CN104239489A - Method for predicting water level by similarity search and improved BP neural network - Google Patents
Method for predicting water level by similarity search and improved BP neural network Download PDFInfo
- Publication number
- CN104239489A CN104239489A CN201410454011.7A CN201410454011A CN104239489A CN 104239489 A CN104239489 A CN 104239489A CN 201410454011 A CN201410454011 A CN 201410454011A CN 104239489 A CN104239489 A CN 104239489A
- Authority
- CN
- China
- Prior art keywords
- water level
- neural network
- data
- month
- training
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3322—Query formulation using system suggestions
- G06F16/3323—Query formulation using system suggestions using document space presentation or visualization, e.g. category, hierarchy or range presentation and selection
-
- 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
-
- 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
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a method for predicting the water level by similarity search and an improved BP neural network. According to the method, the similarity measurement is carried out according to the water level in 15 days before the prediction day and the water level in months with the similar hydrological characteristics in the past 50 years, the water level time period most similar to each year is found, then, the most similar water level time period in the 50 years and the water level in the later day are used as a training set, and the BP neural network based on a genetic algorithm can be adopted for prediction. The method comprises the steps that data preprocessing is carried out for making up the data missing error and the like; similarity search is carried out, the dynamic bending distance and the sliding window technology are used for finding the minimum distance, i.e., the most similar sequence, between the water level in the 15 days and the water level in the similar months in the former 50 years; the BP neural network based on the genetic algorithm is adopted, the genetic algorithm is used for building a system hierarchy structure for global optimization, and in addition, the study training capability of the BP neural network is used for prediction. The method provided by the invention has the advantages that the water level can be predicted in advance, and the effective technical support can be provided for the flood control and disaster relief.
Description
Technical field
The present invention relates to a kind of technology utilizing similarity searching and the BP neural network prediction water level based on genetic algorithm improvement, particularly relate to the similarity searching to water level information and the BP neural network technology based on genetic algorithm, belong to areas of information technology.
Background technology
To be property value be feature in time sequencing to time series, be the accumulation of time, along with moving ahead of epoch, hydrographic data is also in accumulation slowly, the features such as these hydrographic datas have in a large number, kind is many, dimension is high, updating decision, how strong analysis is carried out to these data, therefrom obtain the focus that useful information becomes people's concern.Along with the development of science and technology and the accumulation of hydrographic data, people give flood control and disaster relief and more pay close attention to.If can effectively predict for one day or the many days water level in a basin, this will be flood forecasting, and Flood Control Dispatch provides strong technical support.
The method of a lot of hydrologic(al) prognosis of current existence, but they have some defects.Using the widest is the model prediction in hydrology field, but these models generally can only be used in specific basin, and they have unique corresponding relation each other, and namely adaptability is weak, and more focus on the application of hydrology knowledge, the good popularization that cannot obtain; Get rid of the limitation of hydrology professional knowledge, more acceptable is the method for computer realm, this more emphasizes the analysis to data, apply various method to mass data analysis in former years to reach the object of prediction, such as based on the prediction of neural network, it may converge to local minimum, cannot control etc. speed of convergence; The prediction of support vector machine, cannot implement large-scale training sample.
Summary of the invention
Goal of the invention: for problems of the prior art is the flood precision and adaptability predicted, the invention provides a kind of method utilizing similarity searching and the BP neural network prediction water level based on genetic algorithm improvement.
Technical scheme: a kind of method utilizing similarity searching and the BP neural network prediction water level based on genetic algorithm improvement, comprising:
A) data prediction: preprocessing process comprises: data selection (data selection), data cleansing (data cleaning), data conversion (data transformation).First determine to need data to be processed and the water level value in 15 days a few days ago to be predicted water level months identical with front ISUZU company, Here it is data selection; The disappearance existed in Hydrological Time Series and noise are needed to clean, makes it the correctness not affecting result; Hydrological Time Series is the high dimensional data of magnanimity, and the noise spot (fluctuation of short-term) wherein contained can affect similarity and differentiate, so need the smoothing process of time series data and data conversion;
B) similarity measurement: according to dynamic time warping distance, utilizes the water level of 15 days a few days ago to be predicted to search the most similar water level time period at ISUZU company with in month water level, using these 50 groups of similar water levels and latter one day accordingly water level as training set;
Described same month water level: the determination of namely searching for month, according to the water regime of basin water level, the water level information in annual each season or each month has certain characteristic, such as: the Hydrological characteristics of Taihu Lake basin and seasonal variations rule be May water table ratio comparatively mild, June then rises slightly to some extent.Therefore must take into full account Hydrological characteristics and the seasonal variations rule in basin when determining to search for month, having the month of close Hydrological characteristics to list hunting zone in the water level characteristic with 15 days to be searched.
After determining search month, according to dynamic time warping (Dynamic Time Warping, DTW) method, utilize sliding window technique, find out in the annual search month of ISUZU company every year to the water level that water level was the most similar in 15 days to be searched, and its initial date of expiry is marked, take out the water level of after annual similar water level one day simultaneously, so just can obtain the training set of 50 groups of similar water levels+latter day water level (being equivalent to the water level of day to be predicted).
C) genetic algorithm: before training, first finds the initial weight of BP neural network optimum to genetic operation such as chromosomal selection cross and variation by genetic algorithm.Further, when BP neural network is absorbed in minimal value, genetic algorithm optimization network parameter is again proceeded to.Best initial weights and threshold value is obtained after meeting accuracy requirement;
The optimum initial weight of described acquisition: refer to and produce initial population and carry out Population Coding, for the enter factor participating in training, because scale of neural network is comparatively large, so with real coding, by a real number directly as a chromosomal gene position.According to the weight of the conventional method generating network of neural network, the ingredient of coding has: connection weights, hidden layer threshold value, the output layer threshold value of the connection weights of input layer and hidden layer, hidden layer and output layer.These are joined together to form a long string, above each position represent a weights and threshold of network, this just constitutes body one by one, produces multiple individuality like this and just constitutes initial population;
The best initial weights threshold value that described acquisition is final: according to the optimum initial weight threshold value of the BP neural network that individuality obtains, obtain system by training data training BP neural network and export the prediction output namely expected, ideal adaptation angle value is exactly the Error Absolute Value between actual output and desired output.Individuality low for fitness value is carried out selection cross and variation, and what meet optimization principles is best initial weights threshold value.
D) BP neural metwork training is utilized to obtain predicted value: the optimum initial weight obtained by genetic algorithm and the best initial weights threshold value satisfied condition to be substituted into BP neural network and trains, obtain the error between the actual output of sample and desired output, again according to normal training philosophy adjustment weight matrix, again train, until obtain final weights, finally obtain predicted value according to the water level of 15 days a few days ago to be predicted.
Beneficial effect: compared with prior art, the method of the BP neural network prediction water level utilizing similarity searching and genetic algorithm to improve provided by the present invention has very strong adaptability, not by the restriction in basin, similarity searching is utilized to obtain the most effective training set, and utilize genetic algorithm improved BP, avoid it to be absorbed in local minimum, greatly can improve training effect.
Accompanying drawing explanation
Fig. 1 is the method flow diagram of the embodiment of the present invention;
Fig. 2 is the data prediction process flow diagram of the embodiment of the present invention;
Fig. 3 is the similarity searching flowchart of the embodiment of the present invention;
Fig. 4 is the BP neural network flowchart that the genetic algorithm of the embodiment of the present invention is improved;
Fig. 5 is the genetic algorithm flowchart of the embodiment of the present invention;
Fig. 6 is the BP neural network flowchart of the embodiment of the present invention.
Embodiment
Below in conjunction with specific embodiment, illustrate the present invention further, these embodiments should be understood only be not used in for illustration of the present invention and limit the scope of the invention, after having read the present invention, the amendment of those skilled in the art to the various equivalent form of value of the present invention has all fallen within the application's claims limited range.
As shown in Figure 1:
A) data prediction: comprise data selection, data cleansing, data conversion.
First determine to need data to be processed and the water level value in 15 days a few days ago to be predicted water level months identical with front ISUZU company, Here it is data selection; The disappearance existed in Hydrological Time Series and noise are needed to clean, makes it the correctness not affecting result; Hydrological Time Series is the high dimensional data of magnanimity, and the noise spot (fluctuation of short-term) wherein contained can affect similarity and differentiate, so need the smoothing process of time series data and data conversion;
B) similarity measurement: according to dynamic time warping distance, utilizes the water level of 15 days a few days ago to be predicted to search the most similar water level time period at ISUZU company with in month water level, using these 50 groups of similar water levels and latter one day accordingly water level as training set;
Described same month water level: the determination of namely searching for month, according to the water regime of basin water level, the water level information in annual each season or each month has certain characteristic, such as: the Hydrological characteristics of Taihu Lake basin and seasonal variations rule be May water table ratio comparatively mild, June then rises slightly to some extent.Therefore must take into full account Hydrological characteristics and the seasonal variations rule in basin when determining to search for month, having the month of close Hydrological characteristics to list hunting zone in the water level characteristic with 15 days to be searched.
After determining search month, according to dynamic time warping method, utilize sliding window technique, find out in the annual search month of ISUZU company every year to the water level that water level was the most similar in 15 days to be searched, and its initial date of expiry is marked, take out the water level of after annual similar water level one day simultaneously, so just can obtain the training set of (50 groups of similar water levels+latter one day water level (being equivalent to the water level of day to be predicted)).
C) genetic algorithm: before training, first finds the initial weight of BP neural network optimum to genetic operation such as chromosomal selection cross and variation by genetic algorithm.Further, when BP neural network is absorbed in minimal value, genetic algorithm optimization network parameter is again proceeded to.Best initial weights and threshold value is obtained after meeting certain precision;
The optimum initial weight of described acquisition: refer to and produce initial population and carry out Population Coding, for the enter factor participating in training, because scale of neural network is comparatively large, so with real coding, by a real number directly as a chromosomal gene position.According to the weight of the conventional method generating network of neural network, the ingredient of coding has: connection weights, hidden layer threshold value, the output layer threshold value of the connection weights of input layer and hidden layer, hidden layer and output layer.These are joined together to form a long string, above each position represent a weights and threshold of network, this just constitutes body one by one, produces multiple individuality like this and just constitutes initial population;
The best initial weights threshold value that described acquisition is final: according to the optimum initial weight threshold value of the BP neural network that individuality obtains, obtain system by training data training BP neural network and export the prediction output namely expected, ideal adaptation angle value is exactly the Error Absolute Value between actual output and desired output.Individuality low for fitness value is carried out selection cross and variation, and what meet optimization principles is best initial weights threshold value.
D) BP neural network: the optimum initial weight obtained by genetic algorithm and the best initial weights threshold value satisfied condition are substituted into BP neural network and trains, obtain the error between the actual output of sample and desired output, again according to normal training philosophy adjustment weight matrix, again train, until obtain final weights, finally obtain predicted value according to the water level of 15 days a few days ago to be predicted.
If Fig. 2 is data prediction process flow diagram:
In real life, due to the reason such as scope fault, system be delayed, cause the shortage of data of one or more consecutive time point in hydrological data bank.Such low quality data can affect the differentiation result of similarity to a certain extent, and then the accuracy of impact prediction result, therefore must to the pre-service in addition of hydrologic observation data.Adopt interpolation, data stuffing, sequence smoothly waits transform method to carry out pre-service to time series, for similarity searching model is prepared.Preprocessing process comprises: data selection, data cleansing, data conversion.
First determine to need the water level value in 15 days a few days ago to be predicted water level months identical with front ISUZU company of data to be processed i.e. certain basin, Here it is data selection;
Need to clean for the disappearance existed in Hydrological Time Series, make it the correctness not affecting result, for the shortage of data in time series, its Crack cause is often data acquisition equipment fault in data-gathering process, and Internet Transmission lacks or manually omits.Ignore these data or simple usage data carries out completion, usually can affect the result of similarity query, cause insecure matching result, and then the result of impact prediction.The population mean of time related sequence on this time period is used to fill up disappearance; Such as with reference to the information of the multiple survey stations closed on corresponding time period;
Hydrological Time Series is the high dimensional data of magnanimity, and the noise spot (fluctuation of short-term) wherein contained can affect similarity and differentiate, so need the smoothing process of time series data and data conversion.Utilize wavelet transform (DWT) to carry out multiple dimensioned conversion, obtain low frequency signal until meet required smoothness.
