CN110019488A - Multi-source heterogeneous data fusion multi-core classification method - Google Patents
Multi-source heterogeneous data fusion multi-core classification method Download PDFInfo
- Publication number
- CN110019488A CN110019488A CN201811063714.1A CN201811063714A CN110019488A CN 110019488 A CN110019488 A CN 110019488A CN 201811063714 A CN201811063714 A CN 201811063714A CN 110019488 A CN110019488 A CN 110019488A
- Authority
- CN
- China
- Prior art keywords
- data
- information
- carries out
- sample
- classification
- 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
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- 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
-
- 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
- G06F16/26—Visual data mining; Browsing structured data
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Multi-source heterogeneous data fusion multi-core classification method, comprising the following steps: take the distributed new access information of power grid in operation, power grid production management information and geographical weather information as sample；Artificial treatment is carried out as training sample to sample；Distributed new access information, power grid production management information and geographical weather information are calculated, common parameter Pb carries out a variety of Multiple Kernel Learning Experimental Comparisons to common parameter Pb and calculates difference common parameter Pbd, obtains amounting to common parameter daughter nucleus number Pa=Pb*Pbd；Core study is carried out to Pa core with training sample, for constructing stochastic kernel；The random kernel function investment testing site that training is finished carries out integrated classification to multi-source heterogeneous data；Lossless compression encryption storage is carried out to the data having been classified.Fused distributed new related data is provided for each department, company, provinces and cities is improved to the management level and quality of distributed new, provides the customization service of different demands for various circles of society.
Description
Technical field
The present invention relates to power grid internet of things data to integrate fusion method, and in particular to multi-source heterogeneous data fusion multicore classification
Method.
Background technique
The world today, with the development of internet, governance two-way interaction are more and more, under line with merged on line, from
Simple government regulation is administered to more emphasis social synergy.We play effect of the heightened awareness Internet of Things in administration of power networks,
It is shared as approach with data set neutralization, builds the integrated power grid large data center of micro-capacitance sensor, Push Technology fusion, business are melted
It closes, data fusion, realizes cross-layer grade, cross-region, cross-system, trans-departmental, hoof business coordinated management and service.
Under the overall background of distributed new scale access, to realize to the effective of distributed new mass data
Management, the pre- of multi-source heterogeneous data such as research distributed energy access information, power grid production management information, geographical weather information are commented
Estimate, extract, quality control etc. data processing techniques, ensure the consistency and integrality of trans-departmental distributed new data；It builds
Vertical distributed new data fusion computation model proposes distributed data base constructing plan and visual presentation method, exploitation
Distributed new information management database provides data basis for aid decision；Distribution by Henan Electric Power System accumulation is new
Multi-energy data is realized and is mentioned to Provincial Power Grid Corporation's planning and designing, marketing, scheduling, fortune inspection, Fa Cedeng each department related data
It takes, merge and customizes and process, provide data basis for subsequent distribution formula new energy related service expanded application.
High-order by studying distributed new related data couples relevance data mining technology, proposes status monitoring
With operation diagnostic techniques, income analysis and prediction model are established, realizes the intelligence aided decision towards all types of user；Based on data
Excavation and analytical technology realize the excavation to the market individual demand in distributed new direction and enterprise itself benign development
And satisfaction, the core value of distributed new mass data is improved, distributed new is promoted to distribute rationally, guide distribution
Generation of electricity by new energy production and operation and guarantee power network safety operation.
It is proposed status monitoring, operation diagnosis, income analysis and operating maintenance service towards large-scale distributed new energy
Frame；Grasp the customization service content generation technique towards different society object individual demand；It is proposed grid company from it is different
The Informatization Service framework transboundary of demand interaction and model innovation between social object.
Distributed new information management database, information management system, public informationization service platform are developed, and in
The former unique Provincial Power Grid Corporation in economic zone core area-Henan Electric Power Company carries out Demonstration Application, realizes to distributed new
Energy operating status on-line monitoring, operation diagnosis, Profit Assessment, O&M service, support each business department to distributed new
Coordination Decision, further increase distributed new grid connection capacity, digestion capability and operational efficiency.
Chinese publication CN 107247787A, publication date on October 13rd, 2017 disclose a kind of based on multi-source number
According to the classification method of fusion, the classification method is real by data combing, data personalization classification, multisource data fusion three steps of classification
It is existing；Data combing: government data, social data, the internet data producer and data are combed respectively；Data are personalized
Classification: according to the respective attribute of government data, social data, internet data, classify respectively to it according to different dimensions；
Multisource data fusion classification: respectively classifying according to government data, social data, internet data, finds general character classification dimension, presses
License-master's topic, industry carry out integrated classification, establish publicly-owned theme and trade classification system and respectively personalized classification dimension, real
Present government's data, social data, internet data depth integration.The present invention realizes government data, social data, interconnection netting index
According to depth integration, to realize that integrated large data center construction provides basic guarantee；This method practicability is stronger, the scope of application
Extensively.
But its shortcoming is only to have been carried out dividing latitude and classification to data, is not involved with specific fusion
Mode.
Summary of the invention
The present invention be for all kinds of historical datas such as on-line monitoring system and real time data fusion on the basis of, using big data
Technology carries out fault diagnosis, and for repair based on condition of component provides decision, it can be achieved that dynamic evaluation and base to grid equipment key performance
In the fault diagnosis of complicated correlativity identification, it is different that multi-source designed by technical support is provided for solution standing state maintenance problem
Structure data fusion multi-core classification method.
Multi-source heterogeneous data fusion multi-core classification method, comprising the following steps:
M1 takes the distributed new access information of power grid in operation, power grid production management information and geographical weather information conduct
Sample；
M2 carries out artificial treatment as training sample to the sample in step M1；
M3 calculates distributed new access information, power grid production management information and geographical weather information, common parameter Pb
M4 carries out a variety of Multiple Kernel Learning Experimental Comparisons to common parameter Pb and calculates difference common parameter Pbd, obtains amounting to public ginseng
Number daughter nucleus number Pa=Pb*Pbd；
M5 carries out core study to Pa core with the training sample in step M2, for constructing stochastic kernel；
M6, the random kernel function investment testing site that training is finished carry out integrated classification to multi-source heterogeneous data；
M7 carries out lossless compression encryption storage to the data having been classified.
It is realized and is divided by technologies such as data assessment, data recombination, data cleansing, data pick-up, data filtering, data regularizations
The pretreatment of the relevant multi-source heterogeneous data of cloth new energy, and realize that the quality of data controls using matrix Renew theory frame.
Distributed data base is constructed based on measurements association, XML technology and relational database technology.It is real based on mixing method for visualizing
The data visualization of the existing relevant multi-source heterogeneous data fusion of distributed new.
Preferably, the step M2 includes:
A1, data classification are energy information, management data and geographical weather information
A2 carries out secondary classification to energy information, management data and the geographical weather information in step A1；
A3 carries out information overlap classification to complete secondary classification geography weather information and energy information in step A2；
A4, with the management data and energy information progress information overlap classification in step A2；
A5 is added to step A3 with the findings data of data in the corresponding step A2 in step A4 the knot of data in step A2
Tail forms new sample data
A6 carries out high latitude mapping calculation, completes sample to energy information, management data and the geographical weather information in step A5
Present treatment.
Distributed new related data representation, in terms of there are many differences, can not be direct
Combined Treatment is carried out, needs to study how each data to be mapped to same same sex member space.Kernel method is to solve nonlinear model
Formula indicates a kind of effective ways of problem, and the main purpose of kernel function is the correlation between valid metric sample data, so that reflecting
The Near-neighbor Structure of sample can still be maintained in higher dimensional space for feature after penetrating.
And the specific classification of step M2 and secondary classification are exactly to carry out core classification to a variety of data.
