CN112185482A - GBDT model-based water quality characteristic mineral water classification method - Google Patents
GBDT model-based water quality characteristic mineral water classification method Download PDFInfo
- Publication number
- CN112185482A CN112185482A CN202011090036.5A CN202011090036A CN112185482A CN 112185482 A CN112185482 A CN 112185482A CN 202011090036 A CN202011090036 A CN 202011090036A CN 112185482 A CN112185482 A CN 112185482A
- Authority
- CN
- China
- Prior art keywords
- gbdt model
- data
- mineral water
- water quality
- water
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Chemical & Material Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a water quality characteristic mineral water classification method based on a GBDT model, which comprises the following steps: collecting a water sample in a mineral water source; testing the water quality information of each group of water samples; establishing an Excel table by utilizing a plurality of groups of water quality information, and importing an R language; reducing the dimension of the data by using a principal component analysis method to obtain dimension reduction data; classifying the dimension reduction data by using a Gaussian mixture model to obtain classified data; marking the classified data, and selecting a plurality of groups of marking data which can be effectively distinguished; marking a plurality of groups of data according to the following steps of 7: 3 into a training data set and a test data set; performing feature selection on the training data set; establishing a GBDT model; and (4) using the GBDT model for testing the data set, and evaluating the accuracy of the GBDT model. According to the water quality characteristic mineral water classification method based on the GBDT model, the rationality and the scientificity of mineral water classification are improved.
Description
Technical Field
The invention relates to the technical field of mineral water classification, in particular to a water quality characteristic mineral water classification method based on a GBDT model.
Background
Mineral water is a precious water resource, and is beneficial to human bodies and suitable for long-term drinking, so that the mineral water has a great resource protection value and an economic value. The mineral water is mainly dissolved in inorganic substances, wherein the macroelement comprises K+、Na+、Ca2+、Mg2+、Cl-、SO42-、HCO3 -And the like,important trace elements include Se, Sr, Li, Zn, etc. These components represent the difference of water quality on one hand, and the difference of formation conditions and formation processes on the other hand, and are related to the geological conditions of the underground aquifer where the components are located.
The global mineral water sales increased at a rate of 6.4% per year in the last five years. The government of China promulgates the national standard of 'Natural mineral Water for drinking' (GB 8537-2018), and makes some regulations on the water quality of mineral water. From the viewpoint of current research and general acceptance, mineral water is roughly classified into metasilicic acid mineral water, strontium mineral water, zinc mineral water, lithium mineral water, selenium mineral water, bromine mineral water, iodine mineral water, carbonated mineral water, and the like. The classification method only inspects the characteristics of a certain aspect of the mineral water, but the inspection is not comprehensive and the classification is not reasonable.
The resource distribution of mineral water is regular. By establishing a classification model of mineral water, the method is helpful for more scientifically and effectively managing mineral water resources, guiding the public to reasonably identify and select the mineral water required by the public, and simultaneously has a basic guiding function for further analysis of the mineral water.
Disclosure of Invention
The invention provides a water quality characteristic mineral water classification method based on a GBDT model, which can improve the rationality and scientificity of mineral water classification.
The water quality characteristic mineral water classification method based on the GBDT model comprises the following steps: step S1: selecting more than three mineral water source places with certain distances, and collecting water samples in the mineral water source places, wherein the number of the water samples is at least 60 groups, and each water source place is not less than 20 groups; step S2: testing the water quality information of each group of water samples, wherein the water quality information comprises the content of macroelements, the content of trace elements, the pH value, total soluble solids, the value and the hardness of isotopes; step S3: establishing an Excel table by utilizing a plurality of groups of water quality information, converting the Excel table into a CSV table, and importing the CSV table into an R language; step S4: reducing the dimension of the data by using a principal component analysis method to obtain dimension reduction data; step S5: classifying the dimensionality reduction data by using a Gaussian mixture model to obtain classified data; step S6: marking the classified data, and selecting a plurality of groups of marking data which can be effectively distinguished; step S7: importing a plurality of groups of the mark data into an R language and according to 7: 3 into a training data set and a test data set; step S8: selecting characteristics of the training data set by adopting a random forest method, and selecting 3-6 parameters; step S9: applying the GBDT model framework to the training data set after the feature selection for training, and establishing a GBDT model; step S10: applying the GBDT model to the test data set, evaluating the GBDT model for correctness, and refining the GBDT model.
