CN117349731A - Intelligent supervision system and method for river water pollution restoration process - Google Patents
Intelligent supervision system and method for river water pollution restoration process Download PDFInfo
- Publication number
- CN117349731A CN117349731A CN202311489868.8A CN202311489868A CN117349731A CN 117349731 A CN117349731 A CN 117349731A CN 202311489868 A CN202311489868 A CN 202311489868A CN 117349731 A CN117349731 A CN 117349731A
- Authority
- CN
- China
- Prior art keywords
- water quality
- feature vector
- vector
- differential
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 95
- 230000008569 process Effects 0.000 title claims abstract description 72
- 238000003903 river water pollution Methods 0.000 title claims abstract description 58
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 322
- 230000000694 effects Effects 0.000 claims abstract description 35
- 238000011156 evaluation Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims description 198
- 238000001514 detection method Methods 0.000 claims description 57
- 238000005067 remediation Methods 0.000 claims description 56
- 238000012545 processing Methods 0.000 claims description 27
- 238000010606 normalization Methods 0.000 claims description 21
- 238000000605 extraction Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 description 13
- 238000010586 diagram Methods 0.000 description 10
- 238000003860 storage Methods 0.000 description 10
- 230000008859 change Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000011161 development Methods 0.000 description 6
- 230000018109 developmental process Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 4
- 230000008439 repair process Effects 0.000 description 4
- 241000282414 Homo sapiens Species 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000006866 deterioration Effects 0.000 description 2
- 239000013505 freshwater Substances 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000003651 drinking water Substances 0.000 description 1
- 235000020188 drinking water Nutrition 0.000 description 1
- 230000035876 healing Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000008235 industrial water Substances 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F1/00—Treatment of water, waste water, or sewage
- C02F1/008—Control or steering systems not provided for elsewhere in subclass C02F
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
- G06F18/15—Statistical pre-processing, e.g. techniques for normalisation or restoring missing data
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Hydrology & Water Resources (AREA)
- Water Supply & Treatment (AREA)
- Probability & Statistics with Applications (AREA)
- Environmental & Geological Engineering (AREA)
- Chemical & Material Sciences (AREA)
- Organic Chemistry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to the field of intelligent evaluation, and particularly discloses an intelligent supervision system and an intelligent supervision method for a river water pollution restoration process. Therefore, the restoration effect of the water quality in the restoration process can be known in time, and when the restoration effect of the water quality is not obvious, restoration measures are adjusted in time so as to achieve more obvious restoration effect.
Description
Technical Field
The application relates to the field of intelligent evaluation, and more particularly, to an intelligent supervision system and method for river water pollution remediation process.
Background
Rivers are an integral part of the ecosystem and they foster a rich biodiversity, the health of which has a critical impact on maintaining the living environment of aquatic organisms, the balance of the food chain and the stability of the ecosystem. The interest in river ecology helps to protect and restore the natural state of the river, maintain the integrity of biodiversity, protect the species that are endangered and extinct, and help to promote the stable and sustainable development of the ecosystem. In addition, rivers are also an important source of fresh water resources, meeting the demands of human beings in aspects of drinking water, agricultural irrigation, industrial water and the like. However, many rivers face problems of deterioration of water quality due to excessive development, pollution, and climate change. Therefore, restoring the water quality of the river helps to ensure sustainable supply of water resources and meets the living demands of human beings.
In the river water pollution restoration process, the existing supervision mode relies on a supervision mechanism to perform regular water quality monitoring and evaluation so as to know the condition and restoration effect of river water quality. The supervision mode is low in efficiency, and the environment change condition of the water quality data cannot be mastered in real time, so that the development of a repair process is not facilitated, and the repair effect is affected.
Therefore, an optimized intelligent supervision scheme for the river water pollution restoration process is needed.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides an intelligent supervision system and method for a river water pollution restoration process, which adopts an artificial intelligent monitoring technology based on deep learning to evaluate the water restoration effect by monitoring the turbidity, suspended matters and hardness of restored water. Therefore, the restoration effect of the water quality in the restoration process can be known in time, and when the restoration effect of the water quality is not obvious, restoration measures are adjusted in time so as to achieve more obvious restoration effect.
According to one aspect of the present application, there is provided a river water body pollution remediation process intelligent supervision system, comprising:
the water quality data acquisition module is used for acquiring water quality detection data at a first time point and water quality detection data at a second time point, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality;
The first water quality characteristic extraction module is used for enabling the water quality detection data at the first time point to pass through a first water quality data semantic context encoder to obtain a first water quality characteristic vector;
the first water quality feature normal normalization processing module is used for calculating normal normalization values of feature values of all positions in the first water quality feature vector to obtain a first normal normalized water quality feature vector;
the second water quality characteristic extraction module is used for enabling the water quality detection data at the second time point to pass through a second water quality data semantic context encoder to obtain a second water quality characteristic vector;
the second water quality characteristic normal normalization processing module is used for calculating normal normalization values of characteristic values of all positions in the second water quality characteristic vector to obtain a second normal normalized water quality characteristic vector;
the water quality data difference calculation module is used for carrying out difference operation on the first normal normalized water quality characteristic vector and the second normal normalized water quality characteristic vector to obtain a difference characteristic vector;
the optimization module is used for carrying out prior order-based feature engineering parameterization on the differential feature vectors so as to obtain optimized differential feature vectors;
And the water quality restoration effect evaluation module is used for enabling the optimized differential feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether water quality restoration is effective or not.
In the above-mentioned river water body pollution restoration process intelligent supervisory system, the first water quality feature extraction module includes: the first word segmentation unit is used for carrying out word segmentation processing on the water quality detection data at the first time point so as to convert the water quality detection data at the first time point into a word sequence consisting of a plurality of words; the first word embedding unit is used for mapping each word in the word sequence into a word embedding vector by using a word embedding layer of the first water quality data semantic context encoder so as to obtain a sequence of word embedding vectors; a first context coding unit, configured to perform global context semantic coding on the sequence of word embedded vectors using a converter of the first water quality data semantic context encoder, so as to obtain a plurality of global context semantic feature vectors; and the first cascading unit is used for cascading the plurality of global context semantic feature vectors to obtain the first water quality feature vector.
In the intelligent supervision system for river water pollution restoration process, the first water quality feature normal normalization processing module is used for: calculating a normal normalized value of the feature value of each position in the first water quality feature vector according to the following normal normalized feature value calculation formula; the normal normalized eigenvalue calculation formula is as follows:
y＝(x-μ)/σ
Wherein χ is the eigenvalue of each position in the first water quality eigenvector, μ is the mean of all eigenvalues in the first water quality eigenvector, σ is the variance of all eigenvalues in the first water quality eigenvector, and y is the normal normalized value of the eigenvalue of each position in the first water quality eigenvector.
In the above river water body pollution remediation process intelligent supervision system, the second water quality feature extraction module includes: the second word segmentation unit is used for carrying out word segmentation processing on the water quality detection data at the second time point so as to convert the water quality detection data at the second time point into a word sequence consisting of a plurality of words; a second word embedding unit, configured to map each word in the word sequence into a word embedding vector by using a word embedding layer of the second semantic encoder that includes a word embedding layer, so as to obtain a sequence of word embedding vectors; a second context coding unit, configured to perform global context semantic coding on the sequence of word embedding vectors using a converter of the second semantic encoder that includes a word embedding layer, so as to obtain a plurality of global context semantic feature vectors; and the second cascading unit is used for cascading the plurality of global context semantic feature vectors to obtain the second water quality feature vector.
In the intelligent monitoring system for river water pollution restoration process, the water quality data difference calculation module is used for: performing differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector by using the following differential formula to obtain the differential feature vector; wherein, the difference formula is:
wherein V is 1 Representing the first normal normalized water quality feature vector,representing difference in position, V 2 And representing the second normal normalized water quality characteristic vector, and V represents the differential characteristic vector.
In the river water body pollution restoration process intelligent supervision system, the optimization module is used for: performing prior order-based feature engineering parameterization on the differential feature vector by using the following optimization formula to obtain the optimized differential feature vector; wherein, the optimization formula is:
wherein v is i Is the eigenvalue of the i-th position of the differential eigenvector V, V 0 Representing the zero norm of the differential feature vector, L being the length of the differential feature vector, and β being a weight superparameter, log representing a logarithmic function value based on 2, v' i Is the eigenvalue of the ith position of the optimized differential eigenvector.
In the river water pollution restoration process intelligent supervision system, the water quality restoration effect evaluation module is used for: processing the optimized differential feature vector using the classifier in a classification formula to generate the classification result; wherein, the classification formula is:
O＝softmax{(M c ,B c )|V c }
wherein O is the classification result, V c Representing the optimized differential eigenvector, M c Weight matrix of full connection layer, B c Representing the bias vector for the fully connected layer, softmax is a normalized exponential function.
According to another aspect of the application, there is provided an intelligent supervision method for a river water pollution remediation process, including:
acquiring water quality detection data at a first time point and water quality detection data at a second time point, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality;
the water quality detection data at the first time point passes through a first water quality data semantic context encoder to obtain a first water quality feature vector;
calculating a normal normalized value of the characteristic value of each position in the first water quality characteristic vector to obtain a first normal normalized water quality characteristic vector;
passing the water quality detection data at the second time point through a second water quality data semantic context encoder to obtain a second water quality feature vector;
Calculating a normal normalized value of the characteristic value of each position in the second water quality characteristic vector to obtain a second normal normalized water quality characteristic vector;
performing differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector to obtain a differential feature vector;
performing prior order-based feature engineering parameterization on the differential feature vector to obtain an optimized differential feature vector;
and the optimized differential feature vector passes through a classifier to obtain a classification result, and the classification result is used for indicating whether water quality restoration is effective or not.
Compared with the prior art, the river water pollution restoration process intelligent supervision system and method provided by the application adopt an artificial intelligent monitoring technology based on deep learning, and the water quality restoration effect is evaluated by monitoring the turbidity, suspended matters and hardness of restored water quality. Therefore, the restoration effect of the water quality in the restoration process can be known in time, and when the restoration effect of the water quality is not obvious, restoration measures are adjusted in time so as to achieve more obvious restoration effect.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not to limit the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a system block diagram of an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application.
Fig. 2 is a schematic diagram of an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application.
Fig. 3 is a block diagram of a first water quality feature extraction module in an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application.
Fig. 4 is a block diagram of a second water quality feature extraction module in an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application.
Fig. 5 is a flowchart of an intelligent supervision method for a river water pollution remediation process according to an embodiment of the present application.
Fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Exemplary System
Fig. 1 is a system block diagram of an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application. Fig. 2 is a schematic diagram of an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application. As shown in fig. 1 and 2, in the river water pollution remediation process intelligent supervision system 100, it includes: a water quality data acquisition module 110, configured to acquire water quality detection data at a first time point and water quality detection data at a second time point, where the water quality detection data includes turbidity of water quality, suspended solids of water quality, and hardness of water quality; a first water quality feature extraction module 120, configured to pass the water quality detection data at the first time point through a first water quality data semantic context encoder to obtain a first water quality feature vector; a first water quality feature normal normalization processing module 130, configured to calculate normal normalized values of feature values of each position in the first water quality feature vector to obtain a first normal normalized water quality feature vector; a second water quality feature extraction module 140, configured to pass the water quality detection data at the second time point through a second water quality data semantic context encoder to obtain a second water quality feature vector; the second water quality feature normal normalization processing module 150 is configured to calculate normal normalized values of feature values of each position in the second water quality feature vector to obtain a second normal normalized water quality feature vector; the water quality data difference calculation module 160 is configured to perform a difference operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector to obtain a difference feature vector; an optimization module 170, configured to perform a priori order based feature engineering parameterization on the differential feature vector to obtain an optimized differential feature vector; the water quality restoration effect evaluation module 180 is configured to pass the optimized differential feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the water quality restoration is effective.
In the intelligent monitoring system 100 for river water pollution remediation process, the water quality data acquisition module 110 is configured to acquire water quality detection data at a first time point and water quality detection data at a second time point, where the water quality detection data includes turbidity of water quality, suspended solids of water quality, and hardness of water quality. As stated above in the background, rivers play a vital role in the ecosystem, which has a certain impact on biodiversity, food chain balance and stability of the ecosystem. The river ecology is concerned, so that the natural state is protected and restored, the complete biodiversity is maintained, and the stable and sustainable development of the ecological system is promoted. In addition, rivers are also important fresh water resource supply sources, and the living and production demands of human beings are met. However, excessive development, pollution and climate change lead to deterioration of many river water quality, so restoration of water quality is critical to ensure sustainable supply of water resources. In the existing water quality restoration process, the current supervision mode is low in efficiency, water quality data and change conditions cannot be obtained in real time, and the restoration effect is influenced. Therefore, an optimized intelligent supervision scheme for the river water pollution remediation process is expected.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like. The development of deep learning and neural networks provides a new solution idea and scheme for intelligent supervision of river water pollution restoration processes.
Specifically, in the technical scheme of the application, firstly, water quality detection data at a first time point and water quality detection data at a second time point are obtained, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality. It should be understood that the water quality detection data at the first time point is used as reference data for comparison analysis with the water quality detection data at the second time point. The first point in time and the second point in time are not here meant to be concrete times, but rather abstract expressions. The first point in time may be specific to a certain time of day and the second point in time may be selected at intervals from the first point in time, such as half a month, one month apart. The indexes such as turbidity of water, suspended matters of water, hardness of water and the like can reflect the clarity degree of water, the content of dissolved matters and the hardness of water. If the healing effect is significant, these indicators will vary significantly. Turbidity of the water quality at the first time point and turbidity data of the water quality at the second time point can be measured by a turbidity meter, and suspended matter of the water quality at the first time point and suspended matter data of the water quality at the second time point can be measured by a suspended matter meter; hardness data of water quality at the first time point and hardness data of water quality at the second time point can be measured by a hardness kit.
In the river water pollution remediation process intelligent monitoring system 100, the first water quality feature extraction module 120 is configured to pass the water quality detection data at the first time point through a first water quality data semantic context encoder to obtain a first water quality feature vector. The structure of the first water quality data semantic context encoder is in fact a transducer-based context encoder comprising an embedded layer. The embedding layer may map the input data into a high-dimensional vector space; the transducer is a powerful neural network model, the core of which is a self-attention mechanism that is able to capture the relevance and importance of different positions in an input sequence. By inputting the water quality detection data at the first time point into the first water quality data semantic encoder, the original water quality data can be converted into a feature vector with semantic information, and the feature vector contains key features and context information of the water quality data and can well reflect the state and the features of water quality.
Fig. 3 is a block diagram of a first water quality feature extraction module in an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application. As shown in fig. 3, the first water quality feature extraction module 120 includes: a first word segmentation unit 121, configured to perform word segmentation processing on the water quality detection data at the first time point to convert the water quality detection data at the first time point into a word sequence composed of a plurality of words; a first word embedding unit 122, configured to map each word in the word sequence into a word embedding vector by using a word embedding layer of the first water quality data semantic context encoder, so as to obtain a sequence of word embedding vectors; a first context coding unit 123, configured to perform global context semantic coding on the sequence of word embedded vectors using a converter of the first water quality data semantic context encoder to obtain a plurality of global context semantic feature vectors based on the converter; a first cascade unit 124, configured to cascade the plurality of global context semantic feature vectors to obtain the first water quality feature vector.
In the intelligent supervisory system 100 for river water pollution remediation process, the first water quality feature normal normalization processing module 130 is configured to calculate normal normalized values of feature values of each position in the first water quality feature vector to obtain a first normal normalized water quality feature vector. Normalization is a common data normalization method that makes data have similar scales by converting the data into a normal distribution with a mean value of 0 and a standard deviation of 1. This normalization method can eliminate dimensional differences between different features so that they can be compared on the same scale. By calculating the normal normalized values of the feature values of each position in the first water quality feature vector, the value ranges of different features can be mapped to similar scales, and deviation in the feature values can be removed, so that the data better accords with the assumption of normal distribution. This may make the subsequent differential operations and classifier processing more stable and reliable.
Specifically, in the river water pollution remediation process intelligent supervision system 100, the first water quality feature normal normalization processing module 130 is configured to: calculating a normal normalized value of the feature value of each position in the first water quality feature vector according to the following normal normalized feature value calculation formula; the normal normalized eigenvalue calculation formula is as follows:
y＝(χ-μ)/σ
Wherein χ is the eigenvalue of each position in the first water quality eigenvector, μ is the mean of all eigenvalues in the first water quality eigenvector, σ is the variance of all eigenvalues in the first water quality eigenvector, and y is the normal normalized value of the eigenvalue of each position in the first water quality eigenvector.
In the river water pollution remediation process intelligent supervision system 100, the second water quality feature extraction module 140 is configured to pass the water quality detection data at the second time point through a second water quality data semantic context encoder to obtain a second water quality feature vector. The structure of the second water quality data semantic context encoder is also a transducer-based context encoder including an embedded layer. By inputting the water quality detection data at the second point in time into the second water quality data semantic context encoder, the encoder can convert the water quality data into a semantically meaningful feature vector, i.e., a second water quality feature vector, by learning patterns, associations and semantic information in the data.
Fig. 4 is a block diagram of a second water quality feature extraction module in an intelligent supervisory system for river water pollution remediation process according to an embodiment of the present application. As shown in fig. 4, the second water quality feature extraction module 140 includes: a second word segmentation unit 141, configured to perform word segmentation processing on the water quality detection data at the second time point to convert the water quality detection data at the second time point into a word sequence composed of a plurality of words; a second word embedding unit 142, configured to map each word in the word sequence into a word embedding vector by using a word embedding layer of the second semantic encoder including a word embedding layer, so as to obtain a sequence of word embedding vectors; a second context encoding unit 143, configured to perform global context semantic encoding on the sequence of word embedding vectors using a converter of the second semantic encoder including a word embedding layer, so as to obtain a plurality of global context semantic feature vectors; and a second concatenation unit 144, configured to concatenate the plurality of global context semantic feature vectors to obtain the second water quality feature vector.
In the intelligent supervisory system 100 for river water pollution remediation process, the second water quality feature normal normalization processing module 150 is configured to calculate normal normalized values of feature values of each position in the second water quality feature vector to obtain a second normal normalized water quality feature vector. And calculating the normal normalized value of the characteristic value of each position in the second water quality characteristic vector, so that the characteristic values of different positions have similar scales and distribution. The dimension difference between the characteristic values can be eliminated, and the excessive influence of certain characteristics on model training is avoided. Meanwhile, the normal normalization is also beneficial to improving the generalization capability of the model, so that the model has better adaptability to different water quality data, and more accurate and stable input is provided for the processing of the data in the subsequent steps.
In the intelligent supervisory system 100 for river water pollution remediation process, the water quality data difference calculation module 160 is configured to perform a difference operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector to obtain a difference feature vector. It should be appreciated that by calculating the difference between the second normalized water quality feature vector and the first normalized water quality feature vector, a differential feature vector may be obtained that provides dynamic variation information about the water quality at two points in time. By analyzing the numerical value and trend of the differential feature vector, the restoration effect can be evaluated and the change of the water quality can be monitored.
Specifically, in the river water pollution remediation process intelligent supervision system 100, the water quality data difference calculation module 160 is configured to: performing differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector by using the following differential formula to obtain the differential feature vector; wherein, the difference formula is:
wherein V is 1 Representing the first normal normalized water quality feature vector,representing difference in position, V 2 And representing the second normal normalized water quality characteristic vector, and V represents the differential characteristic vector.
In particular, in the present solution, it is considered that, on a local scale, the first and second water quality data are respectively converted into feature vectors by means of a semantic context encoder. These feature vectors are primarily concerned with water quality characteristics such as turbidity, suspended matter and hardness at various points in time. The local scale code can better capture the local water quality characteristics and the change conditions of each time point. However, since only local information of each time point is considered, global trend and semantic information of the entire time series may not be accurately reflected. In contrast, the differential feature vector is obtained by performing a differential operation on the first and second normal normalized water quality feature vectors. The difference operation can capture the difference and the change trend between the first time point and the second time point, and reflects the change condition of water quality. However, since the global scale code is obtained by calculating the feature vector of the local scale, there may be a difference in accuracy of the local scale code, thereby affecting the accuracy of the global scale code. Therefore, the differential feature vector may not adequately capture global correlation information of the water quality data due to the difference in precision between the semantic encodings of the correlation features on the local scale and the global scale. This may lead to a decrease in the training effect of the differential feature vector when trained by the classifier, as the classifier cannot accurately distinguish between feature differences between different water quality variations. In summary, the difference in accuracy between the semantic encodings of the associated features on the local scale and the global scale affects the training effect of the differential feature vectors. In order to improve the quality of the differential feature vector, feature engineering parameterization based on prior order is carried out on the differential feature vector to obtain an optimized differential feature vector so as to better capture global associated features of water quality data and improve the performance of a classifier.
In the river water pollution remediation process intelligent supervision system 100, the optimizing module 170 is configured to perform a priori order-based feature engineering parameterization on the differential feature vector to obtain an optimized differential feature vector.
Specifically, in the river water pollution remediation process intelligent supervision system 100, the optimization module 170 is configured to: performing prior order-based feature engineering parameterization on the differential feature vector by using the following optimization formula to obtain the optimized differential feature vector; wherein, the optimization formula is:
wherein v is i Is the eigenvalue of the i-th position of the differential eigenvector V, V 0 Representing the zero norm of the differential feature vector, L being the length of the differential feature vector, and β being a weight superparameter, log representing a logarithmic function value based on 2, v' i Is the eigenvalue of the ith position of the optimized differential eigenvector.
It should be understood that in the technical solution of the present application, the mapping relationship between the differential feature vector and the class probability label is modeled as an optimization problem by using the prior order-based feature engineering parameterized transition, so as to ensure the coding efficiency and editing flexibility. Specifically, a sparse distribution balance strategy based on scale representation is designed according to the structure and the attribute of single-parameter high-dimensional feature coding, and feature values of different scales and directions are distributed to different intervals and probability density functions, so that information loss and noise interference in the coding process are reduced. Furthermore, the inversion type recovery technology based on vector counting is utilized to convert the semantic editing of the associated features into an inverse solution problem, and the associated detail information matched with the editing target is extracted from the encoded representation through an iterative optimization algorithm, so that the semantic consistency and the expression capacity in the editing process are enhanced. In such a way, the accuracy of classification regression of the differential feature vector through the classifier is improved.
In the intelligent supervision system 100 for river water pollution remediation process, the water quality remediation effect evaluation module 180 is configured to pass the optimized differential feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether water quality remediation is effective. The classifier is used as a machine learning model, and can be analyzed and judged according to input data, and the classifier is mapped to different categories. By inputting the optimized differential feature vector into the trained classifier, a classification result for indicating whether water quality restoration is effective can be obtained. The classification result can be specifically described as a significant improvement in water quality and a slight improvement in water quality. Based on the classification result, the water quality restoration effect can be rapidly evaluated, and if the water quality restoration effect is not obvious, restoration measures are timely adjusted so as to obtain more obvious restoration effect.
Specifically, in the river water pollution remediation process intelligent supervision system 100, the water quality remediation effect evaluation module 180 is configured to: processing the optimized differential feature vector using the classifier in a classification formula to generate the classification result; wherein, the classification formula is:
O＝softmax{(M c ,B c )|V c }
wherein O is the classification result, V c Representing the optimized differential eigenvector, M c Weight matrix of full connection layer, B c Representing the bias vector for the fully connected layer, softmax is a normalized exponential function.
In summary, the intelligent monitoring system 100 for the river water pollution remediation process according to the embodiment of the present application is illustrated, which adopts the artificial intelligent monitoring technology based on deep learning to evaluate the water quality remediation effect by monitoring the turbidity, suspended matters and hardness of the remediated water quality. Therefore, the restoration effect of the water quality in the restoration process can be known in time, and when the restoration effect of the water quality is not obvious, restoration measures are adjusted in time so as to achieve more obvious restoration effect.
As described above, the river water pollution remediation process intelligent supervision system 100 according to the embodiment of the present application may be implemented in various terminal devices, for example, a server or the like for river water pollution remediation process intelligent supervision. In one example, river water pollution remediation process intelligent supervisory system 100 according to embodiments of the present application may be integrated into a terminal device as one software module and/or hardware module. For example, the river water pollution remediation process intelligent supervisory system 100 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the river water pollution remediation process intelligent supervisory system 100 can also be one of many hardware modules of the terminal device.
Alternatively, in another example, the river water pollution remediation process intelligent supervisor system 100 and the terminal device may be separate devices, and the river water pollution remediation process intelligent supervisor system 100 may be connected to the terminal device via a wired and/or wireless network and transmit interactive information in a agreed data format.
Exemplary method
Fig. 5 is a flowchart of an intelligent supervision method for a river water pollution remediation process according to an embodiment of the present application. As shown in fig. 5, in the intelligent supervision method for the river water pollution remediation process, the method comprises the following steps: s110, acquiring water quality detection data at a first time point and water quality detection data at a second time point, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality; s120, passing the water quality detection data at the first time point through a first water quality data semantic context encoder to obtain a first water quality feature vector; s130, calculating normal normalized values of the characteristic values of all positions in the first water quality characteristic vector to obtain a first normal normalized water quality characteristic vector; s140, the water quality detection data at the second time point passes through a second water quality data semantic context encoder to obtain a second water quality feature vector; s150, calculating a normal normalization value of the feature value of each position in the second water quality feature vector to obtain a second normal normalization water quality feature vector; s160, carrying out differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector to obtain a differential feature vector; s170, carrying out prior order-based feature engineering parameterization on the differential feature vectors to obtain optimized differential feature vectors; and S180, the optimized differential feature vector passes through a classifier to obtain a classification result, and the classification result is used for indicating whether water quality restoration is effective or not.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described river water body pollution repair process intelligent supervision method have been described in detail in the above description of the river water body pollution repair process intelligent supervision system with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
In summary, the intelligent supervision method for the river water pollution restoration process based on the embodiment of the application is clarified, and the water restoration effect is evaluated by monitoring the turbidity, suspended matters and hardness of restored water by adopting an artificial intelligent monitoring technology based on deep learning. Therefore, the restoration effect of the water quality in the restoration process can be known in time, and when the restoration effect of the water quality is not obvious, restoration measures are adjusted in time so as to achieve more obvious restoration effect.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present application is described with reference to fig. 6.
Fig. 6 is a block diagram of an electronic device according to an embodiment of the present application.
As shown in fig. 6, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. On which one or more computer program instructions may be stored that may be executed by processor 11 to implement the river water body pollution remediation process intelligent supervision method and/or other desired functions of the various embodiments of the present application described above. Various contents such as water quality detection data at a first time point, water quality detection data at a second time point, and the like may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 can output various information to the outside, including a result of judging whether the water quality restoration is effective or not, and the like. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 6 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the present application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the intelligent supervisory method of river water pollution remediation processes according to various embodiments of the present application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing the operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Moreover, embodiments of the present application may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform the steps in the river water body pollution remediation process intelligent supervision method according to various embodiments of the present application described in the "exemplary methods" section of the present specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Claims (10)
1. An intelligent supervisory system for river water pollution remediation process, which is characterized by comprising:
the water quality data acquisition module is used for acquiring water quality detection data at a first time point and water quality detection data at a second time point, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality;
the first water quality characteristic extraction module is used for enabling the water quality detection data at the first time point to pass through a first water quality data semantic context encoder to obtain a first water quality characteristic vector;
the first water quality feature normal normalization processing module is used for calculating normal normalization values of feature values of all positions in the first water quality feature vector to obtain a first normal normalized water quality feature vector;
the second water quality characteristic extraction module is used for enabling the water quality detection data at the second time point to pass through a second water quality data semantic context encoder to obtain a second water quality characteristic vector;
the second water quality characteristic normal normalization processing module is used for calculating normal normalization values of characteristic values of all positions in the second water quality characteristic vector to obtain a second normal normalized water quality characteristic vector;
the water quality data difference calculation module is used for carrying out difference operation on the first normal normalized water quality characteristic vector and the second normal normalized water quality characteristic vector to obtain a difference characteristic vector;
The optimization module is used for carrying out prior order-based feature engineering parameterization on the differential feature vectors so as to obtain optimized differential feature vectors;
and the water quality restoration effect evaluation module is used for enabling the optimized differential feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether water quality restoration is effective or not.
2. The river water pollution remediation process intelligent supervisory system of claim 1, wherein the first water quality feature extraction module comprises:
the first word segmentation unit is used for carrying out word segmentation processing on the water quality detection data at the first time point so as to convert the water quality detection data at the first time point into a word sequence consisting of a plurality of words;
the first word embedding unit is used for mapping each word in the word sequence into a word embedding vector by using a word embedding layer of the first water quality data semantic context encoder so as to obtain a sequence of word embedding vectors;
a first context coding unit, configured to perform global context semantic coding on the sequence of word embedded vectors using a converter of the first water quality data semantic context encoder, so as to obtain a plurality of global context semantic feature vectors;
And the first cascading unit is used for cascading the plurality of global context semantic feature vectors to obtain the first water quality feature vector.
3. The river water pollution remediation process intelligent supervisory system of claim 2, wherein the first water quality feature normal normalization processing module is configured to: calculating a normal normalized value of the feature value of each position in the first water quality feature vector according to the following normal normalized feature value calculation formula;
the normal normalized eigenvalue calculation formula is as follows:
y＝(χ-μ)/σ
wherein x is the characteristic value of each position in the first water quality characteristic vector, mu is the mean value of all the characteristic values in the first water quality characteristic vector, sigma is the variance of all the characteristic values in the first water quality characteristic vector, and y is the normal normalized value of the characteristic value of each position in the first water quality characteristic vector.
4. The river water pollution remediation process intelligent supervisory system of claim 3 wherein the second water quality feature extraction module includes:
the second word segmentation unit is used for carrying out word segmentation processing on the water quality detection data at the second time point so as to convert the water quality detection data at the second time point into a word sequence consisting of a plurality of words;
A second word embedding unit, configured to map each word in the word sequence into a word embedding vector by using a word embedding layer of the second semantic encoder that includes a word embedding layer, so as to obtain a sequence of word embedding vectors;
a second context coding unit, configured to perform global context semantic coding on the sequence of word embedding vectors using a converter of the second semantic encoder that includes a word embedding layer, so as to obtain a plurality of global context semantic feature vectors;
and the second cascading unit is used for cascading the plurality of global context semantic feature vectors to obtain the second water quality feature vector.
5. The intelligent supervisory system for river water pollution remediation process of claim 4 wherein the water quality data difference calculation module is configured to: performing differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector by using the following differential formula to obtain the differential feature vector;
wherein, the difference formula is:
wherein V is 1 Representing the first normal normalized water quality feature vector,representing difference in position, V 2 And representing the second normal normalized water quality characteristic vector, and V represents the differential characteristic vector.
6. The intelligent supervisory system for river water pollution remediation process of claim 5, wherein the optimization module is configured to: performing prior order-based feature engineering parameterization on the differential feature vector by using the following optimization formula to obtain the optimized differential feature vector;
wherein, the optimization formula is:
wherein v is i Is the eigenvalue of the i-th position of the differential eigenvector V, V 0 Representing the zero norm of the optimized differential feature vector, L being the length of the differential feature vector, and β being a weight superparameter, log representing a logarithmic function value based on 2, v' i Is the eigenvalue of the ith position of the optimized differential eigenvector.
7. The intelligent supervisory system for river water pollution remediation process of claim 6 wherein the water quality remediation effect evaluation module is configured to: processing the optimized differential feature vector using the classifier in a classification formula to generate the classification result;
wherein, the classification formula is:
O＝softmax{(M c ,B c )|V c }
wherein O is the classification result, V c Representing the optimized differential eigenvector, M c Weight matrix of full connection layer, B c Representing the bias vector for the fully connected layer, softmax is a normalized exponential function.
8. An intelligent supervision method for a river water pollution remediation process is characterized by comprising the following steps:
acquiring water quality detection data at a first time point and water quality detection data at a second time point, wherein the water quality detection data comprise turbidity of water quality, suspended matters of water quality and hardness of water quality;
the water quality detection data at the first time point passes through a first water quality data semantic context encoder to obtain a first water quality feature vector;
calculating a normal normalized value of the characteristic value of each position in the first water quality characteristic vector to obtain a first normal normalized water quality characteristic vector;
passing the water quality detection data at the second time point through a second water quality data semantic context encoder to obtain a second water quality feature vector;
calculating a normal normalized value of the characteristic value of each position in the second water quality characteristic vector to obtain a second normal normalized water quality characteristic vector;
performing differential operation on the first normal normalized water quality feature vector and the second normal normalized water quality feature vector to obtain a differential feature vector;
performing prior order-based feature engineering parameterization on the differential feature vector to obtain an optimized differential feature vector;
And the optimized differential feature vector passes through a classifier to obtain a classification result, and the classification result is used for indicating whether water quality restoration is effective or not.
9. The method of intelligent supervision of a river water pollution remediation process of claim 8, wherein performing a priori order based feature engineering parameterization on the differential feature vectors to obtain optimized differential feature vectors includes: performing prior order-based feature engineering parameterization on the differential feature vector by using the following optimization formula to obtain the optimized differential feature vector;
wherein, the optimization formula is:
wherein v is i Is the eigenvalue of the i-th position of the differential eigenvector V, V 0 Representing the zero norm of the differential feature vector, L being the length of the differential feature vector, and β being a weight superparameter, log representing a logarithmic function value based on 2, v' i Is the eigenvalue of the ith position of the optimized differential eigenvector.
10. The method of intelligent supervision of a river water pollution remediation process according to claim 9, wherein passing the optimized differential feature vector through a classifier to obtain a classification result, the classification result being used to indicate whether water quality remediation is effective, comprises: processing the optimized differential feature vector using the classifier in a classification formula to generate the classification result;
Wherein, the classification formula is:
O＝softmax{(M c ,B c )|V c }
wherein O is the classification result, V c Representing the optimized differential eigenvector, M c Weight matrix of full connection layer, B c Representing the bias vector for the fully connected layer, softmax is a normalized exponential function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489868.8A CN117349731A (en) | 2023-11-09 | 2023-11-09 | Intelligent supervision system and method for river water pollution restoration process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311489868.8A CN117349731A (en) | 2023-11-09 | 2023-11-09 | Intelligent supervision system and method for river water pollution restoration process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117349731A true CN117349731A (en) | 2024-01-05 |
Family
ID=89366819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311489868.8A Pending CN117349731A (en) | 2023-11-09 | 2023-11-09 | Intelligent supervision system and method for river water pollution restoration process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117349731A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117800425A (en) * | 2024-03-01 | 2024-04-02 | 宜宾科全矿泉水有限公司 | Water purifier control method and system based on artificial intelligence |
-
2023
- 2023-11-09 CN CN202311489868.8A patent/CN117349731A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117800425A (en) * | 2024-03-01 | 2024-04-02 | 宜宾科全矿泉水有限公司 | Water purifier control method and system based on artificial intelligence |
| CN117800425B (en) * | 2024-03-01 | 2024-06-07 | 宜宾科全矿泉水有限公司 | Water purifier control method and system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Shankaranarayana et al. | ALIME: Autoencoder based approach for local interpretability | |
| Wei et al. | LSTM-autoencoder-based anomaly detection for indoor air quality time-series data | |
| CN107506414B (en) | Code recommendation method based on long-term and short-term memory network | |
| Liu et al. | An adversarial bidirectional serial–parallel LSTM-based QTD framework for product quality prediction | |
| Zeng et al. | Fast code clone detection based on weighted recursive autoencoders | |
| CN117349731A (en) | Intelligent supervision system and method for river water pollution restoration process | |
| Tsamardinos et al. | Towards integrative causal analysis of heterogeneous data sets and studies | |
| CN116049719B (en) | Fault detection and estimation method, system and medium based on migration type generation model | |
| CN116663568B (en) | Critical task identification system and method based on priority | |
| Ballenberger et al. | Novel statistical approaches for non-normal censored immunological data: analysis of cytokine and gene expression data | |
| CN116245513A (en) | Automatic operation and maintenance system and method based on rule base | |
| Cardoso et al. | Automated discovery of relationships, models, and principles in ecology | |
| CN112100374A (en) | Text clustering method and device, electronic equipment and storage medium | |
| CN116205482A (en) | Important personnel risk level assessment method and related equipment | |
| US20220309078A1 (en) | Apparatus, method, and computer readable medium | |
| CN117198421A (en) | Intelligent detection system and method for marine environment | |
| Chen et al. | A unified framework for layout pattern analysis with deep causal estimation | |
| Duan et al. | Learning numeracy: A simple yet effective number embedding approach using knowledge graph | |
| CN116521871A (en) | File detection method and device, processor and electronic equipment | |
| CN110781978A (en) | Feature processing method and system for machine learning | |
| Li et al. | Beyond Tides and Time: Machine Learning’s Triumph in Water Quality Forecasting | |
| CN116127019A (en) | Dynamic parameter and visual model generation WEB 2D automatic modeling engine system | |
| Gu et al. | A High-Robust Displacement Prediction Model for Super-High Arch Dams Integrating Wavelet De-Noising and Improved Random Forest. Water 2023; 15 (7): 1271 | |
| CN115270792A (en) | Medical entity identification method and device | |
| Agrell et al. | Pitfalls of machine learning for tail events in high risk environments |
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 |