CN107798077A - A kind of Population surveillance method and system - Google Patents
A kind of Population surveillance method and system Download PDFInfo
- Publication number
- CN107798077A CN107798077A CN201710934099.6A CN201710934099A CN107798077A CN 107798077 A CN107798077 A CN 107798077A CN 201710934099 A CN201710934099 A CN 201710934099A CN 107798077 A CN107798077 A CN 107798077A
- Authority
- CN
- China
- Prior art keywords
- data
- population
- mrow
- msub
- resource database
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Abstract
The present invention relates to a kind of Population surveillance method and system, including:Obtain the related data message of population and establish population resource database;Population resource database is pre-processed, including data pick-up, conversion, cleaning and loading;Obtained data are analyzed, obtain the prediction result of beneficial data.Population surveillance method proposed by the present invention, data, which pre-process, to be concerned about to governments such as city de facto population, employed population, social security populations based on ETL and wavelet neural network, realize data cleansing and analysis, data cleansing is carried out to demographic data by ETL instruments, and the data after cleaning are analyzed by wavelet neural network, population forecast result is obtained, reference frame is provided for the foundation of policy.
Description
Technical field
The present invention relates to data processing field, and in particular to a kind of Population surveillance method and system.
Background technology
New smart city with serve the people whole process is full-time, Urban Governance effective, data open it is co-melting shared, economical
Green is increased income, cyberspace clear and bright safely is main target for development.
To realize the target, the division data that trans-sectoral to city magnanimity need to be engaged in carries out unified fusion, shows and manage, and generates city
City's fuse information resources bank, that realizes information resources unifies issue, the on demand function such as subscription and exchange and interdynamic, can be each towards city
Operation system, each committee do office, the public provides information resources serviceization shared key foundation tenability.Multi-source information melts
Conjunction method provides the business service of information conversion and information fusion processing, the unified multi-source heterogeneous resource information of fusion, be across
System, cross-cutting information, which exchange, provides dynamic, expansible information format and Content Transformation ability.
At present, document《Harbin City's community sanitation service information system design and realization》It is middle to propose a kind of information system,
Its method is:Data pick-up is completed to Data Mart, establishes data cube, C# passes through the number in MDX language call cubes
According to member, realize health account public affairs and defend medical treatment and outpatient clinician interconnection, bidirectionally transfering consultation, statistical report form, expert's aid decision community
The building-up work of Health Services platform.When doing morbidity crowd's quantitative forecast, it is difficult to solve some using Analytic Hierarchy Process Model first
With acquisition elements and the weight analysis based on time series wavelet neural network morbidity crowd's quantity, then the weight knot by analysis
The weight of fruit and wavelet neural prediction carries out factor of the ratio calculating as wavelet neural prediction result weighted calculation, final to calculate
Go out the forecasted population number of morbidity crowd, experiment shows that prediction result robustness is good, corresponds to actual needs.Although for one in text
A little algorithms propose and have done analysis of cases, but real data is also difficult to gather now, need to the further research of data mining algorithm,
It was found that more actual models.
Document《The design and realization of demographic data analysis system based on data warehouse》Data are suffered from as number using people's message
According to support, using data warehouse as technical foundation, by the Various types of data source ETL (Extraction in system
Transformation Loading, that is, extract, change, load) into data warehouse, data are divided according to practical business demand
Class stores, and according to the numerical value to be investigated and the angle of analysis, refines business datum, specified dimension, forms true table and dimension table
Analyze data model, study the basic skills of demographic data statistical analysis, and using multidimensional analysis OLAP (On-Line
Analytical Processing, i.e. on-line analytical processing) technology, it is fabricated to according to a variety of dimensions and shows analytical statement, finally
One is built up for decision references, the demographic data analysis system of analysis and research.One is built based on people information data
Data analysis system, effective data will be provided and supported for decision references, the market development, research publicity, and be each machine of society
Structure provides effective, customizable statistical data analysis, excavates out the bigger value that demographic data is contained in itself.But the document
The middle data OLAP operations used and report form showing and query performance have much room for improvement, demographic data analysis research angle and content
Need further perfect.
The content of the invention
To realize city population data acquisition, data prediction and the target of data analysis, for existing for prior art
Defect, the present invention propose a kind of Population surveillance method, based on ETL and wavelet neural network to city de facto population, employment people
The governments such as mouth, social security population are concerned about that data are pre-processed, and data cleansing and analysis are realized, by ETL instruments to demographic data
Data cleansing is carried out, and the data after cleaning are analyzed by wavelet neural network, population forecast result is obtained, is policy
Foundation provide reference frame.
To achieve the above object, the present invention proposes a kind of Population surveillance method, including:
S1:Obtain the related data message of population and establish population resource database;
S2:Population resource database is pre-processed, including data pick-up, conversion, cleaning and loading;
S3:Obtained data are analyzed, obtain the prediction result of beneficial data.
Preferably, the data prediction includes:
S21:Population resource database is extracted on demand using configuration information;
S22:Each population resource database data are changed according to unified object format;
S23:Abnormality processing is carried out to the population resource database after conversion and repeats to detect, completes data cleansing;
S24:Data after cleaning are generated into target database.
Specifically, configuration information described in step S21 includes the type of the population resource database, the population number of resources
According to the type of tables of data in storehouse, the field of tables of data in the population resource database, the population resource database data turn
Change, the data type of data cleansing and finally import Target database name.
Specifically, object format unified described in step S22 is:Name, sex is national, identification card number, political affiliation,
Marriage and childbirth situation, household register, work unit, contact method.
Further, the data analysis carries out wavelet decomposition, the wavelet decomposition letter to pretreated demographic data
Number selects Morlet morther wavelet basic functions, the data after decomposition is trained using neutral net, and training result is added
Wavelet reconstruction is carried out, and obtains population forecast result.
Further, the data analysis includes:
S31:Demographic data after data prediction is normalized:
Wherein, x 'iFor the sample value that will be obtained after i-th of sample value processing;xminFor minimum value in sample;xmaxFor sample
Middle maximum;
S32:Neutral net initializes, and from three layers of network structure, sets input layer, hidden layer and output layer neuron
Number;The connection weight of the contraction-expansion factor of network, shift factor and network is assigned to random initial value;
S33:Wavelet function is determined, the excitation function h (x) of hidden neuron=cos is used as using Morlet wavelet functions
(1.75x)·exp(-x2/2);
S34:Calculated using wavelet neural network, and define error function:
Wherein, ypFor the real output value under p-th of pattern sample;It is defeated for the target under p-th of pattern sample
Go out value;For one group of limited basic function in C [0, T] space, T is pre-
Survey the higher limit of time domain;
Conversion basic function using Morlet small echos as hidden layer, then have:
Wherein, xz=(x-bj)/aj, ajFor wavelet neural member j scaling coefficient;bjFor wavelet neural member j translation coefficient,
Work as ajIt is low to the resolution ratio of frequency domain when smaller, to the high resolution of time domain;Work as ajDuring increase, to the high resolution of frequency domain, pair when
The resolution ratio in domain is low;
S35:Establish Population Forecast Model, during prediction, be used to predict the latter numerical value per adjacent N number of data, pass through net
The study of network, the mapping relations for being input to output are established, wherein, N >=2.
In addition, present invention also offers a kind of Population surveillance system, including:
Data capture unit, for obtaining the related data message of population and establishing population resource database;
Data pre-processing unit, be coupled with data capture unit, for population resource database carry out data pick-up,
Conversion, cleaning and loading;
Data analysis unit, it is coupled with data pre-processing unit, for obtaining the prediction result of beneficial data.
Further, the data pre-processing unit includes:
Data extraction module, population resource database is extracted on demand according to configuration information specified in ETL;
Data conversion module, it is coupled with data extraction module, according to unified object format to each population resource data
Storehouse data are changed;
Data cleansing module, it is coupled with data conversion module, exception is carried out to the population resource database after conversion
Reason and repetition detect;
Data load-on module, is coupled with data cleansing module, and the data after cleaning are generated into target database.
Specifically, the configuration information in the data extraction module includes the type of the population resource database, it is described
The type of tables of data in population resource database, the field of tables of data, the population number of resources in the population resource database
Import according to storehouse data conversion, the data type of data cleansing and finally Target database name.
Specifically, the unified object format in the data conversion module is:Name, sex is national, identification card number,
Political affiliation, marriage and childbirth situation, household register, work unit, contact method.
Further, the data analysis unit carries out wavelet decomposition, the small wavelength-division to pretreated demographic data
Solution function selects Morlet morther wavelet basic functions, and the data after decomposition are trained using neutral net, and by training result
It is added and carries out wavelet reconstruction, and obtains population forecast result.
Further, the data analysis unit includes:
Normalized module, for the demographic data after data prediction to be normalized;
Neutral net initialization module, for setting neutral net initiation parameter, from three layers of network structure, set
The number of input layer, hidden layer and output layer neuron;The connection weight of the contraction-expansion factor of network, shift factor and network is assigned
Give random initial value;
Wavelet function determining module, for the determination of wavelet function, hidden neuron is used as using Morlet wavelet functions
Excitation function;
Computing module, for being calculated using wavelet neural network, and define error function, using Morlet small echos as
The conversion basic function of hidden layer;
Population forecast module, for establishing Population Forecast Model, during prediction, it is used to predicting per adjacent N number of data latter
Individual numerical value, by the study of network, the mapping relations for being input to output are established, wherein, N >=2.
Brief description of the drawings
Fig. 1 is the process schematic of population monitoring method.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, below in conjunction with accompanying drawing and example, to this
Invention is further elaborated, it will be appreciated that instantiation described herein only to explain the present invention, is not used to
Limit the present invention.
The embodiment of the present invention proposes a kind of Population surveillance method, including
S1:Obtain the related data message of population and establish population resource database:From city, each business department obtains people
The related data message of mouth, establishes the population resource database such as social security, employment;
S2:Population resource database is pre-processed, including data pick-up, conversion, cleaning and loading;
The data pick-up refers to take out population source database on demand according to configuration information specified in ETL nucleus modules
Take;Wherein described configuration information includes the type of the population resource database, tables of data in the population resource database
Type, the field of tables of data, the population resource database data conversion, the number of data cleansing in the population resource database
According to type and finally import Target database name.
The data conversion refers to because the form of each business department in city statistics population is inconsistent, data conversion i.e. according to
Unified object format is changed to each population resource database data;The unified object format is:Name, sex,
Nationality, identification card number, political affiliation, marriage and childbirth situation, household register, work unit, contact method.
The data cleansing refers to carry out the population resource database after conversion abnormality processing and repeats to detect;The number
Refer to the data after cleaning generating target database according to loading;
S3:Obtained data are analyzed, obtain the prediction result of beneficial data.
Normalized.Demographic data is normalized:
Wherein, x 'iFor the sample value that will be obtained after i-th of sample value processing;xminFor minimum value in sample;xmaxFor sample
Middle maximum.
Netinit.From three layers of network structure, network topology structure 5-25-3, i.e. input layer, hidden layer and defeated
The number for going out layer neuron is respectively 5,25 and 3.The connection weight of the contraction-expansion factor of network, shift factor and network is assigned
The random initial value of (- 0.5,0.5) nearby.
Wherein, in selected network topological structure, input layer number is identical with source database number, output layer number and target
Database number is identical, and hidden layer number empirically formula can be chosen with inputting, exporting number correlation, the present embodiment selection network
Topological structure is 5-25-3, and random starting values are between (- 0.5,0.5).
The determination of wavelet function.Using Morlet wavelet functions as the excitation function of hidden neuron, i.e.,:
H (x)=cos (1.75x) exp (- x2/2)
Calculated using wavelet neural network.Define error function:
Wherein, ypFor the real output value under p-th of pattern sample;It is defeated for the target under p-th of pattern sample
Go out value;For one group of limited basic function in C [0, T] space, T is pre-
Survey the higher limit of time domain.
Conversion basic function using Morlet small echos as hidden layer, then have:
Wherein, xz=(x-bj)/aj, ajFor wavelet neural member j scaling coefficient;bjFor wavelet neural member j translation coefficient.
Work as ajIt is low to the resolution ratio of frequency domain when smaller, to the high resolution of time domain;Work as ajDuring increase, to the high resolution of frequency domain, pair when
The resolution ratio in domain is low.
Establish Population Forecast Model, during prediction, be used to predict the latter numerical value per 8 adjacent data, pass through network
Study, establishes the mapping relations for being input to output.
In addition, the embodiment of the present invention additionally provides a kind of Population surveillance system, including:
Data capture unit, for obtaining the related data message of population and establishing population resource database;
Data pre-processing unit, be coupled with data capture unit, for population resource database carry out data pick-up,
Conversion, cleaning and loading;
Data analysis unit, it is coupled with data pre-processing unit, for obtaining the prediction result of beneficial data.
Further, the data pre-processing unit includes:
Data extraction module, population resource database is extracted on demand according to configuration information specified in ETL;
Data conversion module, it is coupled with data extraction module, according to unified object format to each population resource data
Storehouse data are changed;
Data cleansing module, it is coupled with data conversion module, exception is carried out to the population resource database after conversion
Reason and repetition detect;
Data load-on module, is coupled with data cleansing module, and the data after cleaning are generated into target database.
Specifically, the configuration information in the data extraction module includes the type of the population resource database, it is described
The type of tables of data in population resource database, the field of tables of data, the population number of resources in the population resource database
Import according to storehouse data conversion, the data type of data cleansing and finally Target database name.
Specifically, the unified object format in the data conversion module is:Name, sex is national, identification card number,
Political affiliation, marriage and childbirth situation, household register, work unit, contact method.
Further, the data analysis unit carries out wavelet decomposition, the small wavelength-division to pretreated demographic data
Solution function selects Morlet morther wavelet basic functions, and the data after decomposition are trained using neutral net, and by training result
It is added and carries out wavelet reconstruction, and obtains population forecast result.
Further, the data analysis unit includes:
Normalized module, for the demographic data after data prediction to be normalized;
Neutral net initialization module, for setting neutral net initiation parameter, from three layers of network structure, set
The number of input layer, hidden layer and output layer neuron;The connection weight of the contraction-expansion factor of network, shift factor and network is assigned
Give random initial value;
Wavelet function determining module, for the determination of wavelet function, hidden neuron is used as using Morlet wavelet functions
Excitation function;
Computing module, for being calculated using wavelet neural network, and define error function, using Morlet small echos as
The conversion basic function of hidden layer;
Population forecast module, for establishing Population Forecast Model, during prediction, it is used to predicting per adjacent N number of data latter
Individual numerical value, by the study of network, the mapping relations for being input to output are established, wherein, N >=2.
Claims (12)
1. a kind of Population surveillance method, including:
S1:Obtain the related data message of population and establish population resource database;
S2:Population resource database is pre-processed, including data pick-up, conversion, cleaning and loading;
S3:Obtained data are analyzed, obtain the prediction result of beneficial data.
2. Population surveillance method as claimed in claim 1, the data prediction include:
S21:Population resource database is extracted on demand using configuration information;
S22:Each population resource database data are changed according to unified object format;
S23:Abnormality processing is carried out to the population resource database after conversion and repeats to detect, completes data cleansing;
S24:Data after cleaning are generated into target database.
3. Population surveillance method as claimed in claim 1, configuration information described in step S21 includes the population resource database
Type, the type of tables of data in the population resource database, the field of tables of data, described in the population resource database
Population resource database data conversion, the data type of data cleansing and finally import Target database name.