If Fig. 3 is similarity searching flowchart.Comprise the steps:
Step 101, according in letter of authorization said determine search month after, namely the water level time series of sequence to be matched and 15 days a few days ago to be predicted and sequence to be searched are searched for the water level time series in month and carry out standardization.Adopt zero-Mean Method, for original series C, be standardized as sequence C ', wherein u and v is respectively mean value and the standard deviation of this sequence:
Step 102, determines the length of moving window, is generally 1/2 or 2 times of sequence length to be matched, i.e. [7,21], and matching length is initialized as 7;
Step 103, judges whether the length of mating is [7,21] between the minimum value and maximal value of moving window length, if so, then carries out next step, otherwise carry out step 106;
Step 104, judges whether search sequence coupling to be terminated with the moving window of this length, if not then carry out next step, otherwise the length of moving window is added and carry out step 103;
Step 105, the moving window of calculating certain length often moves the DTW distance between a sequence obtained and sequence to be matched backward, and marks the initial final position of corresponding sequence.The DTW distance process that computational length is respectively between m and n time series X and Y is as follows:
(1) matrix M between X and Y is constructed, the value m that in M, coordinate (i, j) is corresponding
ijfor x
iwith y
jbetween Euclidean distance d (x
i, y
i);
(2) the accumulative matrix R of structure, the worth computing formula that coordinate (i, j) is corresponding is as follows:
r
1,1＝d(x
1,y
1) (2)
r
i,j＝d(x
i,y
j)+min{r
i-1,j-1,r
i-1,j,r
i,j-1}
(3) the minimum accumulated value r of final time series crooked route
m,nit is exactly the DTW distance between time series X and Y.
Calculate the moving window of certain length travel through a search sequence after all DTW distances after record, repetition step 104;
Step 106, for the water level time series in search month of a year in a search sequence and ISUZU company, calculate the DTW distance that sequence to be matched is all with it, relatively draw the initial final position of bee-line and correspondence and corresponding initial date of expiry, so just obtain the most similar sequences of in ISUZU company 1 year, using this sequence and one day thereafter water level as a training sample, other times by that analogy, so just obtain all training sets.
As shown in Figure 4, be BP neural network flowchart that the genetic algorithm of the present embodiment is improved:
Every bar chromosome in genetic algorithm initial population is all made up of the initial weight threshold value in BP neural network, and carries out Population Coding.The system obtained by initialized BP neural network is exported and actual export between Error Absolute Value as ideal adaptation angle value.Individuality low for fitness value is carried out selection cross and variation, meet optimization principles as best initial weights threshold value, be input to BP neural network to train, the study of continuous utilization BP algorithm, until obtain final weights, namely determine optimal neural network, finally obtain predicted value according to the water level of 15 days a few days ago to be predicted.
As shown in Figure 5, be the genetic algorithm flowchart of the present embodiment.Comprise the steps:
Step 201, produces initial population and carries out Population Coding, for the enter factor participating in training, uses real coding, by a real number directly as a chromosomal gene position.According to the weight of the conventional method generating network of neural network, the ingredient of coding has: connection weights, hidden layer threshold value, the output layer threshold value of the connection weights of input layer and hidden layer, hidden layer and output layer.These are joined together to form a long string, above each position represent a weights and threshold of network, this just constitutes body one by one, produces multiple individuality like this and just constitutes initial population;
Step 202, according to the optimum initial weight threshold value of the BP neural network that individuality obtains, obtain system by training data training BP neural network and export, ideal adaptation angle value is exactly the Error Absolute Value Δ E between actual output and system export
i, ideal adaptation angle value f (i) is exactly:
f(i)＝M/ΔE
i (3)
Wherein, M is large number, in order to prevent fitness value too little, genetic algorithm can be made like this to evolve to the direction that indication increases;
Step 203, analyzes the fitness of colony, if meet optimization principles, then directly exports optimum individual and parameter and best initial weights and threshold value and enters BP neural network, otherwise carry out next step;
Step 204, the fitness value according to each individuality carries out seletion calculation, retains the individuality having high fitness value, maximum for fitness value is directly entered the next generation, does not carry out the genetic manipulations such as cross and variation, can prevent it from degenerating like this.Select probability P (i) is:
Wherein, N is population at individual number;
Step 205, crossover operator acts on whole individuality and produces a new generation, as i-th individuality and a jth individual interlace operation in k position are:
Wherein, α is the random number between [0,1];
Step 206, uses mutation operator to carry out structure variation adjustment to the individuality in colony and produces new individual, by i-th individual jth gene a
ijmake a variation, mutation operation is as follows:
Wherein, a
maxand a
mina respectively
ijmaximal value and minimum value, α is the random number between [0,1], and g is current iterations, G
maxit is maximum evolution number of times.
Individuality after selecting cross and variation becomes colony of future generation, repeats step 203.
As shown in Figure 6, be BP neural network flowchart of the present invention, specifically comprise the steps:
Step 301, network is set up: determine network topology, trains substituting into BP neural network after the optimum initial weight obtained by genetic algorithm and the best initial weights threshold value satisfied condition decoding;
Step 302, given input vector and target export, and front ISUZU company the most similar annual time period water level is input vector, and latter one day water level of annual similar water level pattern exports as target;
Step 303, asks the output of hidden layer and output layer and the training error of correspondence;
Step 304, according to training the error obtained to adjust the weights and threshold of network at every turn, if training error is less than specification error, adjusts weight matrix, repeats step 303, obtains final network through iterating;
Step 305, obtains predicted value according to the water level input BP neural network of 15 days a few days ago to be predicted.
Claims (3)
1. utilize a method for similarity searching and improved BP forecast level, it is characterized in that, comprising:
A) data prediction, comprising: data selection, data cleansing, data conversion;
First determine to need data to be processed and the water level value in 15 days a few days ago to be predicted water level months identical with front ISUZU company, Here it is data selection; The disappearance existed in Hydrological Time Series and noise are needed to clean, makes it the correctness and the data cleansing that do not affect result; To the smoothing process of time series data and data conversion, the transform methods such as employing interpolation, data stuffing, sequence are level and smooth carry out pre-service to time series, for similarity searching model is prepared;
B) similarity measurement: according to dynamic time warping distance, utilize sliding window technique, the most similar water level time period is searched at ISUZU company with in month water level, using these 50 groups of similar water levels and latter one day accordingly water level as training set with the water levels of 15 days a few days ago to be predicted;
C) genetic algorithm: before training, first finds the initial weight of BP neural network optimum to genetic operation such as chromosomal selection cross and variation by genetic algorithm; Further, when BP neural network is absorbed in minimal value, genetic algorithm optimization network parameter is again proceeded to; Best initial weights and threshold value is obtained after meeting certain precision;
D) BP neural network and reverse transmittance nerve network: the optimum initial weight obtained by genetic algorithm and the best initial weights threshold value satisfied condition are substituted into BP neural network and trains, obtain the error between the actual output of sample and desired output, again according to normal training philosophy adjustment weight matrix, again train, until obtain final weights, finally obtain predicted value according to the water level of 15 days a few days ago to be predicted.
2. utilize the method for similarity searching and improved BP forecast level as claimed in claim 1, it is characterized in that, described same month water level: the determination of namely searching for month, according to the water regime of basin water level, the water level information in annual each season or each month has certain characteristic, therefore must take into full account Hydrological characteristics and the seasonal variations rule in basin when determining to search for month, having the month of close Hydrological characteristics to list hunting zone in the water level characteristic with 15 days to be searched;
After determining search month, according to dynamic time warping method, utilize sliding window technique, find out in the annual search month of ISUZU company every year to the water level that water level was the most similar in 15 days to be searched, and its initial date of expiry is marked, take out the water level of after annual similar water level one day simultaneously, so just can obtain the training set of 50 groups of similar water levels+latter day water level.
3. utilize the method for similarity searching and improved BP forecast level as claimed in claim 1, it is characterized in that, the optimum initial weight of described acquisition: refer to and produce initial population and carry out Population Coding, for the enter factor participating in training, because scale of neural network is larger, so with real coding, by a real number directly as a chromosomal gene position, the weight of generating network, the ingredient of coding has: connection weights, hidden layer threshold value, the output layer threshold value of the connection weights of input layer and hidden layer, hidden layer and output layer;
These are joined together to form a long string, above each position represent a weights and threshold of network, this just constitutes body one by one, produces multiple individuality like this and just constitutes initial population;
The best initial weights threshold value that described acquisition is final: according to the optimum initial weight threshold value of the BP neural network that individuality obtains, obtain system by training data training BP neural network and export the prediction output namely expected, ideal adaptation angle value is exactly the Error Absolute Value between actual output and desired output; Individuality low for fitness value is carried out selection cross and variation, and what meet optimization principles is best initial weights threshold value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410454011.7A CN104239489B (en) | 2014-09-05 | 2014-09-05 | Utilize the method for similarity searching and improved BP forecast level |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410454011.7A CN104239489B (en) | 2014-09-05 | 2014-09-05 | Utilize the method for similarity searching and improved BP forecast level |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104239489A true CN104239489A (en) | 2014-12-24 |
| CN104239489B CN104239489B (en) | 2018-03-20 |
Family
ID=52227548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410454011.7A Expired - Fee Related CN104239489B (en) | 2014-09-05 | 2014-09-05 | Utilize the method for similarity searching and improved BP forecast level |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239489B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046321A (en) * | 2015-06-25 | 2015-11-11 | 河海大学 | Combined model water level prediction method based on similarity search |
| CN105426441A (en) * | 2015-11-05 | 2016-03-23 | 华中科技大学 | Automatic pre-processing method for time series |
| CN106203741A (en) * | 2016-08-10 | 2016-12-07 | 国家电网公司 | Multi-element heterogeneous Data Cleaning Method for network load prediction |
| CN106326656A (en) * | 2016-08-24 | 2017-01-11 | 东南大学 | Simulation and prediction method for extreme rainstorm flood level of engineering facility |
| CN106407672A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation system based on Internet |
| CN107301564A (en) * | 2017-06-12 | 2017-10-27 | 河南科技大学 | Abnormal consumer behavior detection method based on clustering algorithm and echo state network |
| CN107704973A (en) * | 2017-10-31 | 2018-02-16 | 武汉理工大学 | Water level prediction method based on neutral net Yu local Kalman filtering mixed model |
| CN108537247A (en) * | 2018-03-13 | 2018-09-14 | 河海大学 | A kind of Multivariate Information In Temporal Spatial Domain Hydrological Time Series Similarity measure |
| CN108846573A (en) * | 2018-06-12 | 2018-11-20 | 河海大学 | River Basin Hydrology similarity evaluation method based on time series core distance |
| CN109272146A (en) * | 2018-08-23 | 2019-01-25 | 河海大学 | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network |
| CN109299812A (en) * | 2018-08-23 | 2019-02-01 | 河海大学 | A kind of Forecasting Flood method based on deep learning model and KNN real time correction |
| CN109558436A (en) * | 2018-11-03 | 2019-04-02 | 北京交通大学 | Air station flight delay causality method for digging based on entropy of transition |
| CN109783051A (en) * | 2019-01-28 | 2019-05-21 | 中科驭数（北京）科技有限公司 | A kind of Time Series Similarity computing device and method |
| CN110738355A (en) * | 2019-09-19 | 2020-01-31 | 河源职业技术学院 | urban waterlogging prediction method based on neural network |
| CN111291020A (en) * | 2019-11-11 | 2020-06-16 | 中国计量大学 | Dynamic process soft measurement modeling method based on local weighted linear dynamic system |
| CN111327441A (en) * | 2018-12-14 | 2020-06-23 | 中兴通讯股份有限公司 | Traffic data prediction method, device, equipment and storage medium |
| CN111340176A (en) * | 2018-12-19 | 2020-06-26 | 富泰华工业（深圳）有限公司 | Neural network training method and device and computer storage medium |
