CN107645545B - Virus monitoring and early warning system based on cloud platform - Google Patents
Virus monitoring and early warning system based on cloud platform Download PDFInfo
- Publication number
- CN107645545B CN107645545B CN201710815961.1A CN201710815961A CN107645545B CN 107645545 B CN107645545 B CN 107645545B CN 201710815961 A CN201710815961 A CN 201710815961A CN 107645545 B CN107645545 B CN 107645545B
- Authority
- CN
- China
- Prior art keywords
- virus
- data
- neural network
- cloud
- monitoring center
- 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
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a virus monitoring and early warning system based on a cloud platform, which comprises a data acquisition terminal, a cloud monitoring center and a user client; the data acquisition terminal comprises air sampling equipment, a 3G network interface and a single chip microcomputer; the data acquisition terminal is used for monitoring viruses in the air in real time and sending monitoring data to the cloud monitoring center through the 3G network; the cloud monitoring center is used for comparing and analyzing the collected virus types and the virus content in the air, storing a comparison result, and issuing early warning information to the user client when an abnormality occurs; the cloud monitoring center also comprises a virus database, and the database is used for storing virus information and comparison results; and the user client is used for receiving the cloud control center information and accessing the cloud control center. The invention can accurately, timely and comprehensively reflect the current situation and the development trend of the airborne virus, and plays an important role in virus prevention, virus infection control and the like.
Description
Technical Field
The invention relates to the field of safety monitoring, in particular to a virus monitoring and early warning system and method based on a cloud platform.
Background
The existing air quality environment in China has many problems, viruses are rapidly transmitted in the air, and outbreaks are easily caused particularly in crowd gathering places. Therefore, the capture and monitoring of the virus in the air are carried out, an early warning mechanism of the virus in the air is established, and the prevention and control of the virus are carried out by combining the monitoring data, so that the health of people is very necessary to be ensured. And the purposes of actively preventing, ensuring the body health of target people, preventing virus from spreading in time and the like can be achieved by evaluating the environmental safety of crowd gathering areas such as hospitals, stations, squares and the like. The virus monitoring and early warning system based on the cloud platform breaks through the traditional monitoring method, applies an innovative design concept, organically combines monitoring and early warning with a cloud computing technology, constructs a big data processing platform, adopts a big data mining and analyzing method, and plays an important innovative supporting role in systematically researching and improving the air environment quality by combining the specific environment condition. Can accurately, timely and comprehensively reflect the current situation and the development trend of the airborne virus, and plays an important role in virus prevention, virus infection control and the like.
Disclosure of Invention
The invention aims to provide a virus monitoring and early warning system based on a cloud platform and an artificial intelligence prediction method based on big data analysis.
The technical scheme for realizing the aim of the invention is as follows:
the utility model provides a virus monitoring early warning system based on cloud platform which characterized in that: the system comprises a data acquisition terminal, a cloud monitoring center and a user client;
the data acquisition terminal comprises air sampling equipment, a 3G network interface and a single chip microcomputer;
the data acquisition terminal is used for monitoring viruses in the air in real time and sending monitoring data to the cloud monitoring center through the 3G network; the cloud monitoring center is used for comparing and analyzing the collected virus types and the virus content in the air, storing a comparison result, and issuing early warning information to the user client when an abnormality occurs; the cloud monitoring center also comprises a virus database, and the database is used for storing virus information and comparison results; and the user client is used for receiving the cloud control center information and accessing the cloud control center.
According to the invention, the air virus monitoring condition is timely sent to the client by using the Internet of things technology, users with different authorities can timely know related information, and then corresponding measures are taken.
Drawings
FIG. 1 is a schematic diagram of the system of the present invention.
FIG. 2 is a flow chart of the system of the present invention.
FIG. 3 is a schematic diagram of the BP neural network without genetic algorithm optimization according to the present invention.
FIG. 4 is a schematic diagram of a BP neural network optimized by a genetic algorithm according to the present invention.
FIG. 5 is a diagram of the coding mapping between the chromosome bit string and the weight threshold according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. 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.
