CN106874674B - A kind of multivariate time series method for measuring similarity towards marine field - Google Patents
A kind of multivariate time series method for measuring similarity towards marine field Download PDFInfo
- Publication number
- CN106874674B CN106874674B CN201710089138.7A CN201710089138A CN106874674B CN 106874674 B CN106874674 B CN 106874674B CN 201710089138 A CN201710089138 A CN 201710089138A CN 106874674 B CN106874674 B CN 106874674B
- Authority
- CN
- China
- Prior art keywords
- typhoon
- data
- time series
- attribute
- moving direction
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01W—METEOROLOGY
- G01W1/00—Meteorology
- G01W1/10—Devices for predicting weather conditions
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Landscapes
- Environmental & Geological Engineering (AREA)
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Atmospheric Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Ecology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of multivariate time series method for measuring similarity towards marine field, the method for measuring similarity is the following steps are included: S1 collection table wind data；S2 pre-processes typhoon data；Typhoon data are described in S3；S4 carries out similarity measurement to typhoon data；S5 exports similar typhoon；Wherein, the step S2 includes screening typhoon attribute, supplementary data, and the step S3 includes that moving direction indicates, typhoon time series indicates, the step S4 includes that typhoon attribute weight calculates, W-DTW distance calculates, W-DTW Distance Judgment.It the advantage is that judgement has dynamic, spatiality, predictability and multiattribute two ocean time serieses whether similar；The development trend of current Oceanic Events is judged according to the Oceanic Events occurred；For Oceanic disasters, convenient and fast aid decision can be provided for relevant departments, properly protect measure, reduces its bring economic loss and casualties.
Description
Technical field
The present invention relates to similarity measurement technical fields, specifically, being a kind of multivariate time sequence towards marine field
Column method for measuring similarity.
Background technique
21 century is numerical ocean model, in the new era for facing the big project of sustainable development, the status of ocean and Development volue
Increasingly paid attention to by people.China is as a developing coastal state, and undoubtedly, ocean also will hair to the development in China
Wave increasingly important role.However, in recent decades, while promoting economic development, all kinds of Oceanic disasters are following,
For Oceanic disasters there are many class, the factor caused is also different.Mainly there are disastrous sea ice, red tide, storm tide and tsunami etc.
Deng there are also typhoons etc. for Disasters relevant to atmosphere, wherein China is by typhoon influence one of the countries with the most serious ....Therefore
Can effectively describe Oceanic disasters and carry out hazard forecasting, trend analysis is of great significance.
Typhoon has the characteristics that dynamic, spatiality, predictability, dynamic refer to that its intensity is constantly changing；Space
Property refer to it is different or there is same intensity but do not occur in the same region in different zones its intensity；Predictability refers to it
Generating process has regularity.Described in typhoon database the time of origin that typhoon has occurred, the end time, longitude and latitude, etc.
The information such as grade, speed, movement speed, moving direction and pressure, typhoon data have more attributes, need to utilize multivariate time sequence
Column are studied.Currently, description, the quantitative analysis for typhoon data are not also very perfect.
It is similar to disclose a kind of traffic flow by Chinese invention patent CN201610811178.3, publication date 2017.02.08
The method of discrimination of property.But the similitude accuracy that this method obtains is high not as good as the method for the present invention.
Chinese invention patent CN201610264725.0, publication date 2016.08.31 are disclosed a kind of based on big data
Trend curve local feature matching process.But this method carry out postsearch screening, data processing amount increase, processing speed compared with
Slowly.
Therefore, the weighting DTW measure for needing a kind of accurate description typhoon data, carrying out typhoon similarity measurement, and
It is had not been reported at present about this method for measuring similarity.
Summary of the invention
The purpose of the present invention is aiming at the shortcomings in the prior art, provide a kind of multivariate time series towards marine field
Method for measuring similarity.
To achieve the above object, the technical solution adopted by the present invention is that:
A kind of multivariate time series method for measuring similarity towards marine field, the method for measuring similarity include
Following steps:
S1: collection table wind data；
S2: typhoon data are pre-processed；
S3: typhoon data are described；
S4: similarity measurement is carried out to typhoon data；
S5: similar typhoon is exported；
Wherein, the step S2 includes screening typhoon attribute, supplementary data, and the step S3 includes moving direction table
Show, the expression of typhoon time series, the step S4 includes that typhoon attribute weight calculates, W-DTW distance calculates, W-DTW distance
Judgement.
The step S1 collection table wind data includes collecting existing typhoon initial data, collecting typhoon number in database
According to.
The step S2 is pretreated to the progress of typhoon initial data, and steps are as follows:
S21: screening typhoon attribute
Typhoon attribute in need of consideration is selected, affiliated typhoon attribute includes intensity L, wind speed V, moving direction MD, movement
Speed MV, pressure P；
S22: supplementary data
The field that the typhoon attribute value filtered out is null is supplemented according to front and back data.
The step of typhoon data are described in the step S3 is as follows:
S31: moving direction indicates
Since the moving direction of typhoon is indicated using 16 wind roses, quantize to it, i.e. shifting in typhoon data
Dynamic direction shares 16 kinds, is indicated with 0-15, with due north for 0, rotates clockwise, is successively 1,2 ... ..., and 15, for not using ten
What six wind roses indicated, numeralization expression also is carried out to it；
S32: typhoon time series indicates
If intensity of typhoon L=[L1,L2,……,Ln]T, wind speed V=[V1,V2,……,Vn]T, moving direction MD=[MD1,
MD2,……,MDn]T, movement speed MV=[MV1,MV2,……,MVn]T, pressure P=[P1,P2,……,Pn]T, then typhoon time
Sequence A are as follows:
Wherein, n indicates time points, intensity of the element representation of the first row typhoon at moment 1, wind speed, movement side
To, the relative recording of movement speed, pressure, and so on, last line indicates intensity of the typhoon in moment n, wind speed, shifting
Dynamic direction, movement speed, pressure relative recording.
The step of step S4 carries out similarity measurement to typhoon data is as follows:
S41: typhoon attribute weight calculates
Using schichtenaufbau method Judgement Matricies, typhoon attribute weight is obtained, its step are as follows:
S411: set the intensity of typhoon, wind speed, moving direction, movement speed, pressure attribute weight be respectively W1、W2、W3、
W4、W5；
S412: Judgement Matricies
Using schichtenaufbau method Judgement Matricies, gained matrix is as follows:
S413: approximate solution calculating is carried out to judgment matrix
S4131: each row each element product M of judgment matrix is calculatedi, calculation formula is
Mi=Li×Vi×MVi×MDi×Pi(i∈[1,5])；
S4132: M is calculatediN times root Wi', calculation formula is
S4133: normalized obtains weight Wi, calculation formula is
S4134: the maximum eigenvalue λ of judgment matrix is calculatedmax；
S4135: carrying out consistency check, and calculation formula is
CR=CI/RI
Wherein, CR is test coefficient, and CI is coincident indicator, and RI is random index, if CR < 0.1, passes through
Consistency check then shows that weight meets the requirements；If CR > 0.1, consistency check does not pass through, and need to re-start weight meter
It calculates；
S42:W-DTW distance calculates
W-DTW distance is the DTW distance of weighting, and steps are as follows for calculating:
S421: selecting the time series of any typhoon in the time series and database of existing typhoon, be set to X, Y,
Then X, Y are respectively
S422: cardinal distance is calculated from d (xi,yj), calculation formula is
Wherein, [1, m] i ∈, j ∈ [1, n]；
S423: calculating the W-DTW distance of time series X and Y, and calculation formula is
Wherein, r (i, j) indicates r (X (1:i), Y (1:j)), i ∈ [1, m], j ∈ [1, n]；
S424: repeating step S421-S423, obtains the W-DTW distance of each typhoon in existing typhoon and database；
S43:W-DTW Distance Judgment
All W-DTW distances are compared two-by-two, obtain one the smallest W-DTW distance.
It is output and platform of the existing typhoon W-DTW in the smallest database that the step S5, which exports similar typhoon,
Wind.
The step S413, approximate solution calculating further include calculating with method calculating, power method.
The invention has the advantages that:
1, whether judgement has dynamic, spatiality, predictability and multiattribute two ocean time serieses similar；
2, the development trend of current Oceanic Events is judged according to the Oceanic Events occurred；
3, for Oceanic disasters, convenient and fast aid decision can be provided for relevant departments, properly protect measure, reduces its band
The economic loss and casualties come.
Detailed description of the invention
Attached drawing 1 is a kind of flow chart of multivariate time series method for measuring similarity towards marine field of the invention.
Attached drawing 2 is that Typhoon Tracks direction number value is indicated referring to figure.
Attached drawing 3 is importance rate and its assignment referring to figure.
Attached drawing 4 is random index value referring to figure.
Specific embodiment
It elaborates with reference to the accompanying drawing to specific embodiment provided by the invention.
Embodiment 1
Referring to Fig.1, a kind of the step of multivariate time series method for measuring similarity towards marine field of the invention is such as
Under:
S1: collection table wind data；
S2: typhoon data are pre-processed；
S3: typhoon data are described；
S4: similarity measurement is carried out to typhoon data；
S5: similar typhoon is exported；
Wherein, the step S2 includes screening typhoon attribute, supplementary data, and the step S3 includes moving direction table
Show, the expression of typhoon time series, the step S4 includes that typhoon attribute weight calculates, W-DTW distance calculates, W-DTW distance
Judgement.
Embodiment 2
A kind of specific work steps of multivariate time series method for measuring similarity towards marine field of the invention is such as
Under:
S1: collection table wind data
Collection table wind data includes collecting existing typhoon initial data, collecting typhoon data in database.
S2: typhoon initial data is pre-processed
S21: screening typhoon attribute
Typhoon attribute in need of consideration is selected, affiliated typhoon attribute includes intensity L, wind speed V, moving direction MD, movement
Speed MV, pressure P；
S22: supplementary data
The field that the typhoon attribute value filtered out is null is supplemented according to front and back data.
S3: typhoon data are described
S31: moving direction indicates
Since the moving direction of typhoon is indicated using 16 wind roses, quantize to it, referring to Fig. 2, i.e. typhoon number
Moving direction in shares 16 kinds, is indicated with 0-15, with due north for 0, rotates clockwise, is successively 1,2 ... ..., and 15, for
It is not indicated using 16 wind roses, numeralization expression also is carried out to it；
S32: typhoon time series indicates
If intensity of typhoon L=[L1,L2,……,Ln]T, wind speed V=[V1,V2,……,Vn]T, moving direction MD=[MD1,
MD2,……,MDn]T, movement speed MV=[MV1,MV2,……,MVn]T, pressure P=[P1,P2,……,Pn]T, then typhoon time
Sequence A are as follows:
Wherein, n indicates time points, intensity of the element representation of the first row typhoon at moment 1, wind speed, movement side
To, the relative recording of movement speed, pressure, and so on, last line indicates intensity of the typhoon in moment n, wind speed, shifting
Dynamic direction, movement speed, pressure relative recording；
S4: similarity measurement is carried out to typhoon data
S41: typhoon attribute weight calculates
Using schichtenaufbau method Judgement Matricies, typhoon attribute weight is obtained, its step are as follows:
S411: set the intensity of typhoon, wind speed, moving direction, movement speed, pressure attribute weight be respectively W1、W2、W3、
W4、W5；
S412: Judgement Matricies
Using schichtenaufbau method Judgement Matricies, gained matrix is as follows:
S413: approximate solution calculating is carried out to judgment matrix
It includes the calculating of root method that approximate solution, which calculates, and method calculates, power method calculates, this step carries out approximate solution meter using root method
It calculates, its step are as follows:
S4131: each row each element product M of judgment matrix is calculatedi, calculation formula is
Mi=Li×Vi×MVi×MDi×Pi(i∈[1,5])；
S4132: M is calculatediN times root Wi', calculation formula is
S4133: normalized obtains weight Wi, calculation formula is
S4134: the maximum eigenvalue λ of judgment matrix is calculatedmax；
S4135: carrying out consistency check, and calculation formula is
CR=CI/RI
Wherein, CR is test coefficient, and CI is coincident indicator, and RI is random index, if CR < 0.1, passes through
Consistency check then shows that weight meets the requirements；If CR > 0.1, consistency check does not pass through, and need to re-start weight meter
It calculates；
S42:W-DTW distance calculates
W-DTW distance is the DTW distance of weighting, and steps are as follows for calculating:
S421: any typhoon time series in existing typhoon time series and database is selected, is set to X, Y, then X, Y
Respectively
S422: cardinal distance is calculated from d (xi, yj), calculation formula is
Wherein, [1, m] i ∈, j ∈ [1, n]；
S423: calculating the W-DTW distance of time series X and Y, and calculation formula is
Wherein, r (i, j) indicates r (X (1:i), Y (1:j)), i ∈ [1, m], j ∈ [1, n]；
S424: repeating step S421-S423, obtains the W-DTW distance of each typhoon in existing typhoon and database；
S43:W-DTW Distance Judgment
All W-DTW distances are compared two-by-two, obtain one the smallest W-DTW distance；
S5: similar typhoon is exported
Output and typhoon of the existing typhoon W-DTW in the smallest database.
A kind of the advantages of multivariate time series method for measuring similarity towards marine field of the invention, is, judges have
There are dynamic, spatiality, predictability and multiattribute two ocean time serieses whether similar；According to the ocean occurred
Event judges the development trends of current Oceanic Events；For Oceanic disasters, easily auxiliary can be provided for relevant departments and determined
Plan, properly protect measure, reduces its bring economic loss and casualties.
Embodiment 3
A kind of Application Example of multivariate time series method for measuring similarity towards marine field of the invention is as follows:
S1: collection table wind data
Collection table wind data includes collecting existing typhoon initial data 1, collecting typhoon data 2,3 in database.
S2: typhoon initial data is pre-processed
S21: screening typhoon attribute
Typhoon attribute in need of consideration is selected, affiliated typhoon attribute includes intensity L, wind speed V, moving direction MD, movement
Speed MV, pressure P；
S22: supplementary data
The field that the typhoon attribute value filtered out is null is supplemented according to front and back data.
S3: typhoon data are described
S31: moving direction indicates
Since the moving direction of typhoon is indicated using 16 wind roses, quantize to it, referring to Fig. 2, i.e. typhoon number
Moving direction in shares 16 kinds, is indicated with 0-15, with due north for 0, rotates clockwise, is successively 1,2 ... ..., and 15, for
It is not indicated using 16 wind roses, numeralization expression also is carried out to it；
S32: typhoon time series indicates
If intensity of typhoon L=[L1,L2,……,Ln]T, wind speed V=[V1,V2,……,Vn]T, moving direction MD=[MD1,
MD2,……,MDn]T, movement speed MV=[MV1,MV2,……,MVn]T, pressure P=[P1,P2,……,Pn]T, then typhoon time
Sequence A are as follows:
Wherein, n indicates time points, intensity of the element representation of the first row typhoon at moment 1, wind speed, movement side
To, the relative recording of movement speed, pressure, and so on, last line indicates intensity of the typhoon in moment n, wind speed, shifting
Dynamic direction, movement speed, pressure relative recording.
The time series of typhoon 1-3 is obtained, it is as follows
S4: similarity measurement is carried out to typhoon data
S41: typhoon attribute weight calculates
Using schichtenaufbau method Judgement Matricies, typhoon attribute weight is obtained, its step are as follows:
S411: set the intensity of typhoon, wind speed, moving direction, movement speed, pressure attribute weight be respectively W1、W2、W3、
W4、W5；
S412: Judgement Matricies
Using schichtenaufbau method and referring to Fig. 3 Judgement Matricies, gained matrix is as follows:
S413: approximate solution calculating is carried out to judgment matrix
This step carries out approximate solution calculating using root method, and its step are as follows:
S4131: each row each element product M of judgment matrix is calculatedi, calculation formula is
Mi=Li×Vi×MVi×MDi×Pi(i∈[1,5])；
S4132: M is calculatediN times root Wi', calculation formula is
S4133: normalized obtains weight Wi, calculation formula is
S4134: the maximum eigenvalue λ of judgment matrix is calculatedmax；
S4135: carrying out consistency check, and calculation formula is
CR=CI/RI
Wherein, CR is test coefficient, and CI is coincident indicator, and RI is random index, the value of RI referring to Fig. 4, if
CR < 0.1 then shows that weight meets the requirements then by consistency check；If CR > 0.1, consistency check does not pass through, and needs weight
It is new to carry out weight calculation；
Weight W is obtained, weight W is as follows,
S42:W-DTW distance calculates
W-DTW distance is the DTW distance of weighting, and steps are as follows for calculating:
S421: selection time series 1,2 is set to X, Y, then X, Y are respectively
S422: cardinal distance is calculated from d (xi,yj), calculation formula is
Wherein, [1, m] i ∈, j ∈ [1, n]；
I=8, j=9 are taken, and substitutes into corresponding W value, then d (x8,y9)=1.673；
S423: calculating the W-DTW distance of time series X and Y, and calculation formula is
Wherein, r (i, j) indicates r (X (1:i), Y (1:j)), i ∈ [1, m], j ∈ [1, n].
By d (x8,y9)=1.673 substitute into and calculate to obtain r (8,9)=17.297；
S424: repeating step S421-S423, obtains the W-DTW distance of time series 1 and 3, r (8,9)=340.928；
S43:W-DTW Distance Judgment
All W-DTW distances are compared, the one the smallest W-DTW distance of acquisition, i.e., 17.297；
S5: similar typhoon is exported
Export typhoon 2 similar with typhoon 1.
The above is only a preferred embodiment of the present invention, it is noted that for the ordinary skill people of the art
Member, under the premise of not departing from the method for the present invention, can also make several improvement and supplement, these are improved and supplement also should be regarded as
Protection scope of the present invention.
Claims (3)
1. a kind of multivariate time series method for measuring similarity towards marine field, which is characterized in that the multivariate time
Sequence similarity measure the following steps are included:
S1: collection table wind data；
S2: typhoon data are pre-processed；
S3: typhoon data are described；
S4: similarity measurement is carried out to typhoon data；
S5: similar typhoon is exported；
Wherein, the step S2 include screening typhoon attribute, supplementary data, the step S3 include moving direction indicate,
Typhoon time series indicates that the step S4 includes that typhoon attribute weight calculates, W-DTW distance calculates, W-DTW distance is sentenced
It is disconnected；The step S1 collection table wind data includes collecting existing typhoon initial data, collecting typhoon data in database；
The step S2 is pretreated to the progress of typhoon initial data, and steps are as follows:
S21: screening typhoon attribute
Typhoon attribute in need of consideration is selected, affiliated typhoon attribute includes intensity L, wind speed V, moving direction MD, movement speed
MV, pressure P；
S22: supplementary data
The field that the typhoon attribute value filtered out is null is supplemented according to front and back data；
The step of typhoon data are described in the step S3 is as follows:
S31: moving direction indicates
Since the moving direction of typhoon is indicated using 16 wind roses, quantize to it, i.e. mobile side in typhoon data
It to sharing 16 kinds, is indicated with 0-15, with due north for 0, rotates clockwise, be successively 1,2 ... ..., 15, for not using 16 wind
It is indicated to figure, numeralization expression also is carried out to it；
S32: typhoon time series indicates
If intensity of typhoon L=[L1,L2,……,Ln]T, wind speed V=[V1,V2,……,Vn]T, moving direction MD=[MD1,
MD2,……,MDn]T, movement speed MV=[MV1,MV2,……,MVn]T, pressure P=[P1,P2,……,Pn]T, then typhoon time
Sequence A are as follows:
Wherein, n indicates time points, intensity of the element representation of the first row typhoon at moment 1, wind speed, moving direction, shifting
The relative recording of dynamic speed, pressure, and so on, last line indicates intensity of the typhoon in moment n, wind speed, movement side
To, the relative recording of movement speed, pressure；
The step of step S4 carries out similarity measurement to typhoon data is as follows:
S41: typhoon attribute weight calculates
Using schichtenaufbau method Judgement Matricies, typhoon attribute weight is obtained, its step are as follows:
S411: set the intensity of typhoon, wind speed, moving direction, movement speed, pressure attribute weight be respectively W1、W2、W3、W4、
W5；
S412: Judgement Matricies
Using schichtenaufbau method Judgement Matricies, gained matrix is as follows:
S413: approximate solution calculating is carried out to judgment matrix
S4131: each row each element product M of judgment matrix is calculatedi, calculation formula is
Mi=Li×Vi×MVi×MDi×Pi(i∈[1,5])；
S4132: M is calculated using root methodiN times root Wi', calculation formula is
S4133: normalized obtains weight Wi, calculation formula is
S4134: the maximum eigenvalue λ of judgment matrix is calculatedmax；
S4135: consistency check, calculation formula CR=CI/RI are carried out
Wherein, CR is test coefficient, and CI is coincident indicator, and RI is random index, if CR < 0.1, by consistent
Property examine, then show that weight meets the requirements；If CR > 0.1, consistency check does not pass through, and need to re-start weight calculation；
S42:W-DTW distance calculates
W-DTW distance is the DTW distance of weighting, and steps are as follows for calculating:
S421: selecting the time series of any typhoon in the time series and database of existing typhoon, is set to X, Y, then X, Y
Respectively
S422: cardinal distance is calculated from d (xi,yj), calculation formula is
d(xi,yj)=(W1(Li-L'j)2+W2(Vi-V'j)2+W3(MDi-MD'j)2+W4(MVi-MV'j)2+W5(Pi-P'j)2)1/2
Wherein, [1, m] i ∈, j ∈ [1, n]；
S423: calculating the W-DTW distance of time series X and Y, and calculation formula is
Wherein, r (i, j) indicates r (X (1:i), Y (1:j)), i ∈ [1, m], j ∈ [1, n]；
S424: repeating step S421-S423, obtains the W-DTW distance of each typhoon in existing typhoon and database；
S43:W-DTW Distance Judgment
All W-DTW distances are compared two-by-two, obtain one the smallest W-DTW distance.
2. multivariate time series method for measuring similarity according to claim 1, which is characterized in that the step S5 is defeated
Similar typhoon is output and typhoon of the existing typhoon W-DTW in the smallest database out.
3. multivariate time series method for measuring similarity according to claim 1, which is characterized in that the step
S413, approximate solution calculating further include and one of method calculating, power method calculating.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710089138.7A CN106874674B (en) | 2017-02-20 | 2017-02-20 | A kind of multivariate time series method for measuring similarity towards marine field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710089138.7A CN106874674B (en) | 2017-02-20 | 2017-02-20 | A kind of multivariate time series method for measuring similarity towards marine field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106874674A CN106874674A (en) | 2017-06-20 |
| CN106874674B true CN106874674B (en) | 2019-04-19 |
Family
ID=59167215
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710089138.7A Active CN106874674B (en) | 2017-02-20 | 2017-02-20 | A kind of multivariate time series method for measuring similarity towards marine field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106874674B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020043029A1 (en) * | 2018-08-25 | 2020-03-05 | 司书春 | Method for predicting air pollution by means of vectorization analysis |
| CN109297470B (en) * | 2018-10-19 | 2021-01-29 | 中国计量大学 | Similar typhoon matching algorithm based on power factors and path information |
| CN109635867B (en) * | 2018-12-10 | 2022-11-08 | 合肥工业大学 | Method and system for measuring ocean moving target track similarity |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005105A (en) * | 2010-09-27 | 2011-04-06 | 上海海洋大学 | Marine disaster early-warning device based on time series similarity matching |
| CN104217260A (en) * | 2014-09-19 | 2014-12-17 | 南京信息工程大学 | Combined filling system for measured wind speed loss values of multiple neighboring wind motors in wind field |
| CN105138729A (en) * | 2015-07-24 | 2015-12-09 | 南京信息工程大学 | Filling method based on PSO-GRNN (Particle Swarm Optimization-Generalized Regression Neural Network) for defect wind speed values of wind turbines in wind power plant |
| CN106354889A (en) * | 2016-11-07 | 2017-01-25 | 北京化工大学 | Batch process unequal-length time period synchronization method based on LWPT-DTW (lifting wavelet package transform-dynamic time warping) |
-
2017
- 2017-02-20 CN CN201710089138.7A patent/CN106874674B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102005105A (en) * | 2010-09-27 | 2011-04-06 | 上海海洋大学 | Marine disaster early-warning device based on time series similarity matching |
| CN104217260A (en) * | 2014-09-19 | 2014-12-17 | 南京信息工程大学 | Combined filling system for measured wind speed loss values of multiple neighboring wind motors in wind field |
| CN105138729A (en) * | 2015-07-24 | 2015-12-09 | 南京信息工程大学 | Filling method based on PSO-GRNN (Particle Swarm Optimization-Generalized Regression Neural Network) for defect wind speed values of wind turbines in wind power plant |
| CN106354889A (en) * | 2016-11-07 | 2017-01-25 | 北京化工大学 | Batch process unequal-length time period synchronization method based on LWPT-DTW (lifting wavelet package transform-dynamic time warping) |
Non-Patent Citations (2)
| Title |
|---|
| 一种基于DTW聚类的水文时间序列相似性挖掘方法;杨艳林等;《计算机科学》;20160229;第43卷(第2期);第2-3.5节 |
| 风电场邻近风电机组缺测风速集成填充方法;杜杰等;《太阳能学报》;20160831;第37卷(第8期);第2105页第2.1节 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106874674A (en) | 2017-06-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Detection of trends in precipitation during 1960–2008 in Jiangxi province, southeast China | |
| CN106874674B (en) | A kind of multivariate time series method for measuring similarity towards marine field | |
| CN106600574A (en) | Landslide extraction method based on remote-sensing image and altitude data | |
| Huang et al. | Hydrologic response to climate change and human activities in a subtropical coastal watershed of southeast China | |
| Li et al. | Dynamic changes of land use/cover and landscape pattern in a typical alpine river basin of the Qinghai‐Tibet Plateau, China | |
| Wei et al. | Spatiotemporal changes of land desertification sensitivity in northwest China from 2000 to 2017 | |
| CN106408213A (en) | Method and system for cascading mountain flood disaster risk analysis | |
| Ma et al. | A multisource remotely sensed data oriented method for “ghost city” phenomenon identification | |
| Wang et al. | A framework for fine classification of urban wetlands based on random forest and knowledge rules: taking the wetland cities of Haikou and Yinchuan as examples | |
| Ren et al. | Variability of the Mindanao Current induced by El Niño events | |
| CN109784720A (en) | The associated power distribution network methods of risk assessment of space-time grid is based under a kind of typhoon disaster | |
| Li et al. | Evaluation and analysis of the impact of coastal urban impervious surfaces on ecological environments | |
| Wallace | Landscape evaluation and the Essex coast | |
| CN109784602A (en) | A kind of disaster-ridden kind of coupling physical vulnerability assessment method based on PTVA model | |
| CN115421220A (en) | Multi-factor local precipitation indication method and system based on deep learning | |
| Montazeri et al. | Evaluation of Tropical Rainfall Measuring Mission (TRMM) Multi-satellite Precipitation Analysis (TMPA v7) in drought monitoring over southwest Iran | |
| Wang et al. | Review of land cover classification based on remote sensing data | |
| Searson, S. and Brundrit | Extreme high sea levels around the coast of southern Africa | |
| Yeh et al. | Applying spatial autocorrelation and logistic regression to analyze land cover change trajectory in a forested watershed | |
| CN111753680B (en) | High-resolution satellite data-based river ecological flow guarantee degree remote sensing rapid discrimination method | |
| Wang et al. | Assessment of debris flow susceptibility based on dual-channel feature fusion CNN model | |
| Heidarizadi et al. | Assessing Drought Hazard Via Combined Drought Index Using Machine Learning Techniques: A Case Study of Ilam Province | |
| Wu et al. | Analysis of Temporal and Spatial Dynamics of Forests From 2003 to 2018 | |
| Wang et al. | Characterizing Urban growth of Nanjing, China, by using multi-stage remote sensing images and landscape metrics | |
| Zhang et al. | Monitoring and Evaluating Ecological Environment Quality Change Based on RSEI Model in the Golden Quadrangle Region in the Border of China, Myanmar, Thailand and Laos |
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 |