| CN111401599A (en) * | 2019-08-01 | 2020-07-10 | 河海大学 | Water level prediction method based on similarity search and L STM neural network |
| CN113033861A (en) * | 2019-12-25 | 2021-06-25 | 广东奥博信息产业股份有限公司 | Water quality prediction method and system based on time series model |
| CN113762618A (en) * | 2021-09-07 | 2021-12-07 | 中国水利水电科学研究院 | Lake water level forecasting method based on multi-factor similarity analysis |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625733A (en) * | 2009-08-03 | 2010-01-13 | 杭州电子科技大学 | Tidewater water level and time forecasting method based on neural network |
| CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
| CN101819407A (en) * | 2010-04-02 | 2010-09-01 | 杭州电子科技大学 | Sewage pump station water level prediction method base on neural network |
| CN102880755A (en) * | 2012-09-25 | 2013-01-16 | 河海大学 | Method and system for quantitatively forecasting extreme rainfall |
-
2014
- 2014-09-05 CN CN201410454011.7A patent/CN104239489B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101625733A (en) * | 2009-08-03 | 2010-01-13 | 杭州电子科技大学 | Tidewater water level and time forecasting method based on neural network |
| CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
| CN101819407A (en) * | 2010-04-02 | 2010-09-01 | 杭州电子科技大学 | Sewage pump station water level prediction method base on neural network |
| CN102880755A (en) * | 2012-09-25 | 2013-01-16 | 河海大学 | Method and system for quantitatively forecasting extreme rainfall |
Non-Patent Citations (4)
| Title |
|---|
| ZHAXI323232: "基于BP神经网络的非线性函数拟合技术报告文档", 《HTTP://WWW.DOCIN.COM/P-365675598.HTML》 * |
| 吴德: "水文时间序列相似模式挖掘的研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 欧阳如琳: "水文时间序列的相似性搜索研究", 《河海大学学报(自然科学版)》 * |
| 迟宝明等: "基于遗传算法的BP神经网络模型在地下水动态预测中的应用研究", 《工程勘察》 * |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105046321A (en) * | 2015-06-25 | 2015-11-11 | 河海大学 | Combined model water level prediction method based on similarity search |
| CN105046321B (en) * | 2015-06-25 | 2018-01-19 | 河海大学 | A kind of method of the Combined model forecast water level based on similarity searching |
| CN105426441A (en) * | 2015-11-05 | 2016-03-23 | 华中科技大学 | Automatic pre-processing method for time series |
| CN105426441B (en) * | 2015-11-05 | 2018-10-16 | 华中科技大学 | A kind of automatic preprocess method of time series |
| CN106203741A (en) * | 2016-08-10 | 2016-12-07 | 国家电网公司 | Multi-element heterogeneous Data Cleaning Method for network load prediction |
| CN106203741B (en) * | 2016-08-10 | 2020-02-21 | 国家电网公司 | Multi-element heterogeneous data cleaning method for power grid load prediction |
| CN106326656A (en) * | 2016-08-24 | 2017-01-11 | 东南大学 | Simulation and prediction method for extreme rainstorm flood level of engineering facility |
| CN106326656B (en) * | 2016-08-24 | 2018-11-09 | 东南大学 | A kind of simulating and predicting method of job facilities Severe rainstorm flood level |
| CN106407672A (en) * | 2016-09-08 | 2017-02-15 | 山东腾泰医疗科技有限公司 | Mental health evaluation system based on Internet |
| CN107301564A (en) * | 2017-06-12 | 2017-10-27 | 河南科技大学 | Abnormal consumer behavior detection method based on clustering algorithm and echo state network |
| CN107704973A (en) * | 2017-10-31 | 2018-02-16 | 武汉理工大学 | Water level prediction method based on neutral net Yu local Kalman filtering mixed model |
| CN108537247A (en) * | 2018-03-13 | 2018-09-14 | 河海大学 | A kind of Multivariate Information In Temporal Spatial Domain Hydrological Time Series Similarity measure |
| CN108537247B (en) * | 2018-03-13 | 2022-03-08 | 河海大学 | Time-space multivariate hydrological time sequence similarity measurement method |
| CN108846573A (en) * | 2018-06-12 | 2018-11-20 | 河海大学 | River Basin Hydrology similarity evaluation method based on time series core distance |
| CN108846573B (en) * | 2018-06-12 | 2021-04-09 | 河海大学 | Watershed hydrological similarity estimation method based on time series kernel distance |
| CN109272146A (en) * | 2018-08-23 | 2019-01-25 | 河海大学 | A kind of Forecasting Flood method corrected based on deep learning model and BP neural network |
| CN109299812A (en) * | 2018-08-23 | 2019-02-01 | 河海大学 | A kind of Forecasting Flood method based on deep learning model and KNN real time correction |
| CN109299812B (en) * | 2018-08-23 | 2021-09-24 | 河海大学 | Flood prediction method based on deep learning model and KNN real-time correction |
| CN109558436A (en) * | 2018-11-03 | 2019-04-02 | 北京交通大学 | Air station flight delay causality method for digging based on entropy of transition |
| CN109558436B (en) * | 2018-11-03 | 2023-03-14 | 北京交通大学 | Airport flight delay cause and effect relationship mining method based on transfer entropy |
| CN111327441A (en) * | 2018-12-14 | 2020-06-23 | 中兴通讯股份有限公司 | Traffic data prediction method, device, equipment and storage medium |
| CN111340176A (en) * | 2018-12-19 | 2020-06-26 | 富泰华工业（深圳）有限公司 | Neural network training method and device and computer storage medium |
| CN109783051A (en) * | 2019-01-28 | 2019-05-21 | 中科驭数（北京）科技有限公司 | A kind of Time Series Similarity computing device and method |
| CN111401599A (en) * | 2019-08-01 | 2020-07-10 | 河海大学 | Water level prediction method based on similarity search and L STM neural network |
| CN111401599B (en) * | 2019-08-01 | 2022-08-26 | 河海大学 | Water level prediction method based on similarity search and LSTM neural network |
| CN110738355A (en) * | 2019-09-19 | 2020-01-31 | 河源职业技术学院 | urban waterlogging prediction method based on neural network |
| CN110738355B (en) * | 2019-09-19 | 2023-07-04 | 河源职业技术学院 | Urban waterlogging prediction method based on neural network |
| CN111291020A (en) * | 2019-11-11 | 2020-06-16 | 中国计量大学 | Dynamic process soft measurement modeling method based on local weighted linear dynamic system |
| CN113033861A (en) * | 2019-12-25 | 2021-06-25 | 广东奥博信息产业股份有限公司 | Water quality prediction method and system based on time series model |
| CN113762618A (en) * | 2021-09-07 | 2021-12-07 | 中国水利水电科学研究院 | Lake water level forecasting method based on multi-factor similarity analysis |
| CN113762618B (en) * | 2021-09-07 | 2022-03-01 | 中国水利水电科学研究院 | Lake water level forecasting method based on multi-factor similarity analysis |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104239489B (en) | 2018-03-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104239489A (en) | Method for predicting water level by similarity search and improved BP neural network | |
| CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
| CN106650767B (en) | Flood forecasting method based on cluster analysis and real-time correction | |
| CN110942194A (en) | Wind power prediction error interval evaluation method based on TCN | |
| CN108920812B (en) | Machining surface roughness prediction method | |
| CN111401599B (en) | Water level prediction method based on similarity search and LSTM neural network | |
| Chen et al. | Groundwater level prediction using SOM-RBFN multisite model | |
| CN107610021A (en) | The comprehensive analysis method of environmental variance spatial and temporal distributions | |
| CN107886160B (en) | BP neural network interval water demand prediction method | |
| CN111709244A (en) | Deep learning method for identifying causal relationship of contradictory dispute events | |
| CN103093643A (en) | Public parking lot berth quantity confirming method | |
| CN105574615A (en) | Spatial correlation and genetic algorithm (GA) based wind power forecast method for wavelet-BP neural network | |
| Huang et al. | Research on urban modern architectural art based on artificial intelligence and GIS image recognition system | |
| Yao et al. | Wave height forecast method with multi-step training set extension LSTM neural network | |
| CN110969312A (en) | Short-term runoff prediction coupling method based on variational modal decomposition and extreme learning machine | |
| CN108229750A (en) | A kind of stock yield Forecasting Methodology | |
| CN117669008B (en) | Foundation settlement prediction method and system based on deep learning | |
| Sweeney et al. | Adaptive post‐processing of short‐term wind forecasts for energy applications | |
| CN115759445A (en) | Machine learning and cloud model-based classified flood random forecasting method | |
| CN116933946A (en) | Rail transit OD passenger flow prediction method and system based on passenger flow destination structure | |
| Bai et al. | Evolutionary algorithm-based error parameterization methods for data assimilation | |
| Jahangir et al. | Generative deep learning for probabilistic streamflow forecasting: Conditional variational auto-encoder | |
| Kou et al. | Prediction intervals for wind power forecasting: using sparse warped Gaussian process | |
| Wu et al. | An Effective Machine Learning Scheme to Analyze and Predict the Concentration of Persistent Pollutants in the Great Lakes | |
| Li et al. | A data-driven rutting depth short-time prediction model with metaheuristic optimization for asphalt pavements based on RIOHTrack |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180320 Termination date: 20210905 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |