during current iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910641128.9A CN110349675A (en) | 2019-07-16 | 2019-07-16 | A kind of pre- measurement equipment of cardiovascular disease and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910641128.9A CN110349675A (en) | 2019-07-16 | 2019-07-16 | A kind of pre- measurement equipment of cardiovascular disease and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110349675A true CN110349675A (en) | 2019-10-18 |
Family
ID=68176514
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910641128.9A Pending CN110349675A (en) | 2019-07-16 | 2019-07-16 | A kind of pre- measurement equipment of cardiovascular disease and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110349675A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111544846A (en) * | 2020-04-30 | 2020-08-18 | 天津大学 | Training and mode switching method for pure idea control rehabilitation robot |
| CN112397199A (en) * | 2020-11-30 | 2021-02-23 | 广东德澳智慧医疗科技有限公司 | Big data disease prediction system based on 5G and block chain |
| CN116131925A (en) * | 2023-04-18 | 2023-05-16 | 北京华航测通科技有限公司 | Cognitive satellite network channel allocation method and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN106951956A (en) * | 2017-03-14 | 2017-07-14 | 中国矿业大学 | A kind of multirobot odor source localization method based on fruit bat optimized algorithm |
| CN107847156A (en) * | 2015-06-15 | 2018-03-27 | 维塔尔实验室公司 | The method and system assessed and managed for angiocardiopathy |
| CN108805215A (en) * | 2018-06-19 | 2018-11-13 | 东北大学 | Based on the Dlagnosis of Sucker Rod Pumping Well dynamic liquid level flexible measurement method for improving drosophila algorithm |
| CN109841278A (en) * | 2017-11-28 | 2019-06-04 | 长庚医疗财团法人林口长庚纪念医院 | A method of the screening of coronary disease disease is carried out with angiocarpy mark and rote learning operation method |
-
2019
- 2019-07-16 CN CN201910641128.9A patent/CN110349675A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107847156A (en) * | 2015-06-15 | 2018-03-27 | 维塔尔实验室公司 | The method and system assessed and managed for angiocardiopathy |
| CN105426954A (en) * | 2015-08-20 | 2016-03-23 | 武汉科技大学 | Particle swarm optimization method based on multi-strategy synergistic function |
| CN106951956A (en) * | 2017-03-14 | 2017-07-14 | 中国矿业大学 | A kind of multirobot odor source localization method based on fruit bat optimized algorithm |
| CN109841278A (en) * | 2017-11-28 | 2019-06-04 | 长庚医疗财团法人林口长庚纪念医院 | A method of the screening of coronary disease disease is carried out with angiocarpy mark and rote learning operation method |
| CN108805215A (en) * | 2018-06-19 | 2018-11-13 | 东北大学 | Based on the Dlagnosis of Sucker Rod Pumping Well dynamic liquid level flexible measurement method for improving drosophila algorithm |
Non-Patent Citations (5)
| Title |
|---|
| X.C. WANG等: "A New Effective Machine Learning Framework for Sepsis Diagnosis", 《IEEE ACCESS》 * |
| 欧阳丽: "基于优化后的随机森林算法的入侵检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王行甫 等: "基于适应性动态步长的变异果蝇优化算法", 《计算机应用》 * |
| 罗斌杰: "基于随机森林的心脏病预测平台的设计与实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 赵东 等: "基于果蝇优化的随机森林预测方法", 《吉林大学学报（工学版）》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111544846A (en) * | 2020-04-30 | 2020-08-18 | 天津大学 | Training and mode switching method for pure idea control rehabilitation robot |
| CN111544846B (en) * | 2020-04-30 | 2021-05-25 | 天津大学 | Training and mode switching method for pure idea control rehabilitation robot |
| CN112397199A (en) * | 2020-11-30 | 2021-02-23 | 广东德澳智慧医疗科技有限公司 | Big data disease prediction system based on 5G and block chain |
| CN116131925A (en) * | 2023-04-18 | 2023-05-16 | 北京华航测通科技有限公司 | Cognitive satellite network channel allocation method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11675940B2 (en) | Generating integrated circuit floorplans using neural networks | |
| CN110349675A (en) | A kind of pre- measurement equipment of cardiovascular disease and device | |
| Wu | Coalescent-based species tree inference from gene tree topologies under incomplete lineage sorting by maximum likelihood | |
| US10474355B2 (en) | Input pattern detection over virtual keyboard for candidate word identification | |
| CN110457675A (en) | Prediction model training method, device, storage medium and computer equipment | |
| JP2023522567A (en) | Generation of integrated circuit layouts using neural networks | |
| Örkcü et al. | Estimating the parameters of 3-p Weibull distribution using particle swarm optimization: A comprehensive experimental comparison | |
| CN110597878A (en) | Cross-modal retrieval method, device, equipment and medium for multi-modal data | |
| CN110827924A (en) | Clustering method and device for gene expression data, computer equipment and storage medium | |
| CN109885774A (en) | Recommended method, device and the equipment of individualized content | |
| CN103577547B (en) | Webpage type identification method and device | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN108256030B (en) | Ontology-based density adaptive concept semantic similarity calculation method | |
| WO2022141840A1 (en) | Network architecture search method and apparatus, electronic device, and medium | |
| US20220180979A1 (en) | Adaptive clinical trials | |
| CN111967581A (en) | Interpretation method and device of clustering model, computer equipment and storage medium | |
| CN104090932A (en) | Content recommending method and device | |
| CN110223780A (en) | A kind of the fetal weight prediction technique and system of adaptive PSO-GRNN | |
| CN109377111A (en) | Job scheduling method and device based on modified-immune algorithm | |
| CN114912331A (en) | Cabin reinforcing rib optimization method, device, equipment and medium | |
| CN107480768A (en) | Bayesian network structure adaptive learning method and device, storage device and terminal device | |
| CN113205185A (en) | Network model optimization method and device, computer equipment and storage medium | |
| CN109829248A (en) | Method for determination of performance parameter, device and the electronic equipment of water pump | |
| CN110533192A (en) | Intensified learning method, apparatus, computer-readable medium and electronic equipment | |
| CN117094387B (en) | Knowledge graph construction method and system based on big data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191018 |
|
| RJ01 | Rejection of invention patent application after publication |