CN108710649A - A kind of medicine AFR control makes up method - Google Patents
A kind of medicine AFR control makes up method Download PDFInfo
- Publication number
- CN108710649A CN108710649A CN201810418247.3A CN201810418247A CN108710649A CN 108710649 A CN108710649 A CN 108710649A CN 201810418247 A CN201810418247 A CN 201810418247A CN 108710649 A CN108710649 A CN 108710649A
- Authority
- CN
- China
- Prior art keywords
- value
- data
- vacancy
- medicine
- vacancy value
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of medicine AFR controls to make up method, and this approach includes the following steps：Step 1 finds out which aggregation record includes vacancy value；Step 2 concentrates each aggregation comprising vacancy value to record focus data, according to the given data tuple that initial data is concentrated, calculates the quantity of data vacancy value；Step 3, the concrete condition according to medical data set the minimum and peak of vacancy value；Step 4, the quantity of data vacancy value calculated according to step 2 and the setting value of step 3 are compared, and determine that medicine AFR control makes up the specific method of use.The present invention medicine AFR control make up method, for vacancy value quantity number, handled accordingly, the gap between data mining algorithm and practical application can be effectively reduced, medical data system completion degree that treated is higher, be suitble to popularization and application.
Description
Technical field
The invention belongs to medicine technology field, it is related to a kind of medicine AFR control and makes up method.
Background technology
It is well known that due to the limitation of network bandwidth, at present domestic Medical Web sites mostly based on text information, and this
Kind of present situation can no longer meet 21 century medical field teaching and scientific research, resource-sharing, remote communication etc. needs.In recent years
Come, the universal and development of internet has greatly pushed global IT application and the process of networking, abundant doctor on internet
Learning information resources just slowly becomes the huge treasure-house of medical information.Under both demands, and medical data base is also just met the tendency of and
It is raw.In a computer, database is the data acquisition system organized and stored according to certain data model in second-level storage.
And when database applies in hospital system, the redundancy and not easy-to-search of traditional medicine document storage mode can either be changed
Problem, and can safeguard the uniformity and authority of medical files.During for medical data mining links, data
Incomplete phenomenon is inevitable, the AFR control of various degrees, also referred to as vacancy value.In order to be cured in biology
The method and system for effectively applying data mining in research field is learned, the incomplete challenge of data must be just faced.
Invention content
The purpose of the present invention is to provide a kind of medicine AFR controls to make up method.
Its specific technical solution is：
A kind of medicine AFR control makes up method, includes the following steps：
Step 1 finds out which aggregation record includes vacancy value；
Step 2 concentrates each aggregation comprising vacancy value to record focus data, is concentrated according to initial data
Primary data tuple calculates the quantity of data vacancy value；
Step 3, the concrete condition according to medical data set the minimum and peak of vacancy value；
Step 4, the quantity of data vacancy value calculated according to step 2 and the setting value of step 3 are compared, and determine medicine
AFR control makes up the specific method of use；
If the quantity of vacancy value is less than minimum setting value, just directly there will be the record deletion of missing information attribute value,
To obtain a complete information table；
If the quantity of vacancy value is more than minimum setting value but is less than most setting values, according to remaining object in decision table
The distribution situation of value is filled a null value；
If the quantity of vacancy value is more than highest set value, do not handle, directly in the enterprising line number of the data comprising null value
According to excavation.
Further, in step 4, the method being filled to a null value includes：It is filled in manually, particular value is filled, average
Value filling, calorie filling, minimum distance neighbour method, using the filling of all possible value, combine completeization method, recurrence, multiple fill out
It mends, desired value maximization approach.
Further, in step 4, the method that data mining use is carried out directly in the data comprising null value, including pattra leaves
This network and artificial neural network.
Compared with prior art, beneficial effects of the present invention are：
The present invention medicine AFR control make up method, for vacancy value quantity number, handled, can be had accordingly
Effect reduces the gap between data mining algorithm and practical application, and treated, and medical data system completion degree is higher, fits
It closes and promotes and applies.
Specific implementation mode
Technical scheme of the present invention is described in more detail with reference to embodiment.
A kind of medicine AFR control makes up method, includes the following steps：
Step 1 finds out which aggregation record includes vacancy value；
Step 2 concentrates each aggregation comprising vacancy value to record focus data, is concentrated according to initial data
Primary data tuple calculates the quantity of data vacancy value；
Step 3, the concrete condition according to medical data set the minimum and peak of vacancy value；
Step 4, the quantity of data vacancy value calculated according to step 2 and the setting value of step 3 are compared, and determine medicine
AFR control makes up the specific method of use；
If the quantity of vacancy value is less than minimum setting value, just directly there will be the record deletion of missing information attribute value,
To obtain a complete information table；
If the quantity of vacancy value is more than minimum setting value but is less than most setting values, according to remaining object in decision table
The distribution situation of value is filled a null value；
If the quantity of vacancy value is more than highest set value, do not handle, directly in the enterprising line number of the data comprising null value
According to excavation.
In step 4, the method being filled to a null value includes：Be filled in manually, particular value filling, average value filling,
Calorie filling, uses the filling of all possible value, combination completeization method, recurrence, multiple imputation, expectation at minimum distance neighbour method
It is worth maximization approach.
In step 4, directly in the data comprising null value carry out data mining use method, including Bayesian network and
Artificial neural network.
The foregoing is only a preferred embodiment of the present invention, protection scope of the present invention is without being limited thereto, it is any ripe
Those skilled in the art are known in the technical scope of present disclosure, the letter for the technical solution that can be become apparent to
Altered or equivalence replacement are each fallen in protection scope of the present invention.
Claims (3)
1. a kind of medicine AFR control makes up method, which is characterized in that include the following steps：
Step 1 finds out which aggregation record includes vacancy value；
Step 2 concentrates each aggregation comprising vacancy value to record focus data, the datum concentrated according to initial data
According to tuple, the quantity of data vacancy value is calculated；
Step 3, the concrete condition according to medical data set the minimum and peak of vacancy value；
Step 4, the quantity of data vacancy value calculated according to step 2 and the setting value of step 3 are compared, and determine medicine vacancy
Data make up the specific method of use；
If the quantity of vacancy value is less than minimum setting value, just directly there will be the record deletions of missing information attribute value, thus
Obtain a complete information table；
If the quantity of vacancy value is more than minimum setting value but is less than most setting values, according to remaining object value in decision table
Distribution situation one null value is filled；
If the quantity of vacancy value is more than highest set value, do not handle, data digging is carried out directly in the data comprising null value
Pick.
2. medicine AFR control according to claim 1 makes up method, which is characterized in that in step 4, to a null value into
Row filling method include：Be filled in manually, particular value filling, average value filling, calorie filling, minimum distance neighbour method, using institute
Possible value filling, combination completeization method, recurrence, multiple imputation, desired value maximization approach.
3. medicine AFR control according to claim 1 makes up method, which is characterized in that in step 4, directly including sky
The method that data mining use is carried out in the data of value, including Bayesian network and artificial neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810418247.3A CN108710649A (en) | 2018-04-29 | 2018-04-29 | A kind of medicine AFR control makes up method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810418247.3A CN108710649A (en) | 2018-04-29 | 2018-04-29 | A kind of medicine AFR control makes up method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108710649A true CN108710649A (en) | 2018-10-26 |
Family
ID=63867815
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810418247.3A Pending CN108710649A (en) | 2018-04-29 | 2018-04-29 | A kind of medicine AFR control makes up method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108710649A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177088A (en) * | 2013-03-08 | 2013-06-26 | 北京理工大学 | Biomedicine missing data compensation method |
| CN105184307A (en) * | 2015-07-27 | 2015-12-23 | 蚌埠医学院 | Medical field image semantic similarity matrix generation method |
| CN106407464A (en) * | 2016-10-12 | 2017-02-15 | 南京航空航天大学 | KNN-based improved missing data filling algorithm |
| CN106844781A (en) * | 2017-03-10 | 2017-06-13 | 广州视源电子科技股份有限公司 | Data processing method and device |
-
2018
- 2018-04-29 CN CN201810418247.3A patent/CN108710649A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103177088A (en) * | 2013-03-08 | 2013-06-26 | 北京理工大学 | Biomedicine missing data compensation method |
| CN105184307A (en) * | 2015-07-27 | 2015-12-23 | 蚌埠医学院 | Medical field image semantic similarity matrix generation method |
| CN106407464A (en) * | 2016-10-12 | 2017-02-15 | 南京航空航天大学 | KNN-based improved missing data filling algorithm |
| CN106844781A (en) * | 2017-03-10 | 2017-06-13 | 广州视源电子科技股份有限公司 | Data processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 铁汉1990: "缺失值的处理", 《新浪博客》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102088489B (en) | Distributed data synchronizing system and method | |
| DE202015009772U1 (en) | Data management systems | |
| CN113655969B (en) | Data balanced storage method based on streaming distributed storage system | |
| CN110009147B (en) | Meteorological data acquisition strategy self-adaptive adjustment method and device | |
| WO2023159813A1 (en) | Incomplete dimension raising-based method for optimizing data-driven power system, and application thereof | |
| CN102646133B (en) | Two-dimensional table organization method based on metadata storage | |
| CN106712050A (en) | Power grid reactive power optimization method and device based on improved leapfrog algorithm | |
| CN104298761B (en) | The implementation method that master data is matched between a kind of heterogeneous software system | |
| CN117273165A (en) | Network model fine-tuning method, system and equipment suitable for community scene | |
| CN109787247A (en) | A kind of reactive compensation planing method based on multi-parametric programming | |
| CN108710649A (en) | A kind of medicine AFR control makes up method | |
| CN110059405A (en) | High-quality Steiner minimum tree construction method with differential evolution under X structure | |
| CN116204787A (en) | Automatic adjustment method for target weight of multi-target recommendation model | |
| CN113688115B (en) | Archive big data distributed storage system based on Hadoop | |
| CN110275868A (en) | A kind of multi-modal pretreated method of manufaturing data in intelligent plant | |
| CN102103736A (en) | A technology for flexibly setting watermark parameters | |
| CN109948836A (en) | Processing method, device, storage medium and the processor of the water filling data in oil field | |
| CN102103607A (en) | No-refresh picture bulk-uploading and automatic picture information acquisition technique | |
| CN117240604B (en) | Cloud computing-based data safe storage and energy saving optimization method | |
| CN116258944B (en) | Remote sensing image classification model sample increment learning method based on double networks | |
| CN107016198A (en) | A kind of multiple dimensioned quantum wavelet transforms optimization method with inherent parallel ability | |
| CN109407973A (en) | A kind of archives and information management Intelligentized regulating and controlling system | |
| CN107071031B (en) | Distributed block memory system data based on chunk block version number restores determination method | |
| CN116979552B (en) | Compensation method for line loss of transformer area based on fixed number capacitance compensation point position selection | |
| CN115277044B (en) | OpenStack encryption link node layering method and system |
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: 20181026 |
|
| RJ01 | Rejection of invention patent application after publication |