CN111831693B - Optical remote sensing load index acquisition method based on numerical correlation analysis - Google Patents
Optical remote sensing load index acquisition method based on numerical correlation analysis Download PDFInfo
- Publication number
- CN111831693B CN111831693B CN202010505977.4A CN202010505977A CN111831693B CN 111831693 B CN111831693 B CN 111831693B CN 202010505977 A CN202010505977 A CN 202010505977A CN 111831693 B CN111831693 B CN 111831693B
- Authority
- CN
- China
- Prior art keywords
- remote sensing
- numerical
- sensing load
- index
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000003287 optical effect Effects 0.000 title claims abstract description 32
- 238000010219 correlation analysis Methods 0.000 title claims abstract description 19
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 238000012098 association analyses Methods 0.000 claims abstract description 14
- 238000005065 mining Methods 0.000 claims abstract description 5
- 238000012216 screening Methods 0.000 claims description 4
- 238000001228 spectrum Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000011524 similarity measure Methods 0.000 claims description 3
- 238000007418 data mining Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000012097 association analysis method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Fuzzy Systems (AREA)
- Software Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to a method for acquiring an optical remote sensing load index based on numerical correlation analysis, which comprises the following steps: step 1, constructing a remote sensing load transaction database based on the application direction and the technical index of the remote sensing load; step 2, carrying out numerical association analysis on the remote sensing load transaction database, mining association rules of the application direction and the technical indexes of the remote sensing load, and extracting strong association rules; and 3, selecting a rule from the application direction to the technical index, combining the strong association rule according to the input application direction information, taking the technical index with the confidence coefficient of at least 0.5 corresponding to the strong association rule as a recommendation result, and further acquiring an optical remote sensing load index facing remote sensing application. According to the method, when the application direction and the technical index strong association rule are mined, the technical index value self information is fully utilized through the numerical support degree and the confidence degree calculation, so that the information loss of data layering of the traditional algorithm can be avoided, and the accuracy of acquiring the index is improved.
Description
Technical Field
The invention belongs to the field of space optical technology and data mining, and particularly relates to an optical remote sensing load index acquisition method based on numerical correlation analysis.
Background
The traditional association analysis algorithm is mature only for Boolean data processing and cannot process numerical data. Numerical data is currently typically mapped into boolean data using various manual or automatic hierarchical algorithms, which are then calculated using conventional algorithms. However, the method of hierarchical mapping of numerical data, the different numerical data divided into the same layer will lose the information contained in the data itself, and reduce the accuracy of the association analysis.
For decades, the optical remote sensing technology is continuously and rapidly developed, and abundant remote sensing load technical indexes and application direction data are accumulated. And carrying out association analysis data mining on the technical indexes and the application data, and exploring the internal connection between the remote sensing load technical indexes and the application direction. However, the technical index corresponding to the optical remote sensing load obviously belongs to numerical data, and the traditional association analysis method is not applicable.
Disclosure of Invention
The invention solves the technical problems that: in order to overcome the defects of the prior art, an optical remote sensing load index obtaining method based on numerical correlation analysis is provided, the defects of the existing Boolean data correlation analysis method are overcome, an Apriori algorithm is improved, numerical calculation correlation rules of remote sensing load technical index data are directly utilized, strong correlation rules from application directions to technical indexes are established, the technical indexes corresponding to the strong correlation rules are used as recommendation results, and further the technical indexes facing remote sensing application are obtained.
The solution of the invention is as follows:
an optical remote sensing load index obtaining method based on numerical correlation analysis comprises the following steps:
step 1, constructing a remote sensing load transaction database based on the application direction and the technical index of the remote sensing load;
step 2, carrying out numerical association analysis on the remote sensing load transaction database, improving an Apriori algorithm, mining association rules of the application direction and the technical index of the remote sensing load, and extracting strong association rules;
and 3, selecting a rule from the application direction to the technical index, combining the strong association rule according to the input application direction information, taking the technical index with the confidence coefficient of at least 0.5 corresponding to the strong association rule as a recommendation result, and further acquiring an optical remote sensing load index facing remote sensing application.
Further, in step 1, the type covered by the technical index in the remote sensing load transaction database is consistent with the type of the technical index which is finally obtained and recommended, and the technical index type data is used as numerical data to keep the original specific numerical value of the numerical data and is not converted into Boolean type data.
Further, the technical index comprises at least one numerical data of ground resolution, spectrum resolution, radiation resolution and time resolution, and the application direction comprises three aspects of land, atmosphere and ocean.
Further, in step 1, a transaction t in the database is formed by using a technical index or application direction data corresponding to the remote sensing load k (k=1, 2..n), wherein the item included is a bj (bj=1, 2,.,. M.) all transactions corresponding to each telemetry load constitute a telemetry load transaction database D.
Further, a certain transaction t in the remote sensing load transaction database D k If a certain technical index of (k=1, 2..n) is missing, the data corresponding to the technical index is recorded as null, and if the application direction corresponds to a plurality of sets of data, the data are recorded as a plurality of items in parallel.
Further, in step 2, the method for extracting the strong association rule is as follows:
step 2.1: normalizing the data;
step 2.2: traversing the database, and calculating the numerical support degree of J-order items, wherein J is more than or equal to 1, so as to obtain a J-order candidate item set;
step 2.3: cutting a J-order candidate item set smaller than the minimum support degree to obtain a J-order frequent item set;
step 2.4: when the J-order frequent item set is not empty, the steps 2.2 and 2.3 are circulated, otherwise, the obtained frequent item sets of each order are cut by using the numerical confidence coefficient, and items smaller than the minimum confidence coefficient are cut, so that a transform domain association rule is obtained;
step 2.5: and (3) recovering the rule, and inversely converting the specific numerical values of the items in the rule from the value range of 0-1 to the original value range according to different attributes according to the conversion method specified in the step (2.1) to obtain a strong association rule result.
Further, in step 2.2, when j=1, the first-order candidate set detection is performed, the normalized data in the database is traversed, and the item support degree is calculated, where the calculation method is as follows:
wherein A is i For transaction t i Parameter value corresponding to technical index A in the middle, A k For transaction t k Parameter values corresponding to technical index a in (k=1, 2..n), abs (a i -A k ) Representing the absolute value of the specific numerical gap of two transactions,is a measure of similarity of two things,
the final numerical support degree; n is the total number of transactions in the database;
in order to transform the similarity.
Further, in step 2.2, when J >1, traversing the J-1 order frequent set, and calculating the multi-order support degree, the method is as follows:
1≤b 1 <b 2 <...<b j ≤M
wherein,for transaction t i Item->And t k Similarity measure of corresponding items in +.>The numerical support degree is the J-order item; />For transaction t i B of (b) j Technical index->Corresponding parameter values,/->For transaction t k (k=1, 2. N) b j Technical index->Corresponding parameter values,/->Representing the absolute value of the difference between specific values of two transactions, M being the thing t i Number of technical index items in b j A random number from 1 to M;in order to transform the similarity.
Further, J-order frequent set screening is carried out, a minimum support threshold is manually specified, J-order items smaller than the minimum support threshold are cut according to respective support ranks, and J-order frequent sets are obtained.
Further, in step 2.4, the numerical confidence levelThe calculation method comprises the following steps:
wherein, support A For the numerical Support degree corresponding to the item A, support (A∪B) The numerical support of the simultaneous occurrence of the items A and B.
Compared with the prior art, the invention has the beneficial effects that:
(1) According to the method, an optical remote sensing load index obtaining method based on numerical association analysis is adopted, when an application direction and technical index strong association rule is mined, the technical index numerical value self information is fully utilized through numerical support and confidence calculation, the information loss of data layering of a traditional algorithm can be avoided, and the association analysis result, namely the accuracy of the obtained index is improved;
(2) According to the optical remote sensing load index acquisition method based on numerical correlation analysis, when the numerical support and the confidence coefficient are calculated, all data can participate in calculation, wherein the data with large difference has small contribution, the data with small difference has large contribution, and results which are more similar to the true support and the confidence coefficient can be given;
(3) According to the optical remote sensing load index acquisition method based on numerical correlation analysis, the Boolean data can be compatible when the numerical support degree and the confidence degree are calculated, and the data mining of a mixed database of the numerical data and the Boolean data can be supported;
(4) The invention does not relate to optical calculation, but only relates to the mining of the technical indexes in the optical remote sensing load transaction database and the strong association rules in the application directions, and can acquire any technical index recommendation result contained in the transaction database aiming at different application directions;
(5) The optical remote sensing load index obtaining method based on the numerical value type association analysis has the characteristics of automation, quantification and application oriented, and can automatically obtain high-confidence recommended design indexes aiming at specific remote sensing application directions on the basis of carrying out the numerical value type association analysis on the optical remote sensing load historical data, thereby realizing the automatic auxiliary design of the optical remote sensing load oriented to the remote sensing application.
Drawings
FIG. 1 is a flow chart of a method of extracting strong association rules in accordance with the present invention;
fig. 2 is a flow chart of the method of the present invention.
Detailed Description
The invention is further illustrated below with reference to examples.
An optical remote sensing load index obtaining method based on numerical correlation analysis is shown in fig. 2, and step 1: remote sensing load transaction database construction
Step 1.1, remote sensing load transaction database data definition, wherein the remote sensing load transaction database data comprise two types of remote sensing load application directions and technical indexes, the index types covered by the technical index type data are consistent with the index types finally obtained and recommended, and the index types are used as numerical data to keep the original specific numerical value of the numerical data and are not converted into Boolean data.
In the embodiment, the technical indexes comprise numerical data such as ground resolution, spectrum resolution, radiation resolution, time resolution and the like and application directions, wherein the application directions cover subdivision applications of three aspects of land, atmosphere and ocean.
Step 1.2, defining a remote sensing load transaction database form, and forming a transaction t in the database by using a technical index corresponding to the remote sensing load and application direction data k (k=1, 2..n), one technical indicator or application direction is transaction t k One item a in (k=1, 2..n) bj (bj=1, 2,.,. M.) all transactions corresponding to each telemetry load constitute a telemetry load transaction database D.
A certain transaction t in the transaction database k If the data of a certain technical index is missing, the corresponding data of the technical index is recorded as null, and if the corresponding data of a certain application direction corresponds to a plurality of groups of data, the corresponding data of the technical index is recorded as a plurality of items in parallel.
Step 2: the remote sensing load application direction and technical index association rule mining based on numerical association analysis improves an Apriori algorithm to obtain a strong association rule, and the steps are shown in figure 1.
And 2.1, normalizing the data, and linearly converting the numerical technical index data with different value ranges and dimensions into the value range of 0-1 by adopting a min-max normalization method according to the minimum value and the maximum value of the numerical technical index data.
Step 2.2, detecting a first-order candidate set, traversing normalized data in a database, and calculating item support; firstly, calculating the support degree of a first-order item;
the traditional support is the number delta of occurrences of transaction x in the transaction database x Ratio to the total number of transactions N of the transaction database:
however, for numerical data, the probability of the same attribute and the same numerical value just repeatedly appearing is very low, by adopting the support degree calculation, the support degree of all the items is very low, the really valuable frequent items are difficult to find out, but are easily influenced by noise (if the numerical value of the item corresponding to a certain attribute is close to the numerical value and appears frequently but does not repeat, the numerical value item near another numerical value is very rarely but has a small number of repeated phenomena, the later support degree is rather large), and the information quantity contained in the numerical value is reduced by projecting the numerical value to a small number of Boolean types through a manual setting or clustering method.
The numerical support degree calculation method is provided as follows:
wherein A is i For transaction t i Parameter value corresponding to technical index A in the middle, A k For transaction t k Parameter values corresponding to technical index a in (k=1, 2..n). A is that i -A k Representing a specific numerical gap between two transactionsObtaining the similarity measurement guaranteed to be positive after absolute value solving and difference with 1This parameter describes the degree of similarity or the magnitude of the difference between the two items, with 0 being the largest and 1 being the smallest.
After the transformation of the function f, summing in all things, dividing by the total transaction number N to obtain a 1-order item A i And corresponding final numerical support degree.
If transaction t k In the above, if the parameter value corresponding to the technical index A is null, A is defined i -A k ＝1；Is 0.
The numerical support degree can also support the calculation of Boolean variable, and the transaction t k And t i Wherein A is defined when the indices of two Boolean-type variables are the same i -A k ＝0，1, different from that, definition A i -A k ＝1；/>Is 0.
In the formula, f should be set according to the distribution condition of the data, and when the data distribution is uniform, f (x) is set as a linear function:
f(x)＝x
if the data with smaller current attribute difference can play a larger role in the increase of the support, and the data with larger difference rapidly drops to approach 0, an exponential function is used.
f(x)＝ae bx
The independent variable x in the above formula shows the difference between the two groups of data, and the difference is largest when 0 and smallest when 1. Setting two groups of parameters a and b, wherein f (x) =1 when the difference is minimum (x=1) after exponential function transformation is ensured; when the difference is maximum (x=0), f (x) should approach 0, and the specific value should refer to the size of the transaction database itself, so that the single support degree is still not more than 0.1 after being accumulated. In an embodiment, 1000 transactions are included, and the value of f (x=0) should be less than 0.0001.
And 2.3, screening the first-order frequent set, manually designating a minimum support threshold, sorting the items according to the respective support, and cutting the first-order item set smaller than the minimum support threshold to obtain the first-order frequent set, wherein the minimum support threshold is set according to the requirements of the data in the embodiment.
Step 2.4, detecting J-order candidate sets, traversing J-1 order frequent sets when J >1, and calculating multi-order support degree, wherein the method comprises the following steps:
1≤b 1 <b 2 <...<b j ≤M
wherein,for transaction t i Item->And t k Similarity measure of corresponding items in +.>The numerical support degree is the J-order item; />For transaction t i B of (b) j Technical index->Corresponding toParameter values,/->For transaction t k (k=1, 2. N) b j Technical index->Corresponding parameter values,/->Representing the absolute value of the difference between specific values of two transactions, M being the thing t i Number of technical index items in b j A random number from 1 to M;in order to transform the similarity.
And 2.5, screening J-order frequent sets, manually designating a minimum support threshold according to the support degree ordering of the candidate sets, and cutting J-order item sets smaller than the minimum support threshold to obtain J-order frequent sets. Wherein the minimum support threshold should be set according to the requirements of the data itself in the embodiment.
Step 2.6, when the J-order frequent set is not empty, circulating the steps 2.4 and 2.5; otherwise, the obtained frequent sets of each order are cut by using a numerical confidence operator, and only the item set with the confidence coefficient larger than the minimum confidence coefficient is reserved and used as the association rule of the database transformation domain. The numerical confidence calculation method is as follows:
wherein, support A For the numerical Support degree corresponding to the item A, support (A∪B) If the item is 1 st order, the calculation method is the same as the step 2.2, otherwise, the calculation method is the same as the step 2.4.
The minimum confidence is set according to the data distribution and application requirements, and in the embodiment is set to 0.7, namely, the mined rule is 70% trusted.
And 2.7, recovering the rule, and inversely converting the specific numerical values of the items in the rule from the value range of 0-1 to the original value range according to different attributes according to the conversion method specified in the step 2.1 to obtain the association rule result.
Step 3: optical remote sensing load index recommendation
And 3.1, selecting association rules, namely selecting rules from application directions to technical indexes in all obtained strong association rules, and eliminating other rules.
And 3.2, analyzing and recommending indexes, and according to the rule selected in the step 3.1, giving out a technical index item with higher confidence as a design recommendation according to the input application direction information, wherein the minimum confidence threshold value is set according to the requirement, and the minimum confidence threshold value is consistent with the step 2.6 in the embodiment.
If rule applies direction B to a certain index A or index set A bj (bj=1, 2,.,. M) (where M is the index set dimension obtained by association analysis) rules have a higher confidence level C, and meet the algorithm requirement. It means that the remote sensing load facing the application direction B should be provided with a under the probability of C bj (bj=1, 2.,.. M) index set. Application of inland water monitoring to spectral resolution, for example<The confidence of 10nm is 100%, which means that when remote sensing load is applied to inland water detection, 100% probability exists that the spectrum resolution should be thinned to be within 10 nm.
According to the method, the optical remote sensing load index acquisition method based on numerical association analysis is adopted, when the strong association rule of the application direction and the technical index is mined, the information of the technical index numerical value is fully utilized through numerical support and confidence calculation, the information loss of data layering of the traditional algorithm can be avoided, and the association analysis result, namely the accuracy of the acquired index is improved.
While the preferred embodiments of the present invention have been described above, it is not intended to limit the invention, and any person skilled in the art may make possible variations and modifications to the solution of the present invention using the methods and techniques disclosed above without departing from the spirit and scope of the invention. Therefore, any simple modification equivalent to the above embodiments according to the technical substance of the present invention falls within the scope of the technical solution of the present invention.
Claims (9)
1. An optical remote sensing load index obtaining method based on numerical correlation analysis is characterized by comprising the following steps:
step 1, constructing a remote sensing load transaction database based on the application direction and the technical index of the remote sensing load;
step 2, carrying out numerical association analysis on the remote sensing load transaction database, improving an Apriori algorithm, mining association rules between the application direction of the remote sensing load and technical indexes, and extracting strong association rules;
step 3, selecting a rule from an application direction to a technical index, combining a strong association rule according to input application direction information, taking the technical index with the confidence coefficient of at least 0.5 corresponding to the strong association rule as a recommendation result, and further acquiring an optical remote sensing load index facing remote sensing application;
in the step 2, the method for extracting the strong association rule is as follows:
step 2.1: normalizing the data;
step 2.2: traversing the database, and calculating the numerical support degree of J-order items, wherein J is more than or equal to 1, so as to obtain a J-order candidate item set;
step 2.3: cutting a J-order candidate item set smaller than the minimum support degree to obtain a J-order frequent item set;
step 2.4: when the J-order frequent item set is not empty, steps 2.2 and 2.3 are circulated, otherwise, the obtained frequent item set of each order is cut by using the numerical confidence coefficient, and items smaller than the minimum confidence coefficient are cut, so that an association rule result of a transformation domain is obtained;
step 2.5: and (3) recovering the rule, and inversely converting the specific numerical values from the value range of 0-1 to the original value range according to different attributes by using the items in the rule according to the conversion method specified in the step (2.1) to obtain a strong association rule result.
2. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 1, wherein the method comprises the following steps: in step 1, the types covered by the technical indexes in the remote sensing load transaction database are consistent with the types of the finally obtained recommended technical indexes, and the technical index data are used as numerical data to keep the original specific numerical value of the numerical data and are not converted into Boolean data.
3. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 2, wherein the method comprises the following steps: the technical index comprises at least one numerical data of ground resolution, spectrum resolution, radiation resolution and time resolution, and the application direction comprises land, atmosphere and ocean.
4. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 1, wherein the method comprises the following steps: in step 1, a transaction t in a database is formed by using a technical index or application direction data corresponding to a remote sensing load k K=1, 2,..n, where the item contained therein is a bj Bj=1, 2, M, all the transactions corresponding to each remote sensing load form a remote sensing load transaction database D.
5. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 4, wherein the method comprises the following steps: certain transaction t in remote sensing load transaction database D k If the technical index corresponding to the data is empty, if the application direction corresponds to multiple groups of data, the data is recorded in parallel as multiple items.
6. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 1, wherein the method comprises the following steps: in step 2.2, when j=1, the first-order candidate item set detection is performed, the normalized data in the database is traversed, and the item support degree is calculated, and the calculation method is as follows:
wherein A is i For transaction t i Parameter value corresponding to technical index A in the middle, A k For transaction t k Parameter values corresponding to technical index a in (1, 2), where k=1, 2, N, abs (a i -A k ) Representing the absolute value of the specific numerical gap of two transactions,is a measure of similarity of two things,
the final numerical support degree; n is the total number of transactions in the database;
in order to transform the similarity.
7. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 1, wherein the method comprises the following steps: in step 2.2, when J >1, traversing the J-1 frequent item set, and calculating the multi-order support degree, wherein the method is as follows:
1≤b 1 ＜b 2 ＜...＜b j ≤M
wherein,for transaction t i Item->And t k Similarity measure of corresponding items in +.>The numerical support degree is the J-order item; />For transaction t i B of (b) j Technical index->Corresponding parameter values,/->For transaction t k B of (b) j Technical index->Corresponding parameter values, wherein k=1, 2,..>Representing the absolute value of the difference between specific values of two transactions, M being the thing t i Number of technical index items in b j A random number from 1 to M;in order to transform the similarity.
8. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 6 or 7, wherein the method comprises the following steps of: and (3) screening J-order frequent item sets, manually designating a minimum support threshold, and sorting J-order items smaller than the minimum support threshold according to the respective support, so as to obtain the J-order frequent item sets.
9. The method for acquiring the optical remote sensing load index based on numerical correlation analysis according to claim 1, wherein the method comprises the following steps: in step 2.4, numerical confidenceThe calculation method comprises the following steps:
wherein, support A For the numerical Support degree corresponding to the item A, support (A∪B) The numerical support of the simultaneous occurrence of the items A and B.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505977.4A CN111831693B (en) | 2020-06-05 | 2020-06-05 | Optical remote sensing load index acquisition method based on numerical correlation analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505977.4A CN111831693B (en) | 2020-06-05 | 2020-06-05 | Optical remote sensing load index acquisition method based on numerical correlation analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111831693A CN111831693A (en) | 2020-10-27 |
| CN111831693B true CN111831693B (en) | 2024-02-09 |
Family
ID=72899269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505977.4A Active CN111831693B (en) | 2020-06-05 | 2020-06-05 | Optical remote sensing load index acquisition method based on numerical correlation analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111831693B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113836793A (en) * | 2021-09-03 | 2021-12-24 | 成都众享天地网络科技有限公司 | Electromagnetic environment situation perception prediction method based on association criterion |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004192140A (en) * | 2002-12-09 | 2004-07-08 | Sony Corp | Data communication system, data transmitting device, data receiving device and method, and computer program |
| CN103776532A (en) * | 2014-01-14 | 2014-05-07 | 北京空间机电研究所 | Hyperspectral-imager index optimization method based on remote-sensing application |
| CN106126577A (en) * | 2016-06-17 | 2016-11-16 | 北京理工大学 | A kind of weighted association rules method for digging based on data source Matrix dividing |
| CN108334548A (en) * | 2017-12-26 | 2018-07-27 | 爱品克科技（武汉）股份有限公司 | A kind of data mining technology based on correlation rule |
| CN110968618A (en) * | 2019-11-07 | 2020-04-07 | 华中科技大学 | Method for mining quantitative association rule of welding parameters and application |
| CN111222199A (en) * | 2019-11-13 | 2020-06-02 | 中国汽车工程研究院股份有限公司 | Key index selection and equivalent calculation method during association of user and test field |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE602005010539D1 (en) * | 2004-12-28 | 2008-12-04 | Fanuc Ltd | Determining a threshold value for a device for detecting damage on a tool |
-
2020
- 2020-06-05 CN CN202010505977.4A patent/CN111831693B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004192140A (en) * | 2002-12-09 | 2004-07-08 | Sony Corp | Data communication system, data transmitting device, data receiving device and method, and computer program |
| CN103776532A (en) * | 2014-01-14 | 2014-05-07 | 北京空间机电研究所 | Hyperspectral-imager index optimization method based on remote-sensing application |
| CN106126577A (en) * | 2016-06-17 | 2016-11-16 | 北京理工大学 | A kind of weighted association rules method for digging based on data source Matrix dividing |
| CN108334548A (en) * | 2017-12-26 | 2018-07-27 | 爱品克科技（武汉）股份有限公司 | A kind of data mining technology based on correlation rule |
| CN110968618A (en) * | 2019-11-07 | 2020-04-07 | 华中科技大学 | Method for mining quantitative association rule of welding parameters and application |
| CN111222199A (en) * | 2019-11-13 | 2020-06-02 | 中国汽车工程研究院股份有限公司 | Key index selection and equivalent calculation method during association of user and test field |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111831693A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110008948B (en) | Hyperspectral image target detection method based on variational self-coding network | |
| CN110619263B (en) | Hyperspectral remote sensing image anomaly detection method based on low-rank joint collaborative representation | |
| CN111008726B (en) | Class picture conversion method in power load prediction | |
| CN115688982B (en) | Building photovoltaic data complement method based on WGAN and whale optimization algorithm | |
| CN111831693B (en) | Optical remote sensing load index acquisition method based on numerical correlation analysis | |
| CN112434662A (en) | Tea leaf scab automatic identification algorithm based on multi-scale convolutional neural network | |
| CN118134539B (en) | User behavior prediction method based on intelligent kitchen multi-source data fusion | |
| CN117078077A (en) | Ecological vulnerability evaluation method for expressway road domain | |
| CN111860359A (en) | Point cloud classification method based on improved random forest algorithm | |
| CN110659686A (en) | Fuzzy coarse grain outlier detection method for mixed attribute data | |
| Liu et al. | Hyperspectral band selection based on consistency-measure of neighborhood rough set theory | |
| CN111340761B (en) | Remote sensing image change detection method based on fractal attribute and decision fusion | |
| CN111666999A (en) | Remote sensing image classification method | |
| CN112784777A (en) | Unsupervised hyperspectral image change detection method based on antagonistic learning | |
| Rabcan et al. | Classification by fuzzy decision trees inducted based on Cumulative Mutual Information | |
| CN116383645A (en) | Intelligent system health degree monitoring and evaluating method based on anomaly detection | |
| CN113640244B (en) | Fruit tree variety identification method based on visible near infrared spectrum | |
| CN113205124B (en) | Clustering method, system and storage medium based on density peak value under high-dimensional real scene | |
| CN114897880A (en) | Remote sensing image change detection method based on self-adaptive image regression | |
| Sheng et al. | Fuzzy preprocessing and clustering analysis method of underwater multiple targets in forward looking sonar image for AUV tracking | |
| CN114254678A (en) | Radar signal pulse internal modulation identification method based on de-noising guide decoupling network | |
| CN106570127A (en) | Remote sensing image retrieval method and system based on object attribute association rules | |
| CN113191397A (en) | Multi-dimensional signal feature fusion method based on maximum correlation entropy criterion | |
| CN106570124A (en) | Remote sensing image semantic retrieval method and remote sensing image semantic retrieval system based on object level association rule | |
| Yu et al. | An Image Comparison Algorithm Based on Contour Similarity |
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 |