As shown in fig. 1, the present invention provides an embodiment:
virus monitoring and early warning system based on cloud platform, its characterized in that: the system comprises a data acquisition terminal, a cloud monitoring center and a user client;
the data acquisition terminal comprises air sampling equipment, a 3G network interface and a single chip microcomputer;
the data acquisition terminal is used for monitoring viruses in the air in real time and sending monitoring data to the cloud monitoring center through the 3G network; the cloud monitoring center is used for comparing and analyzing the collected virus types and the virus content in the air, storing a comparison result, and issuing early warning information to the user client when an abnormality occurs; the cloud monitoring center also comprises a virus database, and the database is used for storing virus information and comparison results; and the user client is used for receiving the cloud control center information and accessing the cloud control center.
As shown in fig. 2, the present invention provides yet another embodiment:
a virus monitoring and early warning method of a virus monitoring and early warning system based on a cloud platform is characterized in that: the method comprises the following steps:
step 000, providing a virus monitoring and early warning system based on a cloud platform, which comprises a data acquisition terminal, a cloud monitoring center and a user client;
the data acquisition terminal comprises air sampling equipment, a 3G network interface and a single chip microcomputer;
the data acquisition terminal is used for monitoring viruses in the air in real time and sending monitoring data to the cloud monitoring center through the 3G network; the cloud monitoring center is used for comparing and analyzing the collected virus types and the virus content in the air, storing a comparison result, and issuing early warning information to the user client when an abnormality occurs; the cloud monitoring center also comprises a virus database, and the database is used for storing virus information and comparison results; the user client is used for receiving the cloud control center information and accessing a cloud control center;
step 100, the data acquisition terminal acquires the real-time situation of the virus in the air;
200, the data acquisition terminal sends the acquired information condition to a cloud monitoring center at certain time intervals;
step 300, the cloud monitoring center receives data sent by a data acquisition terminal, and intelligently analyzes, judges and identifies the data;
step 400, the cloud monitoring center stores monitoring data and analysis results, and updates the virus database at certain intervals;
500, the cloud monitoring center issues the analysis result of the step 300 to a client, and the issued information content is whether the types and the content of the viruses in the air are abnormal or not;
step 600, the client receives information issued by a cloud monitoring center in real time, and can also actively query the cloud monitoring center, wherein the query content includes virus safety conditions, virus characteristics and monitoring equipment operation conditions.
In particular, the step 100 further comprises:
step 120: various sensors transmit acquired air virus types and contents and voltage and current signals of equipment operation to a single chip microcomputer of an acquisition terminal at regular time, and the single chip microcomputer converts various signals into digital signals and performs digital filtering to remove noise and error data;
step 140: and the single chip microcomputer encodes the data obtained by preprocessing in the step 120 by setting a communication protocol, transmits different data information to a 3G network interface through a 485 bus, converts the data information into a 3G network signal and sends the signal to the cloud monitoring center.
As shown in fig. 3, in particular, the step 300 further includes:
step 310: taking data in the virus database as training data;
step 320: initializing a weight threshold value and assigning the weight threshold value to a BP neural network;
step 330: training the BP neural network to a given error range;
step 340: and inputting the virus concentration in the real-time air acquired by the data acquisition terminal into a BP neural network as test data to obtain a prediction result.
In particular, the method for initializing the weight threshold in step 320 includes:
the BP neural network with input nodes i, middle layer nodes j and output layer nodes k is provided, and the corresponding BP neural network has the following matrix;
connecting the input layer of the BP neural network to the middle layer by using a weight matrix:
middle layer threshold matrix of BP neural network
Connecting weight matrix from middle layer to output layer of BP neural network
Output layer threshold matrix of BP neural network
Wherein each element of W, gamma, V, h is a random number belonging to the range of [ -1,1 ].
As shown in fig. 4, in particular, an improved method of step 300 is provided: the method comprises the following steps:
step 350: taking data in the virus database as training data;
step 355: binary coding is carried out on the initialization threshold value;
step 360: setting related parameters including population scale, cross rate, mutation rate and evolution algebra;
step 366: designing a fitness function;
step 370: performing selection, crossing and variation operations in a genetic algorithm, and circularly obtaining an optimal solution;
the selection operator of the invention is an improved one-time roulette method, the crossover operator is random multipoint crossover, the mutation operator adopts a random selection mutation method, and the maximum cycle number is 20000.
Step 377: assigning the optimal weight threshold value to a BP neural network;
step 380: normalizing the virus concentration in the real-time air collected by the data collection terminal;
step 388: assigning the normalized sample data and inputting the sample data into a BP neural network;
step 390: training a BP neural network to a given error range;
step 399: and inputting the test data into the BP neural network to obtain a prediction result.
Specifically, step 355 further includes:
in order to perform weight threshold optimization of the BP neural network, i.e., optimization of the above-mentioned 4 matrices W, y, V and h, using GA, it must be converted into a chromosome string for convenient operation. Each individual is represented by a binary string, and the quality of the individual is evaluated by a fitness function value, namely an evaluation function. The coding mapping relationship between the chromosome bit string and the weight threshold is shown in fig. 5:
wherein w11′,w12′...wij′、γ1′…γj′、v11′,v12′…vjk′、h1′,h2′…hk' are each w11,w12…wij、γ1,γ2…γj、v11,v12…vjk、h1,h2…hkThe value after being represented by a binary string,
is 0 or 1.
The length of the binary string is determined by the range and precision of the parameters, and the weight threshold value is represented by the binary string and input into the network, and the encoding process is as follows:
the range of the parameters is set to [ Umin, Umax]Any parameter is represented by a binary symbol string of length λ, so it has a total of 2λThe encoding is carried out, wherein delta is precision, and the corresponding relation between parameters and encoding is as follows:
the binary encoding precision formula is as follows:
the decoding is as follows:
assuming that the chromosome code corresponding to a certain weight threshold is: x: bλbλ-1bλ-2......b2b1First, λ is determined by a given precision, and the corresponding decoding formula is:
wherein b iseAnd taking the value of the e-th position of the chromosome code corresponding to the weight threshold value.
Further, the determination method of the evaluation function in step 366 is as follows:
according to the characteristics of the prediction problem of the quality of the viruses in the air, an error function of the BP neural network is defined as:
wherein E (W) is the error of the BP neural network when the weight threshold is W; t is tq(p)，yq(p) denotes the values we expect to get and the values we actually predict, respectively, and l and k represent the number of training samples and the number of nodes the output layer contains, respectively.
tq(p) is determined from historical virus concentration data in the virus database, yq(p) is determined from historical alignments in the virus database.
The final purpose of the network model training is to increase progressively with evolution algebra, while the error function is reducing continuously, and the fitness value is increasing continuously, so the fitness coefficient is constructed according to the error function, namely the evaluation function is:
where ξ is a minimum value close to 0.
The process of evolving the network weight threshold mainly comprises the steps of determining a coding scheme, generating an initial population, constructing a fitness function according to actual problems, determining the probability according to the fitness, and completing selection, intersection and variation until an optimal population is generated.
Specifically, step 380 further comprises:
wherein y isuRepresents the concentration y of the u-th virus sampled and received by the data acquisition terminalu' is yuNormalized data, ymimRepresents the minimum value in the set of data, ymaxRepresents the maximum value in the set of data, yu' is input as an input factor to the BP neural network model.
In particular, in step 600, the user client can receive information issued by the cloud monitoring center in real time, and can also actively query relevant data of the server in monitoring, where the query content includes virus safety conditions, virus characteristics, monitoring device operation conditions, and the like. The main characteristics of the method include: the user client can actively inquire the historical data issued by the cloud monitoring center, the inquiry mode is that firstly, through identity verification, access authority is obtained, the data of the cloud monitoring center can be accessed, the data are provided with different access authorities, and users with different authority levels can access different contents; the user client can be various handheld terminals, smart phones or PCs and the like.
The table below shows the accuracy (percentage) of the virus prediction method based on the BP neural network and the virus prediction method based on the genetic algorithm and the BP neural network in the present invention under the condition of different training data amounts, and it can be seen from the data in the table that the larger the training data amount is, the higher the accuracy of the two methods in the present invention is. Compared with the virus prediction method based on the BP neural network, the virus prediction method based on the genetic algorithm and the BP neural network has higher accuracy rate due to the optimization. Therefore, the virus prediction method based on the genetic algorithm and the BP neural network achieves unexpected effects, and has remarkable progress compared with the prior art.
The table below shows the accuracy (percentage) of the virus prediction method based on the BP neural network and the virus prediction method based on the genetic algorithm and the BP neural network in the present invention under the condition of different prediction data amounts, and it can be seen from the data in the table that the larger the prediction data amount is, the higher the accuracy of the two methods in the present invention is. Compared with the virus prediction method based on the BP neural network, the prediction method based on the genetic algorithm and the BP neural network is optimized, so that the prediction accuracy is higher. Therefore, the virus prediction method based on the genetic algorithm and the BP neural network achieves unexpected effects, and has remarkable progress compared with the prior art.
| Amount of test data | BP neural network | BP neural network based on genetic algorithm |
| 500 | 0.79 | 0.83 |
| 1000 | 0.78 | 0.85 |
| 2000 | 0.81 | 0.91 |
| 3000 | 0.84 | 0.93 |
| 5000 | 0.85 | 0.96 |
| 10000 | 0.86 | 0.98 |
| 20000 | 0.88 | 0.97 |
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (1)
1. A virus monitoring and early warning method is realized by a virus monitoring and early warning system based on a cloud platform, wherein the virus monitoring and early warning system comprises a data acquisition terminal, a cloud monitoring center and a user client; the data acquisition terminal comprises air sampling equipment, a 3G network interface and a single chip microcomputer; the data acquisition terminal is used for monitoring viruses in the air in real time and sending monitoring data to the cloud monitoring center through the 3G network; the cloud monitoring center is used for comparing and analyzing the collected virus types and the virus content in the air, storing a comparison result, and issuing early warning information to the user client when an abnormality occurs; the cloud monitoring center also comprises a virus database, and the virus database is used for storing virus information and comparison results; the user client is used for receiving the cloud monitoring center information and accessing a cloud monitoring center, and is characterized in that: the virus monitoring and early warning method comprises the following steps:
step 100, the data acquisition terminal acquires the real-time situation of the virus in the air;
200, the data acquisition terminal sends the acquired information condition to a cloud monitoring center at certain time intervals;
step 300, the cloud monitoring center receives data sent by a data acquisition terminal, and intelligently analyzes, judges and identifies the data;
wherein step 300 further comprises:
step 350: taking data in the virus database as training data;
step 356, initializing a weight threshold of the BP neural network, wherein an input node of the BP neural network is i, a middle layer node is j, an output layer node is k,
connecting the input layer of the BP neural network to the middle layer by using a weight matrix:
middle layer threshold matrix of BP neural network
Connecting weight matrix from middle layer to output layer of BP neural network
Output layer threshold matrix of BP neural network
Wherein each element of W, gamma, V, h is a random number belonging to the range of [ -1,1 ];
step 357: calculating the binary coding bit number according to the required precision delta:
the Umin and the Umax are respectively the minimum value and the maximum value of a single weight threshold, and the lambda is the binary coding bit number representing the single weight threshold;
step 358: determining the chromosomal coding:
wherein w11′,w12′...wij′、γ′1…γ′j、v11′,v12′…vjk′、h1′,h2′…hk' are each w11,w12…wij、γ1,γ2…γj、v11,v12…vjk、h1,h2…hkThe value after being represented by a binary string,
is 0 or 1;
step 360: setting related parameters including population scale, cross rate, mutation rate and evolution algebra;
step 366: fitness function of
Wherein, the error of BP neural network when the input layer is connected with the intermediate layer and the weight matrix is W
tq(p)，yq(p) respectively representing an expected value and an actual predicted value, l and k respectively representing the number of training samples and the number of nodes contained in an output layer, and ξ is a minimum value close to 0;
step 370: performing selection, crossing and variation operations in a genetic algorithm, and circularly obtaining an optimal solution;
the selection operator is an improved one-time roulette method, the crossover operator is random multipoint crossover, the mutation operator adopts a random selection mutation method, and the maximum cycle number is 20000;
step 377: assigning the optimal weight threshold value to a BP neural network;
step 380: normalizing the virus concentration in the real-time air collected by the data collection terminal;
wherein, yuRepresents the concentration y of the u-th virus sampled and received by the data acquisition terminalu' is yuNormalized data, ymimRepresents the minimum value in the virus concentration data, ymaxRepresents the maximum value in the virus concentration data, yu' as an input factor to the BP neural network model;
step 388: inputting the normalized sample data into a BP neural network;
step 390: training a BP neural network to a given error range;
step 399: and inputting the test data into the BP neural network to obtain a prediction result.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710784080 | 2017-09-04 | ||
| CN2017107840808 | 2017-09-04 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107645545A CN107645545A (en) | 2018-01-30 |
| CN107645545B true CN107645545B (en) | 2021-06-25 |
Family
ID=61110210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710815961.1A Active CN107645545B (en) | 2017-09-04 | 2017-09-12 | Virus monitoring and early warning system based on cloud platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107645545B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109407629B (en) * | 2018-09-11 | 2021-02-02 | 广州市赛特检测有限公司 | Pathogen online monitoring system and method |
| CN113267598A (en) * | 2020-02-17 | 2021-08-17 | 曾学军 | Intelligent air quality monitoring and analyzing system based on internet technology |
| CN112435760A (en) * | 2020-12-01 | 2021-03-02 | 熙年科技(深圳)有限公司 | Germ prevention and control method and system based on block chain and Internet of things technology |
| CN112782050A (en) * | 2020-12-25 | 2021-05-11 | 杭州电子科技大学 | Bioaerosol concentration prediction method based on long-short term memory neural network |
| CN113204108A (en) * | 2021-03-19 | 2021-08-03 | 刘利军 | Multifunctional dissecting microscope |
| CN113161007A (en) * | 2021-03-29 | 2021-07-23 | 淄博市妇幼保健院(淄博市第三人民医院、淄博市妇女儿童医院) | Clinical hygiene protection method and system for obstetrics and gynecology department |
| CN113035352B (en) * | 2021-04-27 | 2022-06-21 | 河南科技大学 | Diabetic retinopathy early warning method based on BP neural network |
| CN114344542A (en) * | 2022-02-22 | 2022-04-15 | 珠海横琴润霖生物科技有限公司 | Air early warning disinfection system |
| CN115981256B (en) * | 2022-12-19 | 2023-08-08 | 肇庆高峰机械科技有限公司 | Cloud control system of magnetic steel stacking device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104820072A (en) * | 2015-04-30 | 2015-08-05 | 重庆大学 | Electronic nose air quality monitoring system and method based on cloud computing |
| CN106600140A (en) * | 2016-12-07 | 2017-04-26 | 河海大学常州校区 | Improved support vector machine-based gas pipeline fault prediction and early warning system and method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013075297A1 (en) * | 2011-11-23 | 2013-05-30 | 湖南深拓智能设备股份有限公司 | Remote real-time monitoring system based on cloud computing |
-
2017
- 2017-09-12 CN CN201710815961.1A patent/CN107645545B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN104820072A (en) * | 2015-04-30 | 2015-08-05 | 重庆大学 | Electronic nose air quality monitoring system and method based on cloud computing |
| CN106600140A (en) * | 2016-12-07 | 2017-04-26 | 河海大学常州校区 | Improved support vector machine-based gas pipeline fault prediction and early warning system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107645545A (en) | 2018-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107645545B (en) | Virus monitoring and early warning system based on cloud platform | |
| CN111079977B (en) | Heterogeneous federal learning mine electromagnetic radiation trend tracking method based on SVD algorithm | |
| Traveset et al. | Global patterns of mainland and insular pollination networks | |
| CN104933841B (en) | A kind of fire prediction method based on self organizing neural network | |
| CN106992994A (en) | A kind of automatically-monitored method and system of cloud service | |
| CN112308288A (en) | Particle swarm optimization LSSVM-based default user probability prediction method | |
| CN108874959A (en) | A kind of user's dynamic interest model method for building up based on big data technology | |
| CN110210658A (en) | Prophet and Gaussian process user network method for predicting based on wavelet transformation | |
| CN106997669A (en) | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance | |
| CN111526119B (en) | Abnormal flow detection method and device, electronic equipment and computer readable medium | |
| CN108921359B (en) | Distributed gas concentration prediction method and device | |
| CN103840988A (en) | Network traffic measurement method based on RBF neural network | |
| CN116112292B (en) | Abnormal behavior detection method, system and medium based on network flow big data | |
| CN105354198A (en) | Data processing method and apparatus | |
| CN103020737A (en) | Forecasting method of baking sheet smoke | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN112986492A (en) | Method and device for establishing gas concentration prediction model | |
| Shipley | Measuring and interpreting trait‐based selection versus meta‐community effects during local community assembly | |
| CN115687995A (en) | Big data environmental pollution monitoring method and system | |
| CN116738354B (en) | Method and system for detecting abnormal behavior of electric power Internet of things terminal | |
| CN111444233A (en) | Method for discovering environmental monitoring abnormal data based on duplicator neural network model | |
| CN115713044B (en) | Method and device for analyzing residual life of electromechanical equipment under multi-condition switching | |
| CN107220705B (en) | Atmospheric tower top dry point prediction method for atmospheric and vacuum device | |
| CN112348656A (en) | BA-WNN-based personal loan credit scoring method | |
| CN114422873B (en) | Method, device and equipment for dynamically accessing industrial Internet identification analysis platform |
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 |