4. Population surveillance method as claimed in claim 1, unified object format is described in step S22:Name, sex, the people
Race, identification card number, political affiliation, marriage and childbirth situation, household register, work unit, contact method.
5. Population surveillance method as claimed in claim 1, the data analysis carries out small echo to pretreated demographic data
Decompose, the wavelet decomposition function is selected Morlet morther wavelet basic functions, the data after decomposition are instructed using neutral net
Practice, and training result is added and carries out wavelet reconstruction, and obtain population forecast result.
6. Population surveillance method as claimed in claim 1, the data analysis include:
S31:Demographic data after data prediction is normalized:
<mrow>
<msubsup>
<mi>x</mi>
<mi>i</mi>
<mo>&prime;</mo>
</msubsup>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>min</mi>
</msub>
</mrow>
<mrow>
<msub>
<mi>x</mi>
<mi>max</mi>
</msub>
<mo>-</mo>
<msub>
<mi>x</mi>
<mi>min</mi>
</msub>
</mrow>
</mfrac>
</mrow>
Wherein, x 'iFor the sample value that will be obtained after i-th of sample value processing;xminFor minimum value in sample;xmaxFor in sample most
Big value;
S32:Neutral net initializes, and from three layers of network structure, sets the individual of input layer, hidden layer and output layer neuron
Number;The connection weight of the contraction-expansion factor of network, shift factor and network is assigned to random initial value;
S33:Wavelet function is determined, the excitation function h (x) of hidden neuron=cos is used as using Morlet wavelet functions
(1.75x)·exp(-x2/2);
S34:Calculated using wavelet neural network, and define error function:
<mrow>
<mi>E</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mi>y</mi>
<mi>p</mi>
</msup>
<mo>-</mo>
<msup>
<mover>
<mi>y</mi>
<mo>&OverBar;</mo>
</mover>
<mi>p</mi>
</msup>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>p</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>p</mi>
</munderover>
<msup>
<mrow>
<mo>{</mo>
<mo>&lsqb;</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>j</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>v</mi>
<mi>j</mi>
</msub>
<mi>h</mi>
<mo>&lsqb;</mo>
<mfrac>
<mrow>
<msubsup>
<mo>&Integral;</mo>
<mn>0</mn>
<mi>T</mi>
</msubsup>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>i</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>m</mi>
</munderover>
<msub>
<mi>w</mi>
<mrow>
<mi>i</mi>
<mi>j</mi>
</mrow>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<msub>
<mi>x</mi>
<mi>i</mi>
</msub>
<mrow>
<mo>(</mo>
<mi>t</mi>
<mo>)</mo>
</mrow>
<mi>d</mi>
<mi>t</mi>
<mo>-</mo>
<msub>
<mi>b</mi>
<mi>j</mi>
</msub>
</mrow>
<msub>
<mi>a</mi>
<mi>j</mi>
</msub>
</mfrac>
<mo>&rsqb;</mo>
<mo>-</mo>
<mi>&theta;</mi>
<mo>&rsqb;</mo>
<mo>-</mo>
<msup>
<mover>
<mi>y</mi>
<mo>&OverBar;</mo>
</mover>
<mi>p</mi>
</msup>
<mo>}</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
Wherein, ypFor the real output value under p-th of pattern sample;For the target output value under p-th of pattern sample;For one group of limited basic function in C [0, T] space, T is when predicting
The higher limit in domain;
Conversion basic function using Morlet small echos as hidden layer, then have:
<mrow>
<mi>h</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mi>z</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>=</mo>
<mi>c</mi>
<mi>o</mi>
<mi>s</mi>
<mrow>
<mo>(</mo>
<mn>1.75</mn>
<msub>
<mi>x</mi>
<mi>z</mi>
</msub>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<mi>exp</mi>
<mrow>
<mo>(</mo>
<mo>-</mo>
<msubsup>
<mi>x</mi>
<mi>z</mi>
<mn>2</mn>
</msubsup>
<mo>/</mo>
<mn>2</mn>
<mo>)</mo>
</mrow>
</mrow>
Wherein, xz=(x-bj)/aj, ajFor wavelet neural member j scaling coefficient;bjFor wavelet neural member j translation coefficient, work as aj
It is low to the resolution ratio of frequency domain when smaller, to the high resolution of time domain;Work as ajDuring increase, to the high resolution of frequency domain, to time domain
Resolution ratio is low;
S35:Establish Population Forecast Model, during prediction, be used to predict the latter numerical value per adjacent N number of data, pass through network
Study, establishes the mapping relations for being input to output, wherein, N >=2.
7. a kind of Population surveillance system, including:
Data capture unit, for obtaining the related data message of population and establishing population resource database;
Data pre-processing unit, it is coupled with data capture unit, for carrying out data pick-up to population resource database, turning
Change, clean and load;
Data analysis unit, it is coupled with data pre-processing unit, for obtaining the prediction result of beneficial data.
8. Population surveillance system as claimed in claim 7, the data pre-processing unit include:
Data extraction module, population resource database is extracted on demand according to configuration information specified in ETL;
Data conversion module, it is coupled with data extraction module, according to unified object format to each population resource database number
According to being changed;
Data cleansing module, be coupled with data conversion module, to after conversion population resource database carry out abnormality processing and
Repeat to detect;
Data load-on module, is coupled with data cleansing module, and the data after cleaning are generated into target database.
9. Population surveillance system as claimed in claim 8, the configuration information in the data extraction module includes the population
The type of resource database, the type of tables of data in the population resource database, tables of data in the population resource database
Field, the population resource database data conversion, the data type of data cleansing and finally import Target database name.
10. Population surveillance system as claimed in claim 8, the unified object format in the data conversion module is:Surname
Name, sex is national, identification card number, political affiliation, marriage and childbirth situation, household register, work unit, contact method.
11. Population surveillance system as claimed in claim 7, the data analysis unit is carried out to pretreated demographic data
Wavelet decomposition, the wavelet decomposition function are selected Morlet morther wavelet basic functions, the data after decomposition are entered using neutral net
Row training, and training result is added and carries out wavelet reconstruction, and obtain population forecast result.
12. Population surveillance system as claimed in claim 7, the data analysis unit include:
Normalized module, for the demographic data after data prediction to be normalized;
Neutral net initialization module, for setting neutral net initiation parameter, from three layers of network structure, input is set
The number of layer, hidden layer and output layer neuron;By the connection weight of the contraction-expansion factor of network, shift factor and network assign with
The initial value of machine;
Wavelet function determining module, for the determination of wavelet function, the excitation of hidden neuron is used as using Morlet wavelet functions
Function;
Computing module, for being calculated using wavelet neural network, and error function is defined, using Morlet small echos as implicit
The conversion basic function of layer;
Population forecast module, for establishing Population Forecast Model, during prediction, it is used to predict latter number per adjacent N number of data
Value, by the study of network, establishes the mapping relations for being input to output, wherein, N >=2.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710934099.6A CN107798077A (en) | 2017-10-09 | 2017-10-09 | A kind of Population surveillance method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710934099.6A CN107798077A (en) | 2017-10-09 | 2017-10-09 | A kind of Population surveillance method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107798077A true CN107798077A (en) | 2018-03-13 |
Family
ID=61533005
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710934099.6A Pending CN107798077A (en) | 2017-10-09 | 2017-10-09 | A kind of Population surveillance method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107798077A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704789A (en) * | 2019-08-16 | 2020-01-17 | 重庆特斯联智慧科技股份有限公司 | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform |
CN110807546A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Community grid population change early warning method and system |
CN110807547A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Method and system for predicting family population structure |
WO2021103321A1 (en) * | 2019-11-29 | 2021-06-03 | 青岛理工大学 | Population change monitoring visualization system for old district of historic city |
CN113109669A (en) * | 2021-04-12 | 2021-07-13 | 国网陕西省电力公司西安供电公司 | Power distribution network series-parallel line fault positioning method based on traveling wave characteristic frequency |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102838A (en) * | 2014-07-14 | 2014-10-15 | 河海大学 | Transformer noise prediction method based on wavelet neural network and wavelet technology |
CN105139264A (en) * | 2015-06-06 | 2015-12-09 | 安徽工程大学 | Photovoltaic generation capacity prediction method based on particle swarm algorithm wavelet neural network |
-
2017
- 2017-10-09 CN CN201710934099.6A patent/CN107798077A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104102838A (en) * | 2014-07-14 | 2014-10-15 | 河海大学 | Transformer noise prediction method based on wavelet neural network and wavelet technology |
CN105139264A (en) * | 2015-06-06 | 2015-12-09 | 安徽工程大学 | Photovoltaic generation capacity prediction method based on particle swarm algorithm wavelet neural network |
Non-Patent Citations (3)
Title |
---|
张新红: "小波理论及其在经济预测中的应用研究", 《中国博士学位论文全文数据库 社会科学Ⅰ辑》 * |
杨丽: "小波理论在大坝变形监测数据分析中的应用研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
郭锐: "基于数据仓库的人口数据分析系统的设计及实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110704789A (en) * | 2019-08-16 | 2020-01-17 | 重庆特斯联智慧科技股份有限公司 | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform |
CN110807546A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Community grid population change early warning method and system |
CN110807547A (en) * | 2019-10-22 | 2020-02-18 | 恒大智慧科技有限公司 | Method and system for predicting family population structure |
WO2021103321A1 (en) * | 2019-11-29 | 2021-06-03 | 青岛理工大学 | Population change monitoring visualization system for old district of historic city |
CN113109669A (en) * | 2021-04-12 | 2021-07-13 | 国网陕西省电力公司西安供电公司 | Power distribution network series-parallel line fault positioning method based on traveling wave characteristic frequency |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107798077A (en) | A kind of Population surveillance method and system | |
CN109508360B (en) | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton | |
Ahmad et al. | An efficient divide-and-conquer approach for big data analytics in machine-to-machine communication | |
CN110462604A (en) | The data processing system and method for association internet device are used based on equipment | |
CN110781308B (en) | Anti-fraud system for constructing knowledge graph based on big data | |
CN106506705A (en) | Listener clustering method and device based on location-based service | |
CN104866831B (en) | The face recognition algorithms of characteristic weighing | |
Manley et al. | A review of machine learning and big data applications in addressing ecosystem service research gaps | |
CN103391317B (en) | A kind of system technology maturity appraisal procedure and device | |
CN108985467A (en) | Secondary device lean management-control method based on artificial intelligence | |
CN107992865A (en) | A kind of vehicle identification method and system based on video analysis | |
CN107704970A (en) | A kind of Demand-side load forecasting method based on Spark | |
Karras et al. | Pattern recognition and event detection on IoT data-streams | |
Pęciak | Megatrends and their implications in the globalised world | |
Xia et al. | SW-BiLSTM: a Spark-based weighted BiLSTM model for traffic flow forecasting | |
Rabbi et al. | An Approximation For Monitoring The Efficiency Of Cooperative Across Diverse Network Aspects | |
Li et al. | Graph-powered learning methods in the Internet of Things: A survey | |
Wang et al. | Knowledge fusion enhanced graph neural network for traffic flow prediction | |
Yang | Financial big data management and control and artificial intelligence analysis method based on data mining technology | |
CN106355537A (en) | Smart analysis method and system for interrelated cases | |
CN107995278A (en) | A kind of scene intelligent analysis system and method based on metropolitan area level Internet of Things perception data | |
CN107845042A (en) | Supervisory systems is imposed in house in a kind of state-owned land | |
CN109472115B (en) | Large-scale complex network modeling method and device based on geographic information | |
Ishaq et al. | Information technology governance using cobit 4.0 domain delivery support and monitoring evaluation | |
Pareek et al. | A review report on knowledge discovery in databases and various techniques of data mining |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180313 |