Preferably, the step M5 includes:
B1, setting random output extract ratio Per
B2 randomly selects the data in step M2 with the extraction ratio in step B1；
B3 is trained all Pa daughter nucleus with the sample extracted in step B2；
B4, remaining data carry out verification data training in step B3 are finished daughter nucleus and tested after having been extracted with step B2；
B5 repeats 70 step B1 to B4；
B6 changes extraction ratio per and executes step B5；
B7 repeats B6 and executes 3 times；
B8 carries out 10 cross validation calculated equilibrium factor C.
Self study, which forms more abstract high level by combination low-level feature, indicates attribute classification or feature, to find data
Distributed nature indicate.This project implicitly carries out feature extraction using depth convolutional network from data.By successively special
Sample is transformed to a new feature space in the character representation of former data space, realized to data semantic feature by sign transformation
It automatically extracts.Reach the self study purpose of data preparation optimization by the repetition training of great amount of samples.
Preferably, the step A2 carries out carrying out source non-overlap FIELD Data when classifying to energy information
Sky filling.
Preferably, further include:
M8 is periodically sampled storage data；
M9, sampling with replacement data are initial data, and are thus used as test sample；
M10 carries out artificial treatment with the data sample in step M8, as check and correction test sample；
M11 proofreads daughter nucleus with the data in step M9 and step M10, tests if there is test sample or check and correction
Sample classification mistake then carries out step M12, otherwise completes periodically sampling school team；
M12, re -training daughter nucleus are simultaneously used newly classification data by energy information, management data and geographical weather information major class
Training daughter nucleus is classified, and contrast difference simultaneously carries out manual review.
Substantial effect of the invention is with multi-source heterogeneous data fusion multi-core classification method energy shown in the present invention
It is enough that distributed new information management database, Information Management System and information service distribution platform are established with this；For each portion
Door provides unified, distributed new related data, improves company, provinces and cities to distributed new
Management level and management quality, provide the information-based customization service of different demands for various circles of society.
Specific embodiment
Below by specific embodiment, technical scheme of the present invention will be further explained in detail.
Embodiment 1
The multi-source heterogeneous data fusion multi-core classification method, comprising the following steps:
M1 takes the distributed new access information of power grid in operation, power grid production management information and geographical weather information conduct
Sample；
M2 carries out artificial treatment as training sample to the sample in step M1；
M3 calculates distributed new access information, power grid production management information and geographical weather information, common parameter Pb
M4 carries out a variety of Multiple Kernel Learning Experimental Comparisons to common parameter Pb and calculates difference common parameter Pbd, obtains amounting to public ginseng
Number daughter nucleus number Pa=Pb*Pbd；
M5 carries out core study to Pa core with the training sample in step M2, for constructing stochastic kernel；
M6, the random kernel function investment testing site that training is finished carry out integrated classification to multi-source heterogeneous data；
M7 carries out lossless compression encryption storage to the data having been classified.
It is realized and is divided by technologies such as data assessment, data recombination, data cleansing, data pick-up, data filtering, data regularizations
The pretreatment of the relevant multi-source heterogeneous data of cloth new energy, and realize that the quality of data controls using matrix Renew theory frame.
Distributed data base is constructed based on measurements association, XML technology and relational database technology.It is real based on mixing method for visualizing
The data visualization of the existing relevant multi-source heterogeneous data fusion of distributed new.
The step M2 includes:
A1, data classification are energy information, management data and geographical weather information
A2 carries out secondary classification to energy information, management data and the geographical weather information in step A1；
A3 carries out information overlap classification to complete secondary classification geography weather information and energy information in step A2；
A4, with the management data and energy information progress information overlap classification in step A2；
A5 is added to step A3 with the findings data of data in the corresponding step A2 in step A4 the knot of data in step A2
Tail forms new sample data
A6 carries out high latitude mapping calculation, completes sample to energy information, management data and the geographical weather information in step A5
Present treatment.
