CN104299048B - A kind of vibration of building horizontal forecast method that track traffic causes - Google Patents
A kind of vibration of building horizontal forecast method that track traffic causes Download PDFInfo
- Publication number
- CN104299048B CN104299048B CN201410529094.1A CN201410529094A CN104299048B CN 104299048 B CN104299048 B CN 104299048B CN 201410529094 A CN201410529094 A CN 201410529094A CN 104299048 B CN104299048 B CN 104299048B
- Authority
- CN
- China
- Prior art keywords
- parameter
- signal
- vibration
- building
- normalized
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 20
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 239000002689 soil Substances 0.000 claims abstract description 11
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 9
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000011835 investigation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 8
- 238000012706 support-vector machine Methods 0.000 abstract description 7
- 238000011161 development Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 abstract description 3
- 239000003471 mutagenic agent Substances 0.000 abstract description 2
- 231100000707 mutagenic chemical Toxicity 0.000 abstract description 2
- 230000003505 mutagenic effect Effects 0.000 abstract description 2
- 239000000843 powder Substances 0.000 abstract description 2
- 239000011159 matrix material Substances 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000009435 building construction Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013016 damping Methods 0.000 description 1
- 238000013481 data capture Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Business, Economics & Management (AREA)
- Signal Processing (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of vibration of building horizontal forecast method that track traffic causes,The present invention first passes through the parameter for collecting track irregularity amplitude,The parameter of foundation soil property,The parameter of train speed,The parameter of type of train and the parameter of depth of building are normalized,Then selection dbN wavelet functions and decomposition scale carry out wavelet transformation,Eliminate the Mutagen and Random Effect in primary signal,Signal after reconstruct obtains de-noising,And using the signal after de-noising as SVMs input variable,For the training test of SVMs,The SVM forecast models of demarcation are finally given to significantly improve the precision of the vibration of building horizontal forecast that track traffic causes,Supported for the selection of vibration effect evaluation and the vibration and noise reducing measure of Urban Rail Transit Development provides data,Important contribution is made that to improve urban work living environment.Therefore, present invention can be widely used to civil engineering electric powder prediction.
Description
Technical field
The present invention relates to a kind of building level of vibration Forecasting Methodology, especially with regard to the building that a kind of track traffic causes
Thing level of vibration Forecasting Methodology.
Background technology
Track traffic plays more and more important so that its freight volume is big, speed fast, the advantages of take up an area few in transportation
Role, but also triggered serious environmental problem simultaneously, the evil of shaking caused by environment such as track traffics has been listed in seven grand dukes
One of evil.The ambient vibration that traffic system causes is not only because increasingly to increase, but also due to the progress of society, people
Requirement to modern life quality also more and more higher, may not be problem in the past even for same level of vibration, and
But cause the kickback of the public more and more now.So, the ambient vibration problem caused by track traffic is used as one kind
New environmental hazard, has become a more and more serious social concern.And accurately predicted orbit traffic is to building
Construction of the influence of vibration for perceiving potential level of vibration and track traffic in time all plays the effect of key, right in addition
Level of vibration is reduced in taking appropriate measures also has important references to be worth.
The vibration of building triggered by track traffic is influenceed by many factors, including track irregularity amplitude, foundation soil
Property, train speed, type of train, depth of building etc., have extremely complex relation between them.Actual treatment this
In a little data procedures, the situation that individual data deviates desired value or a large amount of statistical values can be usually run into, how reject therein different
Regular data, extracts key message and then finds the relation between vibration of building level and these factors, with reasonable prediction track
The vibration of building that traffic causes is a difficulty very big and be badly in need of the technical problem for solving.
The content of the invention
Regarding to the issue above, the vibration effect journey it is an object of the invention to provide a kind of predicted orbit traffic for building
Degree, so as to provide the track of data support for the selection of vibration effect evaluation and the vibration and noise reducing measure of Urban Rail Transit Development
The vibration of building horizontal forecast method that traffic causes.
To achieve the above object, the present invention takes following technical scheme：The vibration of building water that a kind of track traffic causes
Flat Forecasting Methodology, it is comprised the following steps：1) original number is carried out for Train Track-roadbed-surrounding formation-building system
According to investigations, the initial data includes parameter, the parameter of foundation soil property, the parameter of train speed, the row of track irregularity amplitude
The parameter of car type and the parameter of depth of building；2) each parameter in initial data is normalized, and obtains normalizing
Each parameter after change treatment；3) by normalized after each parameter carry out respectively successively wavelet transformation decompose, each parameter is every
One layer corresponds to resolve into a low frequency signal and multiple high-frequency signals respectively；4) low frequency signal and height obtained for each parameter
Frequency signal carries out denoising Processing, removes abnormal data；5) respectively by by each parameter after denoising Processing it is corresponding one it is low
The Weight that frequency signal combines its decomposition scale with multiple high-frequency signals is added completion signal reconstruction, each letter for being weighted
Number；6) gridding method is passed through in kernel function based on each signal for weighting as the kernel function of SVM models using Radial basis kernel function
Regularization term parameter C and error term ε demarcated, so as to the SVM models demarcated.
The step 2) including herein below：The formula that each parameter in initial data is normalized one by one is such as
Under：
Wherein,It is the value after normalized, SiIt is raw value, SminIt is the minimum value in sample sequence, SmaxIt is sample
Maximum in this sequence.
The step 4) including herein below：The low frequency signal and high-frequency signal obtained for each parameter are carried out at de-noising
Reason, its process is as follows：Assuming that the model of an one-dimensional signal for Noise is as follows：
S (k)=f (k)+λ e (k) k=0,1 ..., N-1
Wherein, f (k) is the useful signal after denoising, and s (k) is noisy signal, and e (k) is the noise letter of the signal of denoising
Number, λ is weight, N represent each parameter carry out wavelet decomposition after low, high frequency total number.
The step 6) including herein below：Each signal of 70% weighting is taken as the training sample of SVM models, for marking
It is (0,100) to determine the span of regularization term parameter C and error term ε, C, and the span of ε is (0,0.4), remaining 30% conduct
Whether test sample inspection SVM models are correct, and to test result evaluate the precision of prediction of SVM models using mean square deviation,
Its mean square deviation formula is as follows：
Wherein,Represent vibration level predicted value, ViVibration level observed value is represented, n is the quantity of vibration level observed value.
Due to taking above technical scheme, it has advantages below to the present invention：The present invention first passes through collection track irregularity
The parameter of the parameter of amplitude, the parameter of foundation soil property, the parameter of train speed, the parameter of type of train and depth of building is entered
Row normalized, then selects dbN wavelet functions and decomposition scale to carry out wavelet transformation, eliminates the mutation in primary signal
Factor and Random Effect, by reconstruct obtain de-noising after signal, and using the signal after de-noising as SVMs input
Variable, for the training test of SVMs, finally gives the SVM forecast models of demarcation and draws significantly improving track traffic
The precision of the vibration of building horizontal forecast for rising, is the vibration effect evaluation and vibration and noise reducing measure of Urban Rail Transit Development
Selection is supported there is provided data, for improvement urban work living environment is made that important contribution.Therefore, the present invention can be extensive
For civil engineering electric powder prediction.
Brief description of the drawings
Fig. 1 is process schematic of the invention
Fig. 2 is Train Track-roadbed-surrounding formation-contact surface-building system model schematic of the present invention
Fig. 3 is the test site floor map that embodiments of the invention are used
Fig. 4 is the wavelet noise process schematic that the present invention is successively decomposed
Fig. 5 is directed to embodiment carries out three layers of wavelet noise process schematic of decomposition
Fig. 6 is the actual measurement average value comparison diagram of the predicted value and vibration of building obtained using the present invention
Specific embodiment
Below in conjunction with the accompanying drawings and instantiation, the present invention is furture elucidated, it should be understood that these examples are merely to illustrate this hair
Bright rather than limitation the scope of the present invention, after the present invention has been read, those skilled in the art are to of the invention various etc.
The modification of valency form falls within the application appended claims limited range.
As shown in figure 1, the vibration of building horizontal forecast method that a kind of track traffic of the invention causes, it includes following step
Suddenly：
1) as shown in Fig. 2 carrying out initial data investigation for Train Track-roadbed-surrounding formation-building system, should
Initial data includes parameter, the parameter of foundation soil property, the parameter of train speed, the ginseng of type of train of track irregularity amplitude
The parameter of number and depth of building, wherein foundation soil property include foundation soil property damping ratio and foundation soil shear wave velocity.
In this example, in test site floor map as shown in Figure 3, test site is located at capital-wide line Shijiazhuang
Near, subjects are the floor masonry residential building of a building 6, building edge and nearest interorbital distance only 14m, ability
Data of the field technique personnel according to provided in Fig. 2 and Fig. 3, corresponding original can be just obtained according to conventional method of data capture
Beginning data, are not detailed herein.
2) each parameter in initial data is normalized, and obtains each between 0 and 1 after normalized
Parameter, it is to avoid because initial data exist dimension or certain one-dimensional data it is excessive caused by parameter calibration it is inaccurate so that final SVM
Model prediction resultant error is larger.
The formula that each parameter in initial data is normalized one by one is as follows：
Wherein,It is the value after normalized, SiIt is raw value, SminIt is the minimum value in sample sequence, SmaxIt is sample
Maximum in this sequence.Because all parameters are processed using formula (1) in initial data, therefore no longer area one by one
Point.
3) by normalized after each parameter carry out N layers of wavelet transformation respectively and decompose, each layer of each parameter is right respectively
Should resolve into a high-frequency signal A (N) and N number of low frequency signal D (1), D (2) ..., D (N), i.e., each layer obtains a high frequency letter
Number A (N) and N number of low frequency signal D (1), D (2) ..., D (N), so as to primary signal to be resolved into a high-frequency signal and many respectively
Individual low frequency signal；
As shown in figure 4, in this example：N is the series (number of plies) that wavelet transformation is decomposed；As N=1, after de-noising
Track irregularity amplitude sequence indention, occur in that step phenomenon, differed greatly with original track irregularity amplitude signal, no
The fluctuating factor that can reflect in signal；Work as N>When 5, it is evident that it can be seen that by the track irregularity amplitude letter after denoising Processing
Number image lost the part validity feature of original track irregularity amplitude sequence by excess smoothness；As N=2 and N=4, disappear
Sequence has larger difference with the part stage of original series after making an uproar；In N=3, the figure for being obtained can be with relatively good reflection
The fluctuation characteristic of track irregularity amplitude signal.
4) low frequency signal and high-frequency signal for being obtained for each parameter carry out denoising Processing, remove abnormal data, so that
Improve the precision of SVM model predictions；
The low frequency signal and high-frequency signal obtained for each parameter carry out denoising Processing, and its process is as follows：Assuming that one
The model of the one-dimensional signal (treating the signal of denoising) of Noise is as follows：
S (k)=f (k)+λ e (k) k=0,1 ..., N-1 (2)
Wherein, f (k) is the useful signal after denoising, and s (k) is noisy signal, and e (k) is the noise letter of the signal of denoising
Number, λ is weight.
Using wthresh (x, h, t) function in Matlab (Matrix＆Laboratory, matrix factory), signal is set to
Threshold values is processed for the threshold value of t, and wherein x is the matrix of threshold value setting to be carried out, and h represents threshold values selection rule for hard threshold values, t
Take famous threshold values formBecause series (number of plies) is identical with low, the high frequency total number after decomposing, therefore public
In formula N represent each parameter carry out wavelet decomposition after low, high frequency total number so that included in rejecting noisy each parameter with
Machine Mutagen, removes noise jamming, obtains the effective low, high-frequency signal of each parameter.
5) will be combined by the corresponding low frequency signal of each parameter after denoising Processing and multiple high-frequency signals respectively
The Weight of its decomposition scale is added and completes signal reconstruction, each signal for being weighted；
In the present embodiment, the process of signal reconstruction is as shown in figure 5, signal reconstruction is the conventional skill of those skilled in the art
Art means, therefore no longer describe in detail.
6) gridding method is passed through to core based on each signal for weighting as the kernel function of SVM models using Radial basis kernel function
Regularization term parameter C and error term ε in function are demarcated, and the span of C is (0,100), the span of ε for (0,
0.4), so as to the SVM models demarcated；
In above-described embodiment, each signal of 70% weighting is typically taken as the training sample of SVM models, for demarcating rule
Parameter C and error term ε, whether remaining is 30% correct as test sample inspection SVM models, and generally using mean square deviation to surveying
Test result evaluate the precision of prediction of SVM models, and its mean square deviation formula is as follows：
Wherein,Represent vibration level predicted value, ViVibration level observed value is represented, n is the quantity of vibration level observed value.
In the present embodiment, regularization term parameter C is that 3.9821 and error term ε is 0.0064.
In order to verify effectiveness of the invention, as shown in fig. 6, actual measurement average value is contrasted with the situation of predicted value,
Vibration level level and actually measure the vibration level level for obtaining very close to compared with it can objectively respond the soil body-building between that the present invention is obtained
The propagation law of vibration, with precision higher, it was demonstrated that the vibration of building that wavelet support vector machines cause in track traffic
Feasibility on horizontal forecast.
In sum, the present invention is first passed through and collects track irregularity amplitude, foundation soil property, train speed, type of train,
Depth of building data, then select wavelet function and decomposition scale to carry out wavelet transformation, eliminate the mutation in primary signal
Factor and Random Effect, the signal after reconstruct obtains de-noising.The input of the signal after de-noising as SVMs is become
Amount, for the training test of SVMs, finally gives reliable forecast model.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all it is of the invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc. should be included within the scope of the present invention.
Claims (1)
1. a kind of vibration of building horizontal forecast method that track traffic causes, it is comprised the following steps：
1) initial data investigation is carried out for Train Track-roadbed-surrounding formation-building system, the initial data includes rail
The parameter of road irregularity amplitude, the parameter of foundation soil property, the parameter of train speed, the parameter of type of train and depth of building
Parameter；
2) each parameter in initial data is normalized, and obtains each parameter after normalized, by initial data
In the formula that is normalized one by one of each parameter it is as follows：
Wherein,It is the value after normalized, SiIt is raw value, SminIt is the minimum value in sample sequence, SmaxIt is sample sequence
Maximum in row；
3) by normalized after each parameter carry out respectively successively wavelet transformation decompose, by each layer of each parameter respectively correspond to point
Solution is into low frequency signal and multiple high-frequency signals；
4) low frequency signal and high-frequency signal for being obtained for each parameter carry out denoising Processing, remove abnormal data, and its process is such as
Under：Assuming that the model of an one-dimensional signal for Noise is as follows：
S (k)=f (k)+λ e (k) k=0,1 ..., N-1
Wherein, f (k) is the useful signal after denoising, and s (k) is noisy signal, and e (k) is the noise signal of the signal of denoising, λ
Be weight, N represent each parameter carry out wavelet decomposition after low, high frequency total number；
5) its point will be combined by corresponding the low frequency signal of each parameter after denoising Processing and multiple high-frequency signals respectively
The Weight for solving yardstick is added completion signal reconstruction, each signal for being weighted；
6) each signal of 70% weighting is taken as the training of SVM models as the kernel function of SVM models using Radial basis kernel function
Sample, is (0,100) for demarcating the span of regularization term parameter C and error term ε, C, and the span of ε is (0,0.4),
Whether remaining is 30% correct as test sample inspection SVM models, and test result is carried out using mean square deviation evaluate SVM models
Precision of prediction, its mean square deviation formula is as follows：
Wherein,Represent vibration level predicted value, ViVibration level observed value is represented, n is the quantity of vibration level observed value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410529094.1A CN104299048B (en) | 2014-10-09 | 2014-10-09 | A kind of vibration of building horizontal forecast method that track traffic causes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410529094.1A CN104299048B (en) | 2014-10-09 | 2014-10-09 | A kind of vibration of building horizontal forecast method that track traffic causes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104299048A CN104299048A (en) | 2015-01-21 |
| CN104299048B true CN104299048B (en) | 2017-06-16 |
Family
ID=52318769
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410529094.1A Expired - Fee Related CN104299048B (en) | 2014-10-09 | 2014-10-09 | A kind of vibration of building horizontal forecast method that track traffic causes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104299048B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106092015B (en) * | 2016-05-27 | 2018-07-03 | 南京理工大学 | A kind of raceway surface recess length detecting method |
| CN109594669B (en) * | 2018-11-07 | 2020-06-12 | 北京市劳动保护科学研究所 | Method for reducing influence of rail traffic vibration on existing building and vibration-damping building |
| CN115983500B (en) * | 2023-03-06 | 2023-05-30 | 中国科学院空天信息创新研究院 | Method and device for predicting desert locusts |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101697175B (en) * | 2009-10-26 | 2011-08-10 | 华东交通大学 | Simulated prediction method for rail transit noise |
| CN102912696B (en) * | 2011-08-03 | 2014-10-15 | 北京市劳动保护科学研究所 | Construction prediction method of subway environment vibration |
-
2014
- 2014-10-09 CN CN201410529094.1A patent/CN104299048B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN104299048A (en) | 2015-01-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103197299B (en) | Extraction and quantitative analysis system of weather radar radial wind information | |
| CN105424366A (en) | Bearing fault diagnosis method based on EEMD adaptive denoising | |
| CN104299048B (en) | A kind of vibration of building horizontal forecast method that track traffic causes | |
| Zhang et al. | Onset detection of ultrasonic signals for the testing of concrete foundation piles by coupled continuous wavelet transform and machine learning algorithms | |
| Ruggiero et al. | Determining environmental noise measurement uncertainty in the context of the Italian legislative framework | |
| CN111880157A (en) | Method and system for detecting target in radar image | |
| CN107516082A (en) | Based on the SAR image change region detection method from step study | |
| Xiong et al. | A novel deep convolutional image-denoiser network for structural vibration signal denoising | |
| CN107885927A (en) | A kind of railroad bridge operation state method for early warning | |
| Ashton et al. | On errors in low frequency wave measurements from wave buoys | |
| CN104931040A (en) | Installation and debugging method of Beidou generation-II navigation system electric iron tower deformation monitoring device based on machine learning | |
| CN102073867A (en) | Sorting method and device for remote sensing images | |
| Abdelrahman et al. | Signal processing techniques for filtering acoustic emission data in prestressed concrete | |
| CN115758289A (en) | Rail corrugation identification method based on multitask learning neural network | |
| CN114371009A (en) | High-speed train bearing fault diagnosis method based on improved random forest | |
| Lee et al. | A sustainability evaluation of government‐led urban renewal projects | |
| CN117351321A (en) | Single-stage lightweight subway lining cavity recognition method and related equipment | |
| CN116484258A (en) | Elevator traction machine bearing fault diagnosis method | |
| Sharma et al. | NGFS rainfall forecast verification over India using the contiguous rain area (CRA) method | |
| CN103376465A (en) | System and method for earthquake real-time analysis of building floor and storage medium | |
| Lin et al. | On the improvement of ASCAT wind data assimilation in global NWP | |
| Syerrina et al. | Explorative spatial analysis of coastal community incomes in Setiu Wetlands: Geographically weighted regression | |
| Tian et al. | An Internal Defect Detection Algorithm for Concrete Blocks Based on Local Mean Decomposition-Singular Value Decomposition and Weighted Spatial-Spectral Entropy | |
| CN114878691B (en) | Data enhancement method for intelligent detection and multi-classification of rail corrugation | |
| Roshni et al. | Modelling land surface temperature using gamma test coupled wavelet neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170616 Termination date: 20181009 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |