CN110097973A - The prediction algorithm of human health index based on genetic algorithm and BP neural network - Google Patents
The prediction algorithm of human health index based on genetic algorithm and BP neural network Download PDFInfo
- Publication number
- CN110097973A CN110097973A CN201910388960.2A CN201910388960A CN110097973A CN 110097973 A CN110097973 A CN 110097973A CN 201910388960 A CN201910388960 A CN 201910388960A CN 110097973 A CN110097973 A CN 110097973A
- Authority
- CN
- China
- Prior art keywords
- neural network
- operator
- human health
- health index
- genetic
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14542—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring blood gases
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7271—Specific aspects of physiological measurement analysis
- A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
-
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Physiology (AREA)
- Cardiology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Optics & Photonics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Pulmonology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of prediction algorithms of human health index based on genetic algorithm and BP neural network, include the following steps (1) acquisition sign data and carry out genetic coding formation initialization population, and initialization population is successively subjected to calculating individual adaptation degree, selection operator, crossover operator and mutation operator；(2) the maximum genetic algebra i that fused layer is arranged is 100, and the population after individual adaptation degree, selection operator, crossover operator and mutation operator are calculated separately is input to fused layer；(3) population that fused layer meets iteration requirement is inputted into BP neural network, the prediction to human health index is realized in the training and study by BP neural network.The present invention is handled the primary data of acquisition by heredity calculation, the optimal solution of data can be achieved, be input to BP neural network again so that input BP neural network data correcting then change, improve the precision of weight in BP neural network, training effectiveness, network performance and network approximation capability.
Description
Technical field
The present invention relates to human health electric powder predictions, and in particular to a kind of based on genetic algorithm and BP neural network
The prediction algorithm of human health index.
Background technique
With the increasingly raising of living standard and the development of science and technology, people increasingly pay close attention to the health of oneself, with
Wearable and portable intelligent sign data detection device application and give birth to.Currently, most of intelligence sign data
Detection device can only realize unification Data Detection, such as electronic thermometer, Portable blood pressure monitor, also only limit the analysis of data
In number collected and current single comparison, do not have comprehensive analytical capacity, there are also the analyses of specific mass data
Ability, but mass data needs for a long time not having practicability to acquire.
BP neural network is to find out to obtain weight relationship between input and output using existing data, is then closed using weight
System is emulated, such as is inputted one group of data simulation and gone out to export result.It is widely used in predicting, passes through acquisition or test data
Reflect result trend, and then realizes prediction.Application No. is 201610543416.7 patents of invention to disclose based on BP nerve net
The human health status recognition methods of network, this method by measurement do not suffer from major disease person crowd sign data (age,
Gender, lung capacity, weight etc.) it is directly inputted into the prediction that BP neural network is trained and learns to carry out human health status,
Although the prediction of human health also may be implemented, primary data amount is huge and quantity has differences, so that training effectiveness is not
Height causes network performance to decline, and directly affects the approximation capability of network, to influence the pre- of the human health index finally exported
Survey result.
Summary of the invention
In order to overcome the problems referred above, BP neural network and genetic algorithm are combined the purpose of the present invention is to provide a kind of
Realize the algorithm of the prediction of human health index.
The purpose of the present invention is what is be achieved through the following technical solutions:
The prediction algorithm of human health index based on genetic algorithm and BP neural network, includes the following steps:
(1) it acquires sign data and carries out genetic coding and form initialization population, and initialization population is successively counted
Calculate individual adaptation degree, selection operator, crossover operator and mutation operator；
(2) be arranged fused layer maximum genetic algebra i be 100, and by individual adaptation degree, selection operator, crossover operator and
Population after mutation operator calculates separately is input to fused layer；
(3) population that fused layer meets iteration requirement is inputted into BP neural network, by the training and of BP neural network
Practise the prediction realized to human health index.
Further, sign data described in step (1) includes body temperature, blood oxygen, heart rate and blood pressure.
Further, genetic coding described in step (1) is realized using Real Coding Genetic Algorithm.
Further, the error function in BP neural network described in step (3) is bipolar S function, and computational accuracy value is
6.5×10-5, maximum study number is 5000.
The invention has the following advantages:
(1) optimal solution, it can be achieved that data is handled to the primary data of acquisition by heredity calculation, then is input to BP mind
Through network so that input BP neural network data correcting is then changed, improve the precision of weight in BP neural network, training effectiveness,
The approximation capability of network performance and network；
(2) population after calculating separately individual adaptation degree, selection operator, crossover operator and mutation operator in genetic algorithm
It is input to fused layer, without the diversity that can enrich sample, may also speed up the convergence of genetic algorithm.
Detailed description of the invention
Fig. 1 is workflow block diagram of the invention.
Fig. 2 is the mean square error figure of embodiment 1.
Fig. 3 is 1 predicted value of embodiment and actual comparison figure.
Fig. 4 is the mean square error figure of comparative example 1.
Fig. 5 is 1 predicted value of comparative example and actual comparison figure.
Specific embodiment
Embodiment 1
As shown in Figure 1, the prediction of the human health index provided in this embodiment based on genetic algorithm and BP neural network
Algorithm includes the following steps:
(1) it acquires sign data and carries out genetic coding and form initialization population, and initialization population is successively counted
Calculate individual adaptation degree, selection operator, crossover operator and mutation operator；The sign data includes body temperature, blood oxygen, blood pressure and the heart
Rate, but be not limited only to this 4 data, also can also include the data that other home furnishings intelligent terminals can be detected, such as weight, to adopting
Collect a large amount of sign data to be normalized, the precision of sign data can be improved, by the data after normalized according to
Real Coding Genetic Algorithm carries out genetic coding, and the matter of offspring can be improved in the real number increment constitutivegene string that space is respectively tieed up
Amount and precision, the matching degree of individual shift direction and optimization object especially in crossover operator and mutation operator.
(2) be arranged fused layer maximum genetic algebra i be 100, and by individual adaptation degree, selection operator, crossover operator and
Population after mutation operator calculates separately is input to fused layer；The richness of population, the i.e. diversity of sample can be increased, and
Accelerate the convergence of genetic algorithm.
(3) population that fused layer meets iteration requirement is inputted into BP neural network, by the training and of BP neural network
Practise the prediction realized to human health index.
The BP neural network includes input layer, middle layer and output layer, and calculating process includes the following steps (1) BP mind
Through netinit, a section (- 1,1) interior random number is assigned respectively to a connection weight, and set error function as bipolar S letter
Number, computational accuracy value are 6.5 × 10-5, maximum study number is 5000；(2) input sample and corresponding desired output are randomly selected,
Middle layer is calculated to output and input, by desired output and reality output calculate error function to the partial derivative of output layer and in
The local derviation amount of interbed；(3) weight between being corrected by the output valve of the local derviation amount of output layer and middle layer；(4) in passing through
The input of the local derviation amount of interbed and input layer is come the weight between correcting, and (5) finally calculate global error, when error reaches expected
Precision or study number are greater than the maximum times of setting, then terminate algorithm, otherwise, choose next learning sample and corresponding phase
Hope output.
The present embodiment is applied to specific actual data, Fig. 2 indicates that the mean square error figure of the present embodiment output, Fig. 3 are
The comparison diagram of the present embodiment predicted value and reality output.
Comparative example 1
The present embodiment is substantially the same manner as Example 1, only changes second step step, that is, the maximum genetic algebra of fused layer is arranged
I is 100, and the population after mutation operator is calculated is input to fused layer.Other steps are constant, by the identical data of embodiment 1
It is input to the present embodiment, Fig. 4 is the mean square error figure of embodiment output, is compared with Fig. 2, and (3) error that comes into force is relatively large, and
Predicted value and actual value separation degree are larger compared with embodiment 1, and test (2) tends towards stability too early.Fig. 5 be the present embodiment predicted value with
Error is larger and not flat enough between the predicted value and actual value of the present embodiment known to the comparison diagram of reality output, Fig. 5 and Fig. 3 comparison
It is slow.
The above is only the preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto, any
The transformation and replacement carried out based on technical solution provided by the present invention and inventive concept should all be covered in protection model of the invention
In enclosing.
Claims (4)
1. the prediction algorithm of the human health index based on genetic algorithm and BP neural network, it is characterised in that including walking as follows
It is rapid:
(1) it acquires sign data and carries out genetic coding and form initialization population, and initialization population is successively carried out to calculating
Body fitness, selection operator, crossover operator and mutation operator；
(2) the maximum genetic algebra i that fused layer is arranged is 100, and by individual adaptation degree, selection operator, crossover operator and variation
Population after operator calculates separately is input to fused layer；
(3) population that fused layer meets iteration requirement is inputted into BP neural network, the training and study by BP neural network are real
Now to the prediction of human health index.
2. the prediction algorithm of the human health index according to claim 1 based on genetic algorithm and BP neural network,
Be characterized in that: sign data described in step (1) includes body temperature, blood oxygen, heart rate and blood pressure.
3. the prediction algorithm of the human health index according to claim 1 based on genetic algorithm and BP neural network,
Be characterized in that: genetic coding described in step (1) is realized using Real Coding Genetic Algorithm.
4. the prediction algorithm of the human health index according to claim 1 based on genetic algorithm and BP neural network,
Be characterized in that: the error function in BP neural network described in step (3) is bipolar S function, and computational accuracy value is 6.5 × 10-5,
Maximum study number is 5000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388960.2A CN110097973A (en) | 2019-05-10 | 2019-05-10 | The prediction algorithm of human health index based on genetic algorithm and BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910388960.2A CN110097973A (en) | 2019-05-10 | 2019-05-10 | The prediction algorithm of human health index based on genetic algorithm and BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097973A true CN110097973A (en) | 2019-08-06 |
Family
ID=67447639
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910388960.2A Pending CN110097973A (en) | 2019-05-10 | 2019-05-10 | The prediction algorithm of human health index based on genetic algorithm and BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097973A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110604549A (en) * | 2019-09-23 | 2019-12-24 | 上海联影医疗科技有限公司 | Image acquisition method, apparatus, device and medium for magnetic resonance scanner |
| CN111150411A (en) * | 2020-01-17 | 2020-05-15 | 哈尔滨工业大学 | Psychological stress evaluation grading method based on improved genetic algorithm |
| CN112070206A (en) * | 2020-07-31 | 2020-12-11 | 广州中大数字家庭工程技术研究中心有限公司 | Body temperature measuring method based on neural network and computer readable storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101549498A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Automatic tracking and navigation system of intelligent aid type walking robots |
| CN101866525A (en) * | 2010-05-28 | 2010-10-20 | 中国民航大学 | Device and method for forecasting freezing on surface of ground plane based on multisensor |
| CN103646188A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Non-invasive diagnostic method of coronary heart disease based on hybrid intelligent algorithm |
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN106175726A (en) * | 2016-07-11 | 2016-12-07 | 夏茂 | Human health status recognition methods based on BP neutral net |
| CN108990233A (en) * | 2018-08-09 | 2018-12-11 | 广东工业大学 | A kind of intelligent light control system and method |
| CN109259528A (en) * | 2018-09-28 | 2019-01-25 | 杭州电子科技大学 | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection |
| CN109711549A (en) * | 2018-12-27 | 2019-05-03 | 中国农业大学 | A kind of mastitis for milk cows detection method based on genetic algorithm optimization BP neural network |
-
2019
- 2019-05-10 CN CN201910388960.2A patent/CN110097973A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101549498A (en) * | 2009-04-23 | 2009-10-07 | 上海交通大学 | Automatic tracking and navigation system of intelligent aid type walking robots |
| CN101866525A (en) * | 2010-05-28 | 2010-10-20 | 中国民航大学 | Device and method for forecasting freezing on surface of ground plane based on multisensor |
| CN103646188A (en) * | 2013-12-27 | 2014-03-19 | 长春工业大学 | Non-invasive diagnostic method of coronary heart disease based on hybrid intelligent algorithm |
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN106175726A (en) * | 2016-07-11 | 2016-12-07 | 夏茂 | Human health status recognition methods based on BP neutral net |
| CN108990233A (en) * | 2018-08-09 | 2018-12-11 | 广东工业大学 | A kind of intelligent light control system and method |
| CN109259528A (en) * | 2018-09-28 | 2019-01-25 | 杭州电子科技大学 | A kind of home furnishings intelligent mirror based on recognition of face and skin quality detection |
| CN109711549A (en) * | 2018-12-27 | 2019-05-03 | 中国农业大学 | A kind of mastitis for milk cows detection method based on genetic algorithm optimization BP neural network |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110604549A (en) * | 2019-09-23 | 2019-12-24 | 上海联影医疗科技有限公司 | Image acquisition method, apparatus, device and medium for magnetic resonance scanner |
| CN110604549B (en) * | 2019-09-23 | 2022-06-24 | 上海联影医疗科技股份有限公司 | Image acquisition method, apparatus, device and medium for magnetic resonance scanner |
| CN111150411A (en) * | 2020-01-17 | 2020-05-15 | 哈尔滨工业大学 | Psychological stress evaluation grading method based on improved genetic algorithm |
| CN111150411B (en) * | 2020-01-17 | 2022-11-11 | 哈尔滨工业大学 | Psychological stress evaluation grading method based on improved genetic algorithm |
| CN112070206A (en) * | 2020-07-31 | 2020-12-11 | 广州中大数字家庭工程技术研究中心有限公司 | Body temperature measuring method based on neural network and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097973A (en) | The prediction algorithm of human health index based on genetic algorithm and BP neural network | |
| WO2021027295A1 (en) | Human body composition prediction method based on improved adaptive genetic algorithm | |
| Hasenauer et al. | Estimating tree mortality of Norway spruce stands with neural networks | |
| CN110020623A (en) | Physical activity identifying system and method based on condition variation self-encoding encoder | |
| CN112735535B (en) | Prediction model training method, prediction model training device, data prediction method, data prediction device and storage medium | |
| CN104933841B (en) | A kind of fire prediction method based on self organizing neural network | |
| CN106614273B (en) | Pet feeding method and system based on Internet of Things big data analysis | |
| CN110826453A (en) | Behavior identification method by extracting coordinates of human body joint points | |
| CN112037925B (en) | LSTM algorithm-based early warning method for new major infectious diseases | |
| CN111046961B (en) | Fault classification method based on bidirectional long-time and short-time memory unit and capsule network | |
| CN106472412A (en) | Pet feeding method and system based on internet of things | |
| CN115906954A (en) | Multivariate time sequence prediction method and device based on graph neural network | |
| CN112288137A (en) | LSTM short-term load prediction method and device considering electricity price and Attention mechanism | |
| CN107945534A (en) | A kind of special bus method for predicting based on GMDH neutral nets | |
| CN115168669A (en) | Infectious disease screening method and device, terminal equipment and medium | |
| CN117476214A (en) | Data management method and system based on hospital information | |
| Stanković et al. | Artificial neural network model for prediction of students’ success in learning programming | |
| Han et al. | Prediction of human thermal comfort preference based on supervised learning | |
| CN115271033B (en) | Medical image processing model construction and processing method based on federal knowledge distillation | |
| CN110321951A (en) | A kind of VR simulated flight device evaluation of training method | |
| CN115147768A (en) | Fall risk assessment method and system | |
| Subasi et al. | Prediction of early heat of hydration of plain and blended cements using neuro-fuzzy modelling techniques | |
| CN114912027A (en) | Learning scheme recommendation method and system based on learning outcome prediction | |
| CN109871953B (en) | Wavelet neural network modeling method for heavy oil cracking process of fpRNA genetic algorithm | |
| Park et al. | Medical Time-series Prediction With LSTM-MDN-ATTN |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190806 |