Distributed new related data representation, in terms of there are many differences, can not be direct
Combined Treatment is carried out, needs to study how each data to be mapped to same same sex member space.Kernel method is to solve nonlinear model
Formula indicates a kind of effective ways of problem, and the main purpose of kernel function is the correlation between valid metric sample data, so that reflecting
The Near-neighbor Structure of sample can still be maintained in higher dimensional space for feature after penetrating.
And the specific classification of step M2 and secondary classification are exactly to carry out core classification to a variety of data.
The step M5 includes:
B1, setting random output extract ratio Per
B2 randomly selects the data in step M2 with the extraction ratio in step B1；
B3 is trained all Pa daughter nucleus with the sample extracted in step B2；
B4, remaining data carry out verification data training in step B3 are finished daughter nucleus and tested after having been extracted with step B2；
B5 repeats 70 step B1 to B4；
B6 changes extraction ratio per and executes step B5；
B7 repeats B6 and executes 3 times；
B8 carries out 10 cross validation calculated equilibrium factor C.
Self study, which forms more abstract high level by combination low-level feature, indicates attribute classification or feature, to find data
Distributed nature indicate.This project implicitly carries out feature extraction using depth convolutional network from data.By successively special
Sample is transformed to a new feature space in the character representation of former data space, realized to data semantic feature by sign transformation
It automatically extracts.Reach the self study purpose of data preparation optimization by the repetition training of great amount of samples.
The step A2 carries out carrying out source non-overlap FIELD Data empty filling when classifying to energy information.
Further include:
M8 is periodically sampled storage data；
M9, sampling with replacement data are initial data, and are thus used as test sample；
M10 carries out artificial treatment with the data sample in step M8, as check and correction test sample；
M11 proofreads daughter nucleus with the data in step M9 and step M10, tests if there is test sample or check and correction
Sample classification mistake then carries out step M12, otherwise completes periodically sampling school team；
M12, re -training daughter nucleus are simultaneously used newly classification data by energy information, management data and geographical weather information major class
Training daughter nucleus is classified, and contrast difference simultaneously carries out manual review.
Claims (5)
1. multi-source heterogeneous data fusion multi-core classification method, which comprises the following steps:
M1 takes the distributed new access information of power grid in operation, power grid production management information and geographical weather information conduct
Sample；
M2 carries out artificial treatment as training sample to the sample in step M1；
M3 calculates distributed new access information, power grid production management information and geographical weather information, common parameter Pb
M4 carries out a variety of Multiple Kernel Learning Experimental Comparisons to common parameter Pb and calculates difference common parameter Pbd, obtains amounting to public ginseng
Number daughter nucleus number Pa=Pb*Pbd；
M5 carries out core study to Pa core with the training sample in step M2, for constructing stochastic kernel；
M6, the random kernel function investment testing site that training is finished carry out integrated classification to multi-source heterogeneous data；
M7 carries out lossless compression encryption storage to the data having been classified.
2. multi-source heterogeneous data fusion multi-core classification method according to claim 1, which is characterized in that the step M2
Include:
A1, data classification are energy information, management data and geographical weather information
A2 carries out secondary classification to energy information, management data and the geographical weather information in step A1；
A3 carries out information overlap classification to complete secondary classification geography weather information and energy information in step A2；
A4, with the management data and energy information progress information overlap classification in step A2；
A5 is added to step A3 with the findings data of data in the corresponding step A2 in step A4 the knot of data in step A2
Tail forms new sample data
A6 carries out high latitude mapping calculation, completes sample to energy information, management data and the geographical weather information in step A5
Present treatment.
3. multi-source heterogeneous data fusion multi-core classification method according to claim 1, which is characterized in that the step M5
Include:
B1, setting random output extract ratio Per
B2 randomly selects the data in step M2 with the extraction ratio in step B1；
B3 is trained all Pa daughter nucleus with the sample extracted in step B2；
B4, remaining data carry out verification data training in step B3 are finished daughter nucleus and tested after having been extracted with step B2；
B5 repeats 70 step B1 to B4；
B6 changes extraction ratio per and executes step B5；
B7 repeats B6 and executes 3 times；
B8 carries out 10 cross validation calculated equilibrium factor C.