According to the water quality characteristic mineral water classification method based on the GBDT model, in consideration of the difference of the importance of each discrimination parameter, the data is subjected to characteristic selection by using a principal component analysis method and a Gaussian mixture model, namely more representative data can be selected from the angle of a sample, and then R language is used for selecting the data according to the ratio of 7: and 3, dividing the ratio into a training data set and a testing data set, using the training data set to establish a GBDT model, using the GBDT model for the testing data set, evaluating the accuracy of the GBDT model, and improving the GBDT model, so that the accuracy of the GBDT model can be improved, and the rationality and the scientificity of mineral water classification are further improved.
According to some embodiments of the invention, after the step S2, and before the step S3, the method further comprises: and converting the content of the macroelements into equivalent concentration percentage, and converting the content of the trace elements into equivalent concentration.
According to some embodiments of the invention, the step S4 is performed in the psych package of the R language.
In some embodiments of the invention, the dimension of the dimension reduction data is 2-4.
According to some embodiments of the invention, said step S5 is done in the mcust package of said R language.
According to some embodiments of the invention, the tag data selected in the step S6 is 3-5 sets.
According to some embodiments of the invention, the building of the GBDT model is done in gbm package in the R language.
According to some embodiments of the invention, after the step S10, the method further comprises: the GBDT model is used for verification of actual mineral water.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
Fig. 1 is a flowchart of a water quality characteristic mineral water classification method based on a GBDT model according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
The following disclosure provides many different embodiments, or examples, for implementing different features of the invention. To simplify the disclosure of the present invention, the components and arrangements of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. Furthermore, the present invention may repeat reference numerals and/or letters in the various examples. This repetition is for the purpose of simplicity and clarity and does not in itself dictate a relationship between the various embodiments and/or configurations discussed. In addition, the present invention provides examples of various specific processes and materials, but one of ordinary skill in the art may recognize the applicability of other processes and/or the use of other materials.
A water quality characteristic mineral water classifying method based on a GBDT model according to an embodiment of the present invention will be described with reference to the accompanying drawings.
As shown in fig. 1, a GBDT model-based water quality characteristic mineral water classification method according to an embodiment of the present invention includes: step S1, step S2, step S3, step S4, step S5, step S6, step S7, step S8, step S9, and step S10.
Specifically, as shown in fig. 1, in step S1, more than three mineral water sources are selected at a certain distance, and water samples are collected at the mineral water sources, the number of the water samples is at least 60 groups, and each mineral water source is not less than 20 groups. It is understood that the number of water samples may be 60, 70, 80 or more. Therefore, the number of samples can be increased, and the accuracy of the model is improved.
As shown in fig. 1, in step S2, water quality information of each group of water samples is tested, and the water quality information includes content of macroelements, content of trace elements, pH value, total soluble solids, and isotope value and hardness.
It can be understood that the values and the hardness of the macroelement content, the trace element content, the pH value, the total soluble solid and the isotope of different types of water samples are different, and more classification bases can be provided for the classification of the water samples through the analysis of the values and the hardness of the macroelement content, the trace element content, the pH value, the total soluble solid and the isotope.
As shown in fig. 1, in step S3, an Excel table is created by using multiple sets of water quality information, the Excel table is converted into a CSV table, and the CSV table is imported into the R language.
As shown in fig. 1, in step S4, dimension reduction is performed on the data by using a principal component analysis method to obtain dimension reduced data; step S5, classifying the dimension reduction data by using a Gaussian mixture model to obtain classified data; step S6, labeling the classified data, selecting multiple groups of labeled data which can be effectively distinguished; step S7 is to import multiple sets of markup data into the R language and to perform the following steps according to 7: 3 into a training data set and a test data set; step S8, selecting 3-6 parameters for feature selection of the training data set by a random forest method; step S9, the GBDT model framework is applied to the training data set after the feature selection for training, and a GBDT model is established; step S10 is to use the GBDT model for the test data set, evaluate the GBDT model for correctness, and refine the GBDT model. In one example of the present invention, the above-described building of the GBDT model is done in the gbm package of the R language.
