CN107645545A - A kind of virus monitor early warning system based on cloud platform - Google Patents
A kind of virus monitor early warning system based on cloud platform Download PDFInfo
- Publication number
- CN107645545A CN107645545A CN201710815961.1A CN201710815961A CN107645545A CN 107645545 A CN107645545 A CN 107645545A CN 201710815961 A CN201710815961 A CN 201710815961A CN 107645545 A CN107645545 A CN 107645545A
- Authority
- CN
- China
- Prior art keywords
- mtd
- mrow
- msub
- mtr
- virus
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a kind of virus monitor early warning system based on cloud platform, including data collection station, high in the clouds monitoring center and subscription client；The data collection station includes air sampling equipment, 3G network interface, single-chip microcomputer；The data collection station is used to monitor virus in air in real time, and Monitoring Data is sent into high in the clouds monitoring center by 3G network；The high in the clouds Surveillance center is used to compare the viral level in viral species and air that analysis collects, stores comparison result, and when there is abnormal occur, warning information is published into the subscription client；The high in the clouds Surveillance center also includes virus database, and the database is used to store Virus Info and comparison result；The subscription client is used to receive high in the clouds control centre information, accesses high in the clouds control centre.The present invention can accurately, in time, comprehensively reflect the present situation and development trend of transmitted virus in air, and very important effect is played for virus precaution and viral communication control etc..
Description
Technical field
The present invention relates to safety monitoring field, and in particular to a kind of virus monitor early warning system and side based on cloud platform
Method.
Background technology
There are many problems in the current air quality environment in China, virus is propagated rapidly, in crowd massing field in atmosphere
It is particularly susceptible to cause and breaks out.Therefore carry out capture viral in atmosphere, monitoring, establish viral early warning mechanism in air, together
When combine monitoring materials, carry out virus prevention and control, ensure that the health of people is necessary.And pass through
The environmental safety in the crowd massing regions such as hospital, station, square is evaluated, actively prevention can be reached, ensure target group's body
Body health, the purpose of virus diffusion is prevented in time.Virus monitor early warning system based on cloud platform breaches traditional monitoring side
Method, with the design concept of innovation, monitoring and warning is organically combined with cloud computing technology, framework big data processing platform, use
Big data is excavated and analysis method, and combining environmental concrete condition serves great for systematically research improvement quality of air environment
Innovate supporting role.It can accurately, in time, comprehensively reflect the present situation and development trend of transmitted virus in air, it is pre- for virus
Very important effect is played in anti-and viral communication control etc..
The content of the invention
Analyzed it is an object of the invention to provide a kind of virus monitor early warning system based on cloud platform and based on big data
Artificial intelligence Forecasting Methodology.
The present invention realizes that the technical scheme of foregoing invention purpose is：
A kind of virus monitor early warning system based on cloud platform, it is characterised in that：Monitored including data collection station, high in the clouds
Center and subscription client；
The data collection station includes air sampling equipment, 3G network interface, single-chip microcomputer；
The data collection station is used to monitor virus in air in real time, and Monitoring Data is sent into cloud by 3G network
Hold monitoring center；The high in the clouds Surveillance center is used to compare the viral level in viral species and air that analysis collects, deposits
Comparison result is stored up, when there is abnormal occur, warning information is published to the subscription client；The high in the clouds Surveillance center also wraps
Virus database is included, the database is used to store Virus Info and comparison result；The subscription client is used to receive institute
High in the clouds control centre information is stated, accesses high in the clouds control centre.
Virus in air monitoring situation is timely transmitted to client, the user of different rights by the present invention using technology of Internet of things
Relevant information can be understood in time, then taken appropriate measures.
Brief description of the drawings
Fig. 1 is the system schematic of the present invention.
Fig. 2 is the system flow chart of the present invention.
Fig. 3 is the BP neural network schematic diagram without genetic algorithm optimization of the present invention.
Fig. 4 is the BP neural network schematic diagram through genetic algorithm optimization of the present invention.
Fig. 5 is the chromosome bit string of the present invention and the coding mapping graph of a relation of power threshold value.
Embodiment
The technical scheme in the embodiment of the present invention will be clearly and completely described below, it is clear that described implementation
Example only part of the embodiment of the present invention, rather than whole embodiments.It is common based on the embodiment in the present invention, this area
The every other embodiment that technical staff is obtained under the premise of creative work is not made, belong to the model that the present invention protects
Enclose.
As shown in figure 1, the invention provides a kind of embodiment：
Virus monitor early warning system based on cloud platform, it is characterised in that：Including data collection station, high in the clouds monitoring center
And subscription client；
The data collection station includes air sampling equipment, 3G network interface, single-chip microcomputer；
The data collection station is used to monitor virus in air in real time, and Monitoring Data is sent into cloud by 3G network
Hold monitoring center；The high in the clouds Surveillance center is used to compare the viral level in viral species and air that analysis collects, deposits
Comparison result is stored up, when there is abnormal occur, warning information is published to the subscription client；The high in the clouds Surveillance center also wraps
Virus database is included, the database is used to store Virus Info and comparison result；The subscription client is used to receive institute
High in the clouds control centre information is stated, accesses high in the clouds control centre.
As shown in Fig. 2 the invention provides another embodiment：
A kind of virus monitor method for early warning of virus monitor early warning system based on cloud platform, it is characterised in that：Including：
Step 000, there is provided a kind of virus monitor early warning system based on cloud platform, including data collection station, high in the clouds prison
Measured center and subscription client；
The data collection station includes air sampling equipment, 3G network interface, single-chip microcomputer；
The data collection station is used to monitor virus in air in real time, and Monitoring Data is sent into cloud by 3G network
Hold monitoring center；The high in the clouds Surveillance center is used to compare the viral level in viral species and air that analysis collects, deposits
Comparison result is stored up, when there is abnormal occur, warning information is published to the subscription client；The high in the clouds Surveillance center also wraps
Virus database is included, the database is used to store Virus Info and comparison result；The subscription client is used to receive institute
High in the clouds control centre information is stated, accesses high in the clouds control centre；
Step 100, real-time condition viral in the data collection station collection air；
Step 200, collection information state is sent in the monitoring of high in the clouds at regular intervals between the data collection station
The heart；
Step 300, the high in the clouds Surveillance center receives the data sent from data collection station, and intelligence is carried out to data
Analysis, judge and identify；
Step 400, the high in the clouds Surveillance center is stored Monitoring Data and analysis result, and at regular intervals
Update the virus database；
Step 500, the high in the clouds Surveillance center is issued the analysis result of step 300 to client, is released news
Content is that whether viral species and content have abnormal conditions in air；
Step 600, the information of the client real-time reception high in the clouds Surveillance center issue, can also be actively to the high in the clouds
Surveillance center is inquired about, and inquiry content includes virus safe situation, virus characteristic, monitoring device running situation.
Particularly, the step 100 further comprises：
Step 120：The voltage x current that the virus in air species and content of collection, equipment are run is believed in various kinds of sensors timing
The single-chip microcomputer of acquisition terminal number is sent to, various signals are converted into data signal by the single-chip microcomputer, and carry out digital filtering, are picked
Except noise and wrong data；
Step 140：Single-chip microcomputer pre-processes step 120 resulting data, by setting communication protocol, by different numbers
It is believed that breath is encoded, send 3G network interface to by 485 buses, be converted to 3G network signal, send to the high in the clouds and supervise
Control center.
As shown in figure 3, special, the step 300 further comprises：
Step 310：Using the data in the virus database as training data；
Step 320：The power threshold value is simultaneously assigned to BP neural network by initialization power threshold value；
Step 330：The BP neural network is trained to assigned error scope；
Step 340：Virus concentration in the real-time air that the data collection station gathers is input to as test data
BP neural network, obtain prediction result.
Particularly, the method for step 320 initialization power threshold value includes：
It is i, middle layer node j provided with input node, the BP neural network that output node layer is k, then corresponds to BP nerves
Network has following matrix；
The input layer of BP neural network is to intermediate layer connection weight matrix：
The intermediate layer threshold matrix of BP neural network
The intermediate layer of BP neural network is to output layer connection weight matrix
The output layer threshold matrix of BP neural network
Each element is the random number for belonging to [- 1,1] section in wherein W, γ, V, h.
It is as shown in figure 4, special, there is provided a kind of improved method of step 300：Including：
Step 350：Using the data in the virus database as training data；
Step 355：Initial threshold value is subjected to binary coding；
Step 360：Relevant parameter, including population scale, crossing-over rate, aberration rate and evolutionary generation are set；
Step 366：Fitness function designs；
Step 370：Selection, intersection in execution genetic algorithm, mutation operation, circulation obtain optimal solution；
The selection opertor of the present invention is an improved wheel disc bet method, and crossover operator is random multiple-spot detection, and variation is calculated
For son using the method for random selection variation, maximum cycle is 20000 times.
Step 377：Optimal power threshold value is assigned to BP neural network；
Step 380：Virus concentration is normalized in the real-time air that the data collection station is gathered；
Step 388：Sample data assignment after normalization is inputted into BP neural network；
Step 390：BP neural network is trained to assigned error scope；
Step 399：Test data is input to BP neural network, obtains prediction result.
Particularly, step 355 further comprises:
In order to carry out the power threshold optimization of BP neural network, i.e., the optimization of above-mentioned 4 matrix Ws, y, V and h using GA, it is necessary to
Convert thereof into the chromosome string of convenient operation.Each individual is represented with binary string, individual quality fitness function
Value i.e. evaluation function are evaluated.The coding mapping relation of chromosome bit string and power threshold value is as shown in Figure 5：
Wherein w11′,w12′...wij′、γ1′…γj′、v11′,v12′…vjk′、h1′,h2′…hk' it is respectively w11,w12…
wij、γ1,γ2…γj、v11,v12…vjk、h1,h2…hkValue after being represented with binary string,'s
It is worth for 0 or 1.
The length of binary string is determined by the scope and precision of parameter, represents to be input to binary string for power threshold value
In network, its cataloged procedure is as follows:
The scope of setting parameter is arbitrarily joined in [Umin, Umax], the binary character string for being λ with length to represent therein
Number, thus it a total of 2λKind coding, δ is precision, and its parameter and coding corresponding relation are：
Binary coding accuracy formula is：
Decoding is as follows：
Assuming that chromosome coding corresponding to some power threshold value is：X：bλbλ-1bλ-2......b2b1, first by given accuracy
λ is determined, corresponding decoding formula is：
Wherein beFor the e positions value of chromosome coding corresponding to power threshold value.
Further, the determination method of evaluation function is in step 366：
According to the feature of viral quality forecasting problem in air, the error function of BP neural network is defined as：
Wherein E (W) is the error for weighing BP neural network when threshold value is W；tq(p), yq(p) represent respectively it is desirable that obtaining
Value and the obtained value of actual prediction, l and the number that k represents the number of training sample respectively and output layer includes node.
tq(p) determined by the history virus concentration data in virus database, yq(p) by the history ratio in virus database
Result is determined.
The final purpose of network model training is being constantly incremented by with evolutionary generation, and error function is constantly reducing,
Fitness value is constantly to increase, and is that this is according to error function construction fitness coefficient i.e. evaluation function:
Wherein ξ is the minimum close to 0.
The process of evolutive network power threshold value is mainly to determine encoding scheme, produces initial population, is constructed according to practical problem
Fitness function, its probability is determined further according to fitness size, completes selection, is intersected, variation, extremely produces optimum population.
Particularly, step 380 further comprises：
Wherein:yuRepresent the u kind virus concentrations that the data collection station sampling receives, yu' it is yuNumber after normalization
According to ymimRepresent the minimum value in this group of data, ymaxRepresent the maximum in this group of data, yu' be input to as the input factor
BP neural network model.
Particularly, the information that subscription client energy real-time reception high in the clouds Surveillance center issues in the step 600, can also
Actively into monitoring, the relevant data of server are inquired about, and inquiry content includes virus safe situation, virus characteristic, monitoring device
Running situation etc..Its principal character includes：Subscription client can be led for the historical data that high in the clouds Surveillance center issues
Dynamic inquiry, authentication, gain access are first passed through headed by the mode of inquiry, you can access the number of high in the clouds Surveillance center
According to data set different access rights, and the user of different rights grade can access different contents；Subscription client can be
Various handheld terminals, smart mobile phone or or PC etc..
In the case that following table gives different amount of training data, the viral Forecasting Methodology based on BP neural network in the present invention
And the accuracy rate (percentage) of the viral Forecasting Methodology based on genetic algorithm and BP neural network, data can from table
Go out, amount of training data is bigger, and two methods accuracy rate of the invention is higher.With the viral Forecasting Methodology phase based on BP neural network
Than based on genetic algorithm and BP neural network Forecasting Methodology due to have passed through optimization, accuracy rate is higher.Therefore, base of the invention
Unexpected effect is achieved in the viral Forecasting Methodology of genetic algorithm and BP neural network, is had compared with prior art aobvious
The progress of work.
In the case that following table gives different predicted data amounts, the viral Forecasting Methodology based on BP neural network in the present invention
And the accuracy rate (percentage) of the viral Forecasting Methodology based on genetic algorithm and BP neural network, data can from table
Go out, predicted data amount is bigger, and two methods accuracy rate of the invention is higher.With the viral Forecasting Methodology phase based on BP neural network
Than based on genetic algorithm and BP neural network Forecasting Methodology due to have passed through optimization, predictablity rate is higher.Therefore, it is of the invention
The viral Forecasting Methodology based on genetic algorithm and BP neural network achieve unexpected effect, have compared with prior art
There is significant progress.
| 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 is obvious to a person skilled in the art that the invention is not restricted to the details of above-mentioned one exemplary embodiment, Er Qie
In the case of without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, embodiment all should be regarded as exemplary, and be nonrestrictive, the scope of the present invention is by appended power
Profit requires rather than described above limits, it is intended that all in the implication and scope of the equivalency of claim by falling
Change is included in the present invention.
Claims (7)
1. the virus monitor early warning system based on cloud platform, it is characterised in that：Including data collection station, high in the clouds monitoring center and
Subscription client；
The data collection station includes air sampling equipment, 3G network interface, single-chip microcomputer；
The data collection station is used to monitor virus in air in real time, and Monitoring Data is sent into high in the clouds by 3G network and supervised
Measured center；The high in the clouds Surveillance center is used to compare the viral level in viral species and air that analysis collects, stores ratio
To result, when there is abnormal occur, warning information is published to the subscription client；The high in the clouds Surveillance center also includes disease
Malicious database, the database are used to store Virus Info and comparison result；The subscription client is used to receive the cloud
Control centre's information is held, accesses high in the clouds control centre.
2. a kind of virus monitor method for early warning of the virus monitor early warning system according to claim 1 based on cloud platform,
It is characterized in that：Including：
A kind of step 000, there is provided virus monitor early warning system based on cloud platform as claimed in claim 1；
Step 100, real-time condition viral in the data collection station collection air；
Step 200, collection information state is sent to high in the clouds Surveillance center at regular intervals between the data collection station；
Step 300, the high in the clouds Surveillance center receives the data sent from data collection station, and intelligence point is carried out to data
Analysis, judge and identify；
Step 400, the high in the clouds Surveillance center is stored Monitoring Data and analysis result, and is updated at regular intervals
The virus database；
Step 500, the high in the clouds Surveillance center is issued the analysis result of step 300 to the client, is released news
Content is that whether viral species and content have abnormal conditions in air；
Step 600, the information of the client real-time reception high in the clouds Surveillance center issue, actively can also be monitored to the high in the clouds
Center is inquired about, and inquiry content includes virus safe situation, virus characteristic, monitoring device running situation.
3. virus monitor method for early warning according to claim 2, it is characterised in that：The step 100 further comprises：
Step 120：Various kinds of sensors timing passes the voltage and current signal that the virus in air species and content of collection, equipment are run
The single-chip microcomputer of acquisition terminal is delivered to, various signals are converted into data signal by the single-chip microcomputer, and carry out digital filtering, and rejecting is made an uproar
Sound and wrong data；
Step 140：Single-chip microcomputer pre-processes step 120 resulting data, and by setting communication protocol, different data are believed
Breath is encoded, and is sent 3G network interface to by 485 buses, is converted to 3G network signal, is sent to the high in the clouds in monitoring
The heart.
4. virus monitor method for early warning according to claim 2, it is characterised in that：The step 300 further comprises：
Step 310：Using the data in the virus database as training data；
Step 320：The power threshold value is simultaneously assigned to BP neural network by initialization power threshold value；
Step 330：The BP neural network is trained to assigned error scope；
Step 340：BP god is input to using virus concentration in the real-time air that the data collection station gathers as test data
Through network, prediction result is obtained.
5. the virus monitor method for early warning according to claim 2 based on cloud platform, it is characterised in that：The step 300
Further comprise：
Step 350：Using the data in the virus database as training data；
Step 355：Initial threshold value is subjected to binary coding；
Step 360：Relevant parameter, including population scale, crossing-over rate, aberration rate and evolutionary generation are set；
Step 366：Fitness function designs；
Step 370：Selection, intersection in execution genetic algorithm, mutation operation, circulation obtain optimal solution；
Step 377：Optimal power threshold value is assigned to BP neural network；
Step 380：Virus concentration is normalized in the real-time air that the data collection station is gathered；
Step 388：Sample data after normalization is inputted into BP neural network；
Step 390：BP neural network is trained to assigned error scope；
Step 399：Test data is input to BP neural network, obtains prediction result.
6. the virus monitor method for early warning according to claim 5 based on cloud platform, it is characterised in that：The step 355
Including：
Step 356:Initialize BP neural network power threshold value：
It is i, middle layer node j provided with input node, the BP neural network that output node layer is k, then corresponds to BP neural network
There is following matrix；
The input layer of BP neural network is to intermediate layer connection weight matrix：
<mrow>
<mi>W</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>w</mi>
<mn>11</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mn>12</mn>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mrow>
<mn>1</mn>
<mi>j</mi>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>w</mi>
<mn>21</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mn>22</mn>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mrow>
<mn>2</mn>
<mi>j</mi>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mn>1</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mn>2</mn>
</mrow>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
The intermediate layer threshold matrix of BP neural network
<mrow>
<mi>&gamma;</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>&gamma;</mi>
<mn>1</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>&gamma;</mi>
<mn>2</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>...</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>&gamma;</mi>
<mi>j</mi>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
The intermediate layer of BP neural network is to output layer connection weight matrix
<mrow>
<mi>V</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>v</mi>
<mn>11</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mn>12</mn>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mrow>
<mn>1</mn>
<mi>k</mi>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>v</mi>
<mn>21</mn>
</msub>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mn>22</mn>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mrow>
<mn>2</mn>
<mi>k</mi>
</mrow>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>v</mi>
<mrow>
<mi>j</mi>
<mn>1</mn>
</mrow>
</msub>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mrow>
<mi>j</mi>
<mn>2</mn>
</mrow>
</msub>
</mtd>
<mtd>
<mo>...</mo>
</mtd>
<mtd>
<msub>
<mi>v</mi>
<mrow>
<mi>j</mi>
<mi>k</mi>
</mrow>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
The output layer threshold matrix of BP neural network
<mrow>
<mi>h</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<msub>
<mi>h</mi>
<mn>1</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>h</mi>
<mn>2</mn>
</msub>
</mtd>
</mtr>
<mtr>
<mtd>
<mo>...</mo>
</mtd>
</mtr>
<mtr>
<mtd>
<msub>
<mi>h</mi>
<mi>k</mi>
</msub>
</mtd>
</mtr>
</mtable>
</mfenced>
<mo>;</mo>
</mrow>
Each element is the random number for belonging to [- 1,1] section in wherein W, γ, V, h；
Step 357：Binary coding digit is calculated according to the required accuracy δ, formula is：
<mrow>
<mi>&delta;</mi>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>U</mi>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
</msub>
<mo>-</mo>
<msub>
<mi>U</mi>
<mrow>
<mi>m</mi>
<mi>i</mi>
<mi>n</mi>
</mrow>
</msub>
</mrow>
<mrow>
<msup>
<mn>2</mn>
<mi>&lambda;</mi>
</msup>
<mo>-</mo>
<mn>1</mn>
</mrow>
</mfrac>
</mrow>
Wherein Umin, Umax are respectively the minimum value and maximum of single power threshold value, and λ is that the binary system for representing single power threshold value is compiled
Code bit number；
Step 358：Determine chromosome coding：
Wherein w11′,w12′...wij′、γ′1…γ′j、v11′,v12′…vjk′、h1′,h2′…hk' it is respectively w11,w12…wij、
γ1,γ2…γj、v11,v12…vjk、h1,h2…hkValue after being represented with binary string,Value be
0 or 1.
7. the virus monitor method for early warning according to claim 5 based on cloud platform, it is characterised in that：Commented in step 366
The determination method of valency function is：
According to the feature of viral quality forecasting problem in air, the error function of BP neural network is defined as：
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>W</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mn>2</mn>
</mfrac>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>l</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>q</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>k</mi>
</munderover>
<mo>|</mo>
<msub>
<mi>t</mi>
<mi>q</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>)</mo>
</mrow>
<mo>-</mo>
<msub>
<mi>y</mi>
<mi>q</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>p</mi>
<mo>)</mo>
</mrow>
<mo>|</mo>
</mrow>
Wherein E (W) is the error for weighing BP neural network when threshold value is W；tq(p), yq(p) desired value and reality are represented respectively
Predict obtained value, the number that l and k represent the number of training sample respectively and output layer includes node in border；
Then evaluation function is:
<mrow>
<mi>f</mi>
<mi>i</mi>
<mi>t</mi>
<mrow>
<mo>(</mo>
<mi>W</mi>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mfrac>
<mn>1</mn>
<mrow>
<mi>E</mi>
<mrow>
<mo>(</mo>
<mi>W</mi>
<mo>)</mo>
</mrow>
<mo>+</mo>
<mi>&xi;</mi>
</mrow>
</mfrac>
</mrow>
Wherein ξ is the minimum close to 0.
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 true CN107645545A (en) | 2018-01-30 |
| CN107645545B 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) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109407629A (en) * | 2018-09-11 | 2019-03-01 | 广州市赛特检测有限公司 | A kind of pathogen on-line monitoring system and method |
| 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 |
| CN113035352A (en) * | 2021-04-27 | 2021-06-25 | 河南科技大学 | Diabetic retinopathy early warning method based on BP neural network |
| 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 |
| CN113204108A (en) * | 2021-03-19 | 2021-08-03 | 刘利军 | Multifunctional dissecting microscope |
| CN113267598A (en) * | 2020-02-17 | 2021-08-17 | 曾学军 | Intelligent air quality monitoring and analyzing system based on internet technology |
| 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 |
| CN115981256A (en) * | 2022-12-19 | 2023-04-18 | 肇庆高峰机械科技有限公司 | High in clouds control system of magnet steel pile up neatly device |
Citations (4)
| 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 |
| US20150032886A1 (en) * | 2011-11-23 | 2015-01-29 | Shen Wang | Remote Real-Time Monitoring System based on cloud computing |
| 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 |
-
2017
- 2017-09-12 CN CN201710815961.1A patent/CN107645545B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150032886A1 (en) * | 2011-11-23 | 2015-01-29 | Shen Wang | Remote Real-Time Monitoring System based on cloud computing |
| 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 |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109407629A (en) * | 2018-09-11 | 2019-03-01 | 广州市赛特检测有限公司 | A kind of pathogen on-line 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 |
| CN113035352A (en) * | 2021-04-27 | 2021-06-25 | 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 |
| CN115981256A (en) * | 2022-12-19 | 2023-04-18 | 肇庆高峰机械科技有限公司 | High in clouds control system of magnet steel pile up neatly device |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107645545B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107645545A (en) | A kind of virus monitor early warning system based on cloud platform | |
| Yang et al. | A new air quality monitoring and early warning system: Air quality assessment and air pollutant concentration prediction | |
| Janarthanan et al. | A deep learning approach for prediction of air quality index in a metropolitan city | |
| Asha et al. | IoT enabled environmental toxicology for air pollution monitoring using AI techniques | |
| CN106815971B (en) | A kind of landslide disaster forecasting procedure based on RBF neural | |
| Kang et al. | Application of BP neural network optimized by genetic simulated annealing algorithm to prediction of air quality index in Lanzhou | |
| CN107633638B (en) | A kind of Intelligent Fire Detection method based on WSN | |
| CN106997669A (en) | A kind of method of the judgement traffic congestion origin cause of formation of feature based importance | |
| CN113177737A (en) | Urban rainstorm disaster risk assessment method and system based on GA (genetic algorithm) optimization BP (back propagation) neural network | |
| CN109975366B (en) | Rural domestic sewage A2Soft measurement method and device for COD concentration of effluent from O treatment terminal | |
| CN108399470B (en) | Indoor PM2.5 prediction method based on multi-example genetic neural network | |
| CN111489015A (en) | Atmosphere O based on multiple model comparison and optimization3Concentration prediction method | |
| Wang et al. | Study on MPGA‐BP of gravity dam deformation prediction | |
| CN107871183A (en) | Permafrost Area highway distress Forecasting Methodology based on uncertain Clouds theory | |
| CN116681279A (en) | Forestry pest control risk assessment system based on data analysis | |
| Rokade et al. | IOT‐Based Medical Informatics Farming System with Predictive Data Analytics Using Supervised Machine Learning Algorithms | |
| CN110222916B (en) | Rural domestic sewage A2Soft measurement method and device for total nitrogen concentration of effluent from O treatment terminal | |
| CN115948964A (en) | Road flatness prediction method based on GA-BP neural network | |
| CN116862081A (en) | Operation and maintenance method and system for pollution treatment equipment | |
| CN116738354A (en) | Method and system for detecting abnormal behavior of electric power Internet of things terminal | |
| Ke et al. | The research of network intrusion detection technology based on genetic algorithm and bp neural network | |
| CN117164103A (en) | Intelligent control method, terminal and system of domestic sewage treatment system | |
| CN117350146A (en) | GA-BP neural network-based drainage pipe network health evaluation method | |
| Yin | Practice of air environment quality monitoring data visualization technology based on adaptive wireless sensor networks | |
| CN115775042B (en) | Crop heavy metal enrichment risk prediction method and system based on Bayesian theory |
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 |