4. multi-source heterogeneous data fusion multi-core classification method according to claim 2, which is characterized in that the step A2
It carries out carrying out source non-overlap FIELD Data empty filling when classifying to energy information.
5. multi-source heterogeneous data fusion multi-core classification method according to claim 1, which is characterized in that further include:
M8 is periodically sampled storage data；
M9, sampling with replacement data are initial data, and are thus used as test sample；
M10 carries out artificial treatment with the data sample in step M8, as check and correction test sample；
M11 proofreads daughter nucleus with the data in step M9 and step M10, tests if there is test sample or check and correction
Sample classification mistake then carries out step M12, otherwise completes periodically sampling school team；
M12, re -training daughter nucleus are simultaneously used newly classification data by energy information, management data and geographical weather information major class
Training daughter nucleus is classified, and contrast difference simultaneously carries out manual review.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811063714.1A CN110019488A (en) | 2018-09-12 | 2018-09-12 | Multi-source heterogeneous data fusion multi-core classification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811063714.1A CN110019488A (en) | 2018-09-12 | 2018-09-12 | Multi-source heterogeneous data fusion multi-core classification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110019488A true CN110019488A (en) | 2019-07-16 |
Family
ID=67188467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811063714.1A Pending CN110019488A (en) | 2018-09-12 | 2018-09-12 | Multi-source heterogeneous data fusion multi-core classification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110019488A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021103401A1 (en) * | 2019-11-25 | 2021-06-03 | 深圳壹账通智能科技有限公司 | Data object classification method and apparatus, computer device and storage medium |
| CN117034125A (en) * | 2023-10-08 | 2023-11-10 | 江苏臻云技术有限公司 | Classification management system and method for big data fusion |
| CN117493777A (en) * | 2023-12-29 | 2024-02-02 | 成都秦川物联网科技股份有限公司 | Ultrasonic flowmeter data cleaning method, system and device based on Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080215298A1 (en) * | 2006-10-10 | 2008-09-04 | Haney Philip J | Parameterization of non-linear/non-gaussian data distributions for efficient information sharing in distributed sensor networks |
| CN105184424A (en) * | 2015-10-19 | 2015-12-23 | 国网山东省电力公司菏泽供电公司 | Mapreduced short period load prediction method of multinucleated function learning SVM realizing multi-source heterogeneous data fusion |
| CN105975977A (en) * | 2016-05-05 | 2016-09-28 | 中国石油大学(华东) | Rule-aided data-driven modeling method |
| CN106777141A (en) * | 2016-12-19 | 2017-05-31 | 国网山东省电力公司电力科学研究院 | A kind of acquisition for merging multi-source heterogeneous electric network data and distributed storage method |
| CN107491828A (en) * | 2016-06-13 | 2017-12-19 | 上海交通大学 | A kind of distributed new based on the optimal multi-kernel function of multi-source time-variable data goes out force prediction method |
-
2018
- 2018-09-12 CN CN201811063714.1A patent/CN110019488A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080215298A1 (en) * | 2006-10-10 | 2008-09-04 | Haney Philip J | Parameterization of non-linear/non-gaussian data distributions for efficient information sharing in distributed sensor networks |
| CN105184424A (en) * | 2015-10-19 | 2015-12-23 | 国网山东省电力公司菏泽供电公司 | Mapreduced short period load prediction method of multinucleated function learning SVM realizing multi-source heterogeneous data fusion |
| CN105975977A (en) * | 2016-05-05 | 2016-09-28 | 中国石油大学(华东) | Rule-aided data-driven modeling method |
| CN107491828A (en) * | 2016-06-13 | 2017-12-19 | 上海交通大学 | A kind of distributed new based on the optimal multi-kernel function of multi-source time-variable data goes out force prediction method |
| CN106777141A (en) * | 2016-12-19 | 2017-05-31 | 国网山东省电力公司电力科学研究院 | A kind of acquisition for merging multi-source heterogeneous electric network data and distributed storage method |
Non-Patent Citations (1)
| Title |
|---|
| 邵喜高: "基于统计学习理论的多核预测模型研究及应用", 《中国博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 |
|---|---|---|---|---|
| WO2021103401A1 (en) * | 2019-11-25 | 2021-06-03 | 深圳壹账通智能科技有限公司 | Data object classification method and apparatus, computer device and storage medium |
| CN117034125A (en) * | 2023-10-08 | 2023-11-10 | 江苏臻云技术有限公司 | Classification management system and method for big data fusion |
| CN117034125B (en) * | 2023-10-08 | 2024-01-16 | 江苏臻云技术有限公司 | Classification management system and method for big data fusion |
| CN117493777A (en) * | 2023-12-29 | 2024-02-02 | 成都秦川物联网科技股份有限公司 | Ultrasonic flowmeter data cleaning method, system and device based on Internet of things |
| CN117493777B (en) * | 2023-12-29 | 2024-03-15 | 成都秦川物联网科技股份有限公司 | Ultrasonic flowmeter data cleaning method, system and device based on Internet of things |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107977737B (en) | Distribution transformation load prediction method based on mxnet frame deep neural network | |
| Marsal-Llacuna et al. | Lessons in urban monitoring taken from sustainable and livable cities to better address the Smart Cities initiative | |
| CN107784397B (en) | Power grid material demand prediction system and prediction method thereof | |
| CN110019488A (en) | Multi-source heterogeneous data fusion multi-core classification method | |
| CN110400207A (en) | A kind of financial On-line monitor system and method based on big data | |
| Pilo et al. | ATLANTIDE-Digital archive of the Italian electric distribution reference networks | |
| Samadi Alinia et al. | Tehran’s seismic vulnerability classification using granular computing approach | |
| CN109471884A (en) | The relevant multi-source heterogeneous data processing method of distributed new | |
| Ma et al. | Systematic analysis of the blockchain in the energy sector: Trends, issues, and future directions | |
| Lal et al. | A structural modelling for e-governance service delivery in rural India | |
| Berrou et al. | Smart city development strategy profile: Use case modeling based on simplicial complexes | |
| Nikoloudis et al. | An Evaluation Model for Smart City Performance with Less Than 50, 000 Inhabitants: A Greek Case Study. | |
| CN104318739B (en) | Electric power safety, quality In-site supervision main website-wireless data terminal management system | |
| Edtmayer et al. | High-resolution, spatial thermal energy demand analysis and workflow for a city district | |
| Du et al. | A systematic approach for analyzing building energy conservation and emission reduction policies based on the principle of WSR | |
| Li et al. | Construction Technology Safety Management under the Background of BIM and Information System Modeling | |
| Faezi et al. | The Impact of Rural Housing Rehabilitation on Rural Landscape (Case Study: Ahmadabad Village of Bahabad County) | |
| Casas et al. | Standardization of quality control plans for highway bridges in Europe: COST Action TU 1406 | |
| de Almeida Levino et al. | A group decision model for diagnosing barriers to achieving goals in a Brazilian Water Resources Program: an analysis of the state of Alagoas | |
| Luo et al. | Evaluation on e-government websites based on rough set and genetic neural network algorithm | |
| Cheng | The role of virtual reality technology in urban planning and Its Enlightenment to Macau | |
| Sun et al. | Research on the Dynamic Evolution of Social Risks in Community Renewal Projects: Considering the Coupling Effects of Factors | |
| Gerasimov et al. | Modelling Investment Programs with Machine Learning and Data Mining: Descriptive and Predictive Models of Healthcare State Programs in Russia | |
| Supamid et al. | Integration of techniques with data mining for community project data analysis from project specific characteristics | |
| Alpagut et al. | A database for positive energy districts (PED) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190716 |
|
| RJ01 | Rejection of invention patent application after publication |