According to the water quality characteristic mineral water classification method based on the GBDT model, in consideration of the difference of the importance of each discrimination parameter, the data is subjected to characteristic selection by using a principal component analysis method and a Gaussian mixture model, namely more representative data can be selected from the angle of a sample, and then R language is used for selecting the data according to the ratio of 7: 3, the GBDT model is used for testing the data set after the GBDT model is established by using the training data set, the accuracy of the GBDT model is evaluated, and the GBDT model is improved, so that the accuracy of the GBDT model can be improved, and the rationality and the scientificity of mineral water classification are further improved.
According to some embodiments of the invention, after step S2, and before step S3, the method further comprises: the content of the macroelements is converted into the percentage of equivalent concentration, and the content of the microelements is converted into the equivalent concentration. Therefore, the calculation difficulty can be reduced, the calculation efficiency is improved, and the calculation time is saved. The pH, total soluble solids, isotope values and hardness remain unchanged from the original units.
According to some embodiments of the invention, step S4 is accomplished using the psych package in the R language. Therefore, time can be saved, and accuracy of results can be improved.
Specifically, in one example of the present invention, CSV table data is imported into the R language, and the dimension of the data is reduced by a principal component analysis method, and the calculation method is as follows, and a psych package in the R language is used for calculation.
(1) And centralize data X in columns.
(2) And calculating a covariance matrix C of the sample matrix.
(3) And solving the eigenvalue and the eigenvector of the covariance matrix C of the sample set matrix X.
(4) And constructing a dimension reduction conversion matrix U. And (3) setting n variables in the original data, reducing the dimension of the data to m variables (m < n) according to the requirement (geochemical professional analysis) or a calculation result (covariance matrix), and forming a dimension reduction conversion matrix U by using eigenvectors corresponding to m eigenvalues before ranking according to the size arrangement.
(5) And obtaining a dimension reduction matrix Z of X by using the dimension reduction conversion formula Z as XU, wherein the matrix represents the information of the original data set by using lower dimension (variable).
In some embodiments of the invention, the dimensionality of the dimension reduction data is 2-4. Therefore, the calculation difficulty can be reduced while the result accuracy is ensured, the calculation efficiency is improved, and the calculation time is saved. For example, in one example of the invention, the dimensionality of the dimension reduction data is 2, 3, or 4.
According to some embodiments of the invention, step S5 is accomplished in the mCluster package in the R language. Therefore, time can be saved, and accuracy of results can be improved.
Specifically, in one example of the present invention, the data after dimension reduction is classified by a Gaussian Mixture Model (GMM), and the calculation method is as follows:
(1) and setting each group of water sample data to accord with Gaussian distribution, wherein the distribution function is shown as a formula (2-a):
where K is the number of classifications, πkIs the coefficient of mixing, μkTo expect, sigmakIs a covariance matrix, representing the probability that each sample belongs to the m (m-1, 2, …, k) th group,
(2) and the joint probability of the sample set X (n sample points) is shown as the formula (2-b):
(3) and the log-likelihood function is shown as formula (2-c):
and solving the value of mu, sigma, pi and k in the model by using an EM algorithm.
According to some embodiments of the invention, the tag data selected in step S6 are 3-5 sets. Therefore, the calculation difficulty can be reduced while the result accuracy is ensured, the calculation efficiency is improved, and the calculation time is saved. For example, in one example of the present invention, the marker data is 3 groups, 4 groups, or 5 groups. In an example of the present invention, in step S8, for convenience of use, constant elements are used as the characteristic parameters for modeling, and trace elements with distinct characteristics may be used as the characteristic parameters for modeling. The steps of feature selection are as follows:
(1) and setting the data set X to contain N samples, and randomly taking the N samples from the data set by using a self-service method (Bootstrap) and bagging the samples to serve as a training data set. In this process, the probability that each sample is not selected is p ═ 1-1/NN. When N tends to + ∞, p ≈ 0.37. This indicates that about 37% of the samples were not selected during bootstrap sampling, referred to as out-of-bag data (OOB). The in-bag data was used to train the model and the out-of-bag data was used to evaluate the model.
(2) And performing extraction for k times, so that k training data sets can be obtained. A decision tree is built with each training data set using a pruning-free approach. At the position of each node, M features are randomly selected from the total number M of features, the Gini index of each feature in the M features is calculated, the smaller the Gini index is, the better the distinguishing effect of the features is, and the optimal feature is selected as the branch node. A complete decision tree is built according to this strategy.
(3) And k decision trees can be obtained by using k data sets to form a random forest model. The quality of the model can be evaluated with the prediction accuracy of the out-of-bag data (OOB). Mean Square Error (MSE) of out-of-bag dataOOB) And a coefficient of determination (R)RF 2) Such as equations (1-a) and (1-b), where the smaller the mean square error, the larger the decision coefficient, indicating that the model is superior.
Where n is the number of data outside the bag, yiIs an observed value of the data outside the bag,is the predicted value of the model,is the out-of-bag data prediction variance.
(4) Selecting an important predictive feature using the average impure reduction value. And (3) calculating the Gini index of each variable by applying a formula (1-c) at each node of each tree, calculating the Gini index of each characteristic on each node of each tree, averaging all the Gini indexes according to the characteristics, and calculating the average impure degree reduction value. Each feature is then ranked so that the importance of the features in the model can be scored to select the appropriate feature to model.
Where pi is the probability that a sample belongs to the ith branch, N is the total number of branches at the node, and IGini is the Gini index. Important variables are determined by integrating the analysis method of the random forest and the analysis of the geochemistry for modeling, the important variables are mainly selected from macroelements, and are assisted by microelements, isotopes and other parameters, and the number of the important variables is generally 3-6.
It should be noted that, during modeling, a plurality of parameters need to be set and optimized, and the main parameters to be optimized include the maximum depth of the tree, the learning rate, the number of kernels used in parallel computation, the cycle number, the proportion of training samples, the classification number, and the like. For example, there are 3-6 variables in the model, and the parameters can be optimized to be 2 or 3. The optimization of specific parameters also needs to be determined according to the discriminant performance of the model. The GBDT model is substituted back to analyze the misjudged data, and it should be noted that, unless an error is obvious, the data in the training data set is not deleted, and if a part of the data is deleted, the data needs to be trained again.
The steps of applying the GBDT algorithm to establish the machine learning model are as follows:
(1) initializing a loss function
Where N is the number of data in the dataset, y represents the predicted value, c represents the predicted value for the baseline model (2) versus M1, 2, …, M (M is the number of rounds trained)
(2.1) for i equal to 1,2, …, N (N is the number of data), calculate
The type of computation in this example is classification, so the loss function is determined by the misinterpretation, which has a negative gradient, rmiIs composed of
(2.2) to rmiFitting a regression tree to obtain leaf node regions R of the mth treemjWhere J is 1,2, …, J is the complexity of the regression tree, expressed as the number of leaf nodes
(2.3) for J equal to 1,2, …, J, calculate
Wherein R ismjIs the leaf node region of the regression water, and c is the predicted target value of the leaf node
(2.4) update
Wherein I is an indication function (if the condition is satisfied, return to 1, otherwise 0)
(3) Obtaining the final model
It should be noted that, in step S10, the model is replaced and the misjudged data is analyzed, and unless an error is obvious, the data in the training data set is not deleted, and if a part of the data is deleted, the data needs to be trained again. According to some embodiments of the invention, after step S10, the method further comprises: the GBDT model is used for verification of actual mineral water (step S11). Thus, the accuracy of the GBDT model can be further verified using real mineral water. In an example of the present invention, the model is adaptively modified according to the detection result, so that the reliability of the detection result can be further improved.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (8)
1. A water quality characteristic mineral water classification method based on a GBDT model is characterized by comprising the following steps:
step S1: selecting more than three mineral water source places with certain distances, and collecting water samples in the mineral water source places, wherein the number of the water samples is at least 60 groups, and each water source place is not less than 20 groups;
step S2: testing the water quality information of each group of water samples, wherein the water quality information comprises the content of macroelements, the content of trace elements, the pH value, total soluble solids, the value and the hardness of isotopes;
step S3: establishing an Excel table by utilizing a plurality of groups of water quality information, converting the Excel table into a CSV table, and importing the CSV table into an R language;
step S4: reducing the dimension of the data by using a principal component analysis method to obtain dimension reduction data;
step S5: classifying the dimensionality reduction data by using a Gaussian mixture model to obtain classified data;
step S6: marking the classified data, and selecting a plurality of groups of marking data which can be effectively distinguished;
step S7: importing a plurality of groups of the mark data into an R language and according to 7: 3 into a training data set and a test data set;
step S8: selecting characteristics of the training data set by adopting a random forest method, and selecting 3-6 parameters;
step S9: applying the GBDT model framework to the training data set after the feature selection for training, and establishing a GBDT model;
step S10: applying the GBDT model to the test data set, evaluating the GBDT model for correctness, and refining the GBDT model.
2. The GBDT model-based water quality feature mineral water classification method of claim 1, after the step S2 and before the step S3, the method further comprising: and converting the content of the macroelements into equivalent concentration percentage, and converting the content of the trace elements into equivalent concentration.
3. The GBDT model-based water quality feature mineral water classification method according to claim 1, wherein the step S4 is done in the psych package in the R language.
4. The GBDT model-based water quality characteristic mineral water classification method of claim 3, wherein the dimensionality of the dimensionality reduction data is 2-4.
5. The GBDT model-based water quality feature mineral water classification method according to claim 1, characterized in that the step S5 is done in the R language mcrustt package.
6. The GBDT model-based water quality indicator mineral water classification method according to claim 1, wherein the labeled data selected in step S6 is 3-5 groups.
7. The GBDT model-based water quality feature mineral water classification method of claim 1, wherein the GBDT model building is done in gbm package in the R language.
8. The GBDT model-based water quality feature mineral water classification method of claim 1, after the step S10, the method further comprising: the GBDT model is used for verification of actual mineral water.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011090036.5A CN112185482A (en) | 2020-10-13 | 2020-10-13 | GBDT model-based water quality characteristic mineral water classification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011090036.5A CN112185482A (en) | 2020-10-13 | 2020-10-13 | GBDT model-based water quality characteristic mineral water classification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112185482A true CN112185482A (en) | 2021-01-05 |
Family
ID=73949567
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011090036.5A Withdrawn CN112185482A (en) | 2020-10-13 | 2020-10-13 | GBDT model-based water quality characteristic mineral water classification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112185482A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113252730A (en) * | 2021-04-01 | 2021-08-13 | 青海湘和有色金属有限责任公司 | Method for detecting water hardness and trace elements in sewage |
-
2020
- 2020-10-13 CN CN202011090036.5A patent/CN112185482A/en not_active Withdrawn
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113252730A (en) * | 2021-04-01 | 2021-08-13 | 青海湘和有色金属有限责任公司 | Method for detecting water hardness and trace elements in sewage |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113919448B (en) | Method for analyzing influence factors of carbon dioxide concentration prediction at any time-space position | |
Gerwin et al. | Assessment and quantification of marginal lands for biomass production in Europe using soil-quality indicators | |
Bollen et al. | National industrial structure and the global system | |
CN109765559B (en) | A kind of mountain area disastrous rainstorm recognition methods based on Doppler radar and deep learning | |
CN103632168B (en) | Classifier integration method for machine learning | |
CN112700325A (en) | Method for predicting online credit return customers based on Stacking ensemble learning | |
CN111967712B (en) | Traffic risk prediction method based on complex network theory | |
CN104966105A (en) | Robust machine error retrieving method and system | |
CN108985327A (en) | A kind of Terrain Matching self-organizing Optimum Classification method based on factorial analysis | |
CN105809360A (en) | P2P industry risk assessment method | |
Ju et al. | Source identification of mine water inrush based on principal component analysis and grey situation decision | |
Mayer et al. | A random forest model to assess snow instability from simulated snow stratigraphy | |
CN111797188B (en) | Urban functional area quantitative identification method based on open source geospatial vector data | |
Montagna et al. | A bayesian approach for the use of athlete performance data within anti-doping | |
CN105868906A (en) | Optimized method for analyzing maturity of regional development | |
CN109492230A (en) | A method of insurance contract key message is extracted based on textview field convolutional neural networks interested | |
CN114821340A (en) | Land utilization classification method and system | |
CN104835073A (en) | Unmanned aerial vehicle control system operation performance evaluating method based on intuitionistic fuzzy entropy weight | |
CN102194134A (en) | Biological feature recognition performance index prediction method based on statistical learning | |
CN112185482A (en) | GBDT model-based water quality characteristic mineral water classification method | |
CN105243503A (en) | Coastal zone ecological safety assessment method based on space variables and logistic regression | |
CN111191935A (en) | Evaluation and assessment system and method | |
CN112185483A (en) | SVM (support vector machine) model-based water quality characteristic mineral water classification method | |
CN112185484A (en) | AdaBoost model-based water quality characteristic mineral water classification method | |
Armstrong et al. | The application of data mining techniques to characterize agricultural soil profiles. |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210105 |
|
WW01 | Invention patent application withdrawn after publication |