CN111950627B - Multi-source information fusion method and application thereof - Google Patents
Multi-source information fusion method and application thereof Download PDFInfo
- Publication number
- CN111950627B CN111950627B CN202010798967.4A CN202010798967A CN111950627B CN 111950627 B CN111950627 B CN 111950627B CN 202010798967 A CN202010798967 A CN 202010798967A CN 111950627 B CN111950627 B CN 111950627B
- Authority
- CN
- China
- Prior art keywords
- data
- fusion
- evidence
- source
- iterative
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 31
- 230000004927 fusion Effects 0.000 claims abstract description 73
- 238000012937 correction Methods 0.000 claims abstract description 27
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 6
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 abstract description 10
- 230000007613 environmental effect Effects 0.000 abstract description 3
- 230000008447 perception Effects 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 10
- 238000011156 evaluation Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 239000003344 environmental pollutant Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 231100000719 pollutant Toxicity 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a multisource information fusion method and application thereof, which start from a sensor data source in environmental monitoring and perform standardized processing and preprocessing on acquired data; and introducing a support correction iteration fusion idea to the multisource isomorphic data, comparing the difference between the fusion evidence and the original evidence to evaluate the support of the original evidence, and iterating for many times until convergence to obtain a final fusion result. Aiming at multi-source heterogeneous data, a multi-source fuzzy fusion algorithm is provided, the problem of multi-source perception data isomerism is solved, and the fusion efficiency of mass data among different unit data formats is improved.
Description
Technical Field
The invention relates to the technical field of information processing, in particular to a multi-source information fusion method and application thereof.
Background
The information fusion technology is applied to an environment monitoring system, a plurality of or a plurality of sensors are distributed at different positions to acquire environment information, then data processing is carried out, and as the monitoring scene is continuously increased, data shows mass property, polymorphism and isomerism, timeliness and uncertainty, so that data collision and uncertainty can be caused, and the mass data fusion efficiency between different unit data formats is reduced.
Disclosure of Invention
The invention aims to provide a multi-source information fusion method and application thereof, which enhance the fusion efficiency of mass data among different unit data formats.
In order to achieve the above object, in a first aspect, the present invention provides a multi-source information fusion method, including:
carrying out standardized processing and preprocessing on the acquired data;
carrying out iterative fusion on the preprocessed multisource isomorphic data by using a support correction iterative fusion method;
fusing the preprocessed multi-source heterogeneous data by using a fuzzy fusion iterative algorithm;
and making a decision on the fused data and uploading the decision.
The iterative fusion method for preprocessing the multisource isomorphic data by using the support correction iterative fusion method comprises the following steps:
blurring and normalizing the preprocessed multi-source isomorphic data based on a membership function corresponding to the application environment to obtain a basic trust probability distribution function; and meanwhile, carrying out evidence correction on the evidence obtained by the data of each node by using variance, and fusing all the evidence by using DS theory to obtain a plurality of groups of initial evidence.
The method for iteratively fusing the preprocessed multi-source isomorphic data by using the support correction iterative fusion method further comprises the following steps:
and obtaining correction evidences after fusing a plurality of groups of initial evidences as initial reference evidences of an iterative algorithm, obtaining corresponding discount factors according to the calculated distance, the cosine of the included angle and the conflict quantity among each evidence fusion result, and simultaneously carrying out correction fusion and iteration on the evidence body by utilizing the next discount factors until the iteration reaches an accuracy threshold value, so as to finish fusion of the multisource isomorphic data.
The method for fusing the preprocessed multi-source heterogeneous data by utilizing the fuzzy fusion iterative algorithm comprises the following steps:
blurring the preprocessed multi-source heterogeneous data based on a membership function corresponding to the application environment to obtain a corresponding membership function; and substituting each preprocessed multi-source heterogeneous data into the corresponding membership function to obtain a corresponding fuzzy relation matrix.
Wherein, utilize the iterative algorithm of fuzzy fusion to fuse the multisource heterogeneous data after the preliminary treatment, still include:
modifying the fuzzy relation matrix according to the calculated weight of each preprocessed multi-source heterogeneous data, and fusing the modified fuzzy data by using an iterative fusion algorithm to finish the fusion of the multi-source heterogeneous data.
In a second aspect, the present invention provides an application of a multi-source information fusion method, where the multi-source information fusion method is applied to environmental monitoring, and the method includes:
carrying out standardized processing and preprocessing on data acquired by using a sensor;
carrying out iterative fusion on the preprocessed multisource isomorphic data by using a support correction iterative fusion method;
fusing the preprocessed multi-source heterogeneous data by using a fuzzy fusion iterative algorithm;
and making a decision on the fused data and uploading the decision to an environment detection cloud.
The invention discloses a multisource information fusion method and application thereof, wherein the multisource information fusion method starts from a sensor data source in environment monitoring and performs standardized processing and preprocessing on acquired data; and introducing a support correction iteration fusion idea to the multisource isomorphic data, comparing the difference between the fusion evidence and the original evidence to evaluate the support of the original evidence, and iterating for many times until convergence to obtain a final fusion result. Aiming at multi-source heterogeneous data, a multi-source fuzzy fusion algorithm is provided, the problem of multi-source perception data isomerism is solved, and the fusion efficiency of mass data among different unit data formats is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic step diagram of a multi-source information fusion method provided by the invention.
Fig. 2 is a schematic diagram of steps of an application of a multi-source information fusion method provided by the invention.
Fig. 3 is a comparison of iteration number versus accuracy provided by the present invention.
Fig. 4 is a comparison of the present invention provided by the present invention with a national standard protocol model.
Fig. 5 is a graph of the 24 hour AQI trend for the first city provided by the present invention.
Fig. 6 is a 24 hour AQI trend graph for a second city provided by the present invention.
Fig. 7 is a 24-hour AQI trend graph for a third city provided by the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Referring to fig. 1, the present invention provides a multi-source information fusion method, which includes:
s101, carrying out standardization processing and preprocessing on the acquired data.
Specifically, before the data fusion is performed on the device, the acquired data are different in type, so that the evaluation indexes are different in property and generally have different dimensions and orders of magnitude. When the level difference among the indexes is large, if the original index value is directly used for analysis, the effect of the index with higher value in comprehensive analysis is highlighted, and the effect of the index with lower value level is relatively weakened. Therefore, in order to ensure the reliability of the result, it is necessary to perform normalization processing on the original index data. The data normalization processing mainly comprises two aspects of data isotacticity processing and dimensionless processing. The data isotactics processing mainly solves the problem of data with different properties, and the direct summation of indexes with different properties can not correctly reflect the comprehensive results of different acting forces, and the inverse index data properties are considered to be changed first, so that all indexes can be used for isotactics of acting forces of an evaluation scheme, and then the summation can obtain correct results. The dimensionless data processing mainly solves the comparability of data. Through the standardization processing, the original data are converted into dimensionless index evaluation values, namely, all index values are in the same number level, and comprehensive evaluation analysis can be performed.
The preprocessing stage converts the raw data into a state more suitable for data fusion, which directly affects the performance of the fusion. Because of the nature of multiple sources and the heterogeneity of data, collecting data from different sources can raise varying degrees of problems such as data integrity, authority, dimensional inconsistencies, noise field redundancy or multiple index values, etc. Preprocessing mainly involves compensating for data for integrity through different filling methods, deleting data unrelated to final decisions and eliminating noise, identifying and correcting outlier data points. The data preprocessing performs data cleaning, data integration, data conversion and data reduction according to task requirements.
S102, carrying out iterative fusion on the preprocessed multi-source isomorphic data by using a support correction iterative fusion method.
Specifically, because the collected data have uncertainty and the judgment standard has ambiguity, the corresponding membership function is selected according to the expert system to fuzzify the measured value according to the different application environments, and the basic trust probability distribution function is obtained by normalizing the measured value.
And from the data source layer, the node error data volatility is utilized, the node trust correction parameter is introduced to correct the evidence conflict generated by the error data, and the probability of the evidence conflict is reduced from the source. Firstly, carrying out evidence correction on the evidence obtained by each node data by using variance, fusing each evidence by using DS theory to obtain n groups of initial evidence, obtaining corrected evidence after fusing the initial evidence, and taking the groups of evidence as initial reference evidence of an iterative algorithm. And obtaining a discount factor of each evidence by calculating the distance, the cosine of the included angle and the conflict quantity between each evidence and the evidence fusion result, adopting a new discount factor to revise the evidence body, fusing, and continuously iterating until the precision requirement is met, so as to obtain a final fusion result.
There are currently n pieces of evidence in totalFusion result->Is provided with->Representing evidence of the ith evidence after the jth iterative correction; />Representing evidence of->The j-th iteration corrects the weights, where j=1, 2, … n. i=1, 2, … n.
1. Calculation of
Calculation ofAnd->Jousselme distance of (a):
wherein:is a 2 N ×2 N Is a square matrix of (c).
2. Calculation ofAnd->Cosine of the included angle:
3. calculation ofAnd->The conflict amount k of (2) i ：
Calculating a support degree parameter:
wherein: a, b and c respectively represent importance degree adjusting parameters of a single attribute, and in the test, a, b and c are set to be 1.
4. Support for evidence parametersNormalization and update evidence->Weight of (c):
5. by means of correction weightsCorrection of evidence at jth ∈ ->
Sequentially iterate untilStopping iteration to obtain a final fusion result +.>
S103, fusing the preprocessed multi-source heterogeneous data by using a fuzzy fusion iterative algorithm.
Specifically, corresponding membership functions are constructed according to expert systems according to different application environments, and the measured values of the evaluation level are fuzzified by each index. Given m indices, n evaluation levels, different membership functions r can be obtained ij 。
Each measured data X i Substituted into membership function r ij The fuzzy relation matrix obtained in the method is as follows:
the weight of each evidence is calculated:
calculating a fuzzy matrix with modified weight:
RF＝R×W
and fusing the fuzzy data by using an iterative fusion algorithm to obtain a final fusion result.
And S104, making a decision on the fused data and uploading the decision.
Specifically, decision is made according to fusion results of all the preprocessed data, and the results are uploaded and displayed to detect the change condition of the acquired data in real time.
Referring to fig. 2, the present invention provides an application of a multi-source information fusion method, where the multi-source information fusion method is applied to environmental monitoring, and includes:
s201, carrying out standardized processing and preprocessing on data acquired by using the sensor.
Specifically, before the data fusion of the device, the data collected by each sensor is different in type, and each evaluation index is different in property and usually has different dimensions and magnitude. In order to ensure the reliability of the results, the original index data needs to be standardized. The standardized processing principle is consistent with the step S101; the preprocessing stage converts the raw data into a state more suitable for multi-sensor fusion, which directly affects the performance of the fusion. Because of the nature of multiple sources and the heterogeneity of data, collecting data from different sources can raise varying degrees of problems such as data integrity, authority, dimensional inconsistencies, noise field redundancy or multiple index values, etc. Preprocessing mainly involves compensating for data for integrity through different filling methods, deleting data unrelated to final decisions and eliminating noise, identifying and correcting outlier data points. The data preprocessing performs data cleaning, data integration, data conversion and data reduction according to task requirements.
S202, carrying out iterative fusion on the preprocessed multi-source isomorphic data by using a support correction iterative fusion method.
Specifically, in the environment monitoring system, various sensors have uncertainty when collecting data, and meanwhile, the judgment standard has ambiguity, so that DS evidence theory and ambiguity theory are adopted to fuse the multi-sensor data, and an environment overall evaluation result is obtained. The fusion method of the multisource isomorphic data is consistent with the step S102.
S203, fusion is carried out on the preprocessed multi-source heterogeneous data by using a fuzzy fusion iterative algorithm.
Specifically, for heterogeneous data existing in an environment monitoring system, an iterative algorithm based on fuzzy fusion is selected to fuse multi-source heterogeneous information. Specific fusion methods are shown in S103, and multi-source isomorphic and heterogeneous information fusion methods are respectively researched according to different characteristics of mass data in an environment monitoring scene, so that a hierarchical fusion model is established. And carrying out in-network processing on a large amount of original data acquired by the wireless sensor network, eliminating redundant information among the multi-sensor information, reducing conflict and uncertainty of the data, and enhancing the reliability of the data and the reliability of results.
And S204, making a decision on the fused data and uploading the decision to an environment detection cloud.
Specifically, making a decision according to the fusion result of all the preprocessed data, and uploading the decision result to the cloud end through the NB-IoT; the cloud has a visual interface, can monitor the state of the current environment in real time, and report the abnormal information to the corresponding departments, so that the corresponding operation can be conveniently executed.
Fusion of multisource isomorphic data
(1) Data source
Taking temperature data as an example, matlab2014 is used, normal distribution of different variances is taken as a mean value at 19 ℃ to randomly generate 5 data which are continuously measured for a certain time period of 3 sensors, and as shown in table 5-1, the 5 data which are respectively measured by the 3 temperature sensors are shown.
Table 5-1 sensor node measures 5 times temperature over a period of time
| Sensor for detecting a position of a body | 1 time | 2 times | 3 times | 4 times | 5 times |
| 1 | 19.32 | 19.16 | 18.79 | 18.44 | 18.94 |
| 2 | 18.37 | 19.04 | 18.76 | 19.93 | 18.58 |
| 3 | 18.92 | 18.70 | 18.68 | 19.43 | 18.05 |
The measured value is subjected to fuzzification processing by using a triangle membership function, and the measured data sequence of a certain node is assumed to be d i And there are 3 fuzzy sets, M, N, Q respectively. M represents a measured temperature of less than 18.5 DEG CProbability; n represents the probability of measuring the temperature at 18.5-19.5 ℃; q represents the probability that the measured temperature is higher than 19.5 ℃. Because the sensor data are numerous, and the computing capacity and energy of the sensor nodes are limited, in order to facilitate the computation, the obtained fuzzy values are normalized to obtain the basic trust probability distribution function. The sensor node data basic trust probability distribution function is:
(2) Data fusion results and analysis
The results obtained from the obtained data according to the multisource isomorphic algorithm and other classical DS evidence methods and improved methods are compared as shown in the following tables 5-2.
TABLE 5-2 evidence fusion results
And fusing the 5 groups of data by using a traditional D-S fusion rule to obtain a first fusion result, and carrying out iterative fusion correction on the evidence by using an iterative algorithm until the iteration ending requirement is met to obtain a final fusion result. The results obtained from the fusion of these 5 sets of data using different methods were then compared with the fusion results of the present study, respectively, as shown in tables 5-3. The result shows that the fusion result of the work research method is stable, is closest to real data, and has good compatibility for conflict evidence.
The fused evidence obtained by each last method is converted into specific numerical values through multiplying the evidence probability distribution function by the sum of the corresponding targets, as shown in tables 5-3. The comparison can be achieved, the research method and the iterative correction method of the work are closest to the actual temperature, and the error is minimum.
Table 5-3 estimation results (units: degrees Celsius) of different methods
| Method | D-S method | Classification correction method | Iterative correction method | Research method of the work |
| Result estimation | 18.766 | 18.818 | 18.976 | 18.983 |
| Error with true value | 0.234 | 0.182 | 0.024 | 0.017 |
Comparing the convergence property of the work research method with that of the iterative correction method, and obtaining an iterative result by setting the same precision as shown in figure 3. The convergence speed of the research algorithm of the work is faster, the iteration times reaching the same precision are fewer, and the higher precision can be obtained after the iteration is performed for only 4 times.
Fusion of multisource heterogeneous data
A new air quality evaluation model is established based on a multi-sensor data fusion technology, and the air quality index and the pollution level can be obtained quantitatively according to the pollutant concentration obtained by the sensor. And (3) selecting the concentrations of various atmospheric pollutants in different cities for simulation verification, and comparing the obtained air quality index with the obtained air quality index of the existing national standard.
The new model established by the work is shown in figure 4, and the scheme model pair under the national standard is shown in the figure.
(1) Data source
The multi-sensor fuzzy fusion method provided by the work is verified, the differences between the work model and the national standard scheme model are compared, and the concentrations of three born air quality pollutants are selected and simulated.
(2) Data fusion results and analysis
The obtained data are compared with the results obtained by the national standard algorithm according to the multi-source heterogeneous algorithm adopted by the work model, such as shown in fig. 5, 6 and 7.
The national standard only selects the maximum air quality index in each pollution factor as a final result, and the work model is the air quality index obtained on the basis of comprehensive evaluation of each index, so that the AQI index obtained by the work method is generally lower than the national standard. However, the change trend of the air quality index obtained by the new model of the work is basically consistent with the national standard result, which shows that the result obtained by comprehensively evaluating the air quality grade through the work model is effective.
The invention discloses a multisource information fusion method and application thereof, wherein the multisource information fusion method starts from a sensor data source in environment monitoring and performs standardized processing and preprocessing on acquired data; and introducing a support correction iteration fusion idea to the multisource isomorphic data, comparing the difference between the fusion evidence and the original evidence to evaluate the support of the original evidence, and iterating for many times until convergence to obtain a final fusion result. Aiming at multi-source heterogeneous data, a multi-source fuzzy fusion algorithm is provided, the problem of multi-source perception data isomerism is solved, and the fusion efficiency of mass data among different unit data formats is improved.
The above disclosure is only a preferred embodiment of the present invention, and it should be understood that the scope of the invention is not limited thereto, and those skilled in the art will appreciate that all or part of the procedures described above can be performed according to the equivalent changes of the claims, and still fall within the scope of the present invention.
Claims (1)
1. A method for multi-source information fusion, comprising:
carrying out standardized processing and preprocessing on the acquired data;
carrying out iterative fusion on the preprocessed multisource isomorphic data by using a support correction iterative fusion method;
fusing the preprocessed multi-source heterogeneous data by using a fuzzy fusion iterative algorithm;
making a decision on the fused data and uploading the decision;
the iterative fusion method for carrying out iterative fusion on the preprocessed multi-source isomorphic data by using the support correction iterative fusion method comprises the following steps:
blurring and normalizing the preprocessed multi-source isomorphic data based on a membership function corresponding to the application environment to obtain a basic trust probability distribution function; meanwhile, carrying out evidence correction on the evidence obtained by the data of each node by using variance, and fusing all the evidence by using DS theory to obtain a plurality of groups of initial evidence;
the method comprises the steps of obtaining correction evidences after a plurality of groups of initial evidences are fused to be used as initial reference evidences of an iterative algorithm, obtaining corresponding discount factors according to calculated distances, included angle cosine and conflict quantity among all evidence fusion results, and simultaneously carrying out correction fusion and iteration on evidence bodies by using the next discount factors until the iteration reaches an accuracy threshold value, so that fusion of the multisource isomorphic data is completed;
the method for fusing the preprocessed multi-source heterogeneous data by using the fuzzy fusion iterative algorithm comprises the following steps:
blurring the preprocessed multi-source heterogeneous data based on a membership function corresponding to the application environment to obtain a corresponding membership function; substituting each preprocessed multi-source heterogeneous data into the corresponding membership function to obtain a corresponding fuzzy relation matrix;
modifying the fuzzy relation matrix according to the weight calculated by each preprocessed multi-source heterogeneous data, and fusing the modified fuzzy data by using an iterative fusion algorithm to finish the fusion of the multi-source heterogeneous data;
decision making and uploading are carried out on the fused data, and the method comprises the following steps:
and making a decision according to the fusion result of all the preprocessed data, uploading and displaying the result, and detecting the change condition of the acquired data in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010798967.4A CN111950627B (en) | 2020-08-11 | 2020-08-11 | Multi-source information fusion method and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010798967.4A CN111950627B (en) | 2020-08-11 | 2020-08-11 | Multi-source information fusion method and application thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111950627A CN111950627A (en) | 2020-11-17 |
| CN111950627B true CN111950627B (en) | 2024-04-05 |
Family
ID=73332119
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010798967.4A Active CN111950627B (en) | 2020-08-11 | 2020-08-11 | Multi-source information fusion method and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111950627B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489421A (en) * | 2020-11-18 | 2021-03-12 | 南京速安交通科技有限公司 | Burst congestion judging method and system based on multi-source traffic big data fusion |
| CN112672299B (en) * | 2020-12-09 | 2022-05-03 | 电子科技大学 | Sensor data reliability evaluation method based on multi-source heterogeneous information fusion |
| CN113051249A (en) * | 2021-03-22 | 2021-06-29 | 江苏杰瑞信息科技有限公司 | Cloud service platform design method based on multi-source heterogeneous big data fusion |
| CN113408625B (en) * | 2021-06-22 | 2022-08-09 | 之江实验室 | Multi-source heterogeneous data single-frame fusion and consistent characterization method applied to unmanned system |
| CN113746855A (en) * | 2021-09-09 | 2021-12-03 | 国网电子商务有限公司 | Data access method of energy industry cloud network and related equipment |
| CN114018238B (en) * | 2021-10-21 | 2024-05-07 | 中国电子科技集团公司第五十四研究所 | Multi-source sensor data availability evaluation method combining transverse direction and longitudinal direction |
| CN114881147B (en) * | 2022-05-10 | 2024-04-05 | 桂林电子科技大学 | Multi-source heterogeneous big data fusion and integration system and method |
| CN115564148B (en) * | 2022-12-01 | 2023-04-07 | 北京科技大学 | Chamber safety analysis method based on multi-source heterogeneous data fusion |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556651A (en) * | 2009-04-15 | 2009-10-14 | 北京航空航天大学 | Multi-source data fusion method in clustering wireless sensor network |
| CN101996157A (en) * | 2010-10-23 | 2011-03-30 | 山东科技大学 | Multisource information fusion method in evidence high-conflict environment |
| EP2610636A1 (en) * | 2011-12-29 | 2013-07-03 | Windward Ltd. | Providing near real-time maritime insight from satellite imagery and extrinsic data |
| CN104699818A (en) * | 2015-03-25 | 2015-06-10 | 武汉大学 | Multi-source heterogeneous multi-attribute POI (point of interest) integration method |
| CN106096830A (en) * | 2016-06-07 | 2016-11-09 | 武汉大学 | Relay protection method for evaluating state based on broad sense evidence theory and system |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN108734208A (en) * | 2018-05-15 | 2018-11-02 | 重庆大学 | Multi-source heterogeneous data fusion system based on multi-modal depth migration study mechanism |
| CN108985365A (en) * | 2018-07-05 | 2018-12-11 | 重庆大学 | Multi-source heterogeneous data fusion method based on depth subspace switching integrated study |
| CN109377034A (en) * | 2018-10-11 | 2019-02-22 | 国网新疆电力有限公司信息通信公司 | Risk profiles appraisal procedure based on smart grid information communication system |
| CN110009251A (en) * | 2019-04-15 | 2019-07-12 | 西安邮电大学 | A kind of farmland multi-source information dynamic regulation fusion method and system |
| CN110188882A (en) * | 2018-12-28 | 2019-08-30 | 湖南大学 | A kind of high conflicting evidence fusion method based on fuzzy reasoning |
| CN110441060A (en) * | 2019-08-07 | 2019-11-12 | 贵州电网有限责任公司 | One kind being based on mechanical failure diagnostic method combined of multi-sensor information |
-
2020
- 2020-08-11 CN CN202010798967.4A patent/CN111950627B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101556651A (en) * | 2009-04-15 | 2009-10-14 | 北京航空航天大学 | Multi-source data fusion method in clustering wireless sensor network |
| CN101996157A (en) * | 2010-10-23 | 2011-03-30 | 山东科技大学 | Multisource information fusion method in evidence high-conflict environment |
| EP2610636A1 (en) * | 2011-12-29 | 2013-07-03 | Windward Ltd. | Providing near real-time maritime insight from satellite imagery and extrinsic data |
| CN104699818A (en) * | 2015-03-25 | 2015-06-10 | 武汉大学 | Multi-source heterogeneous multi-attribute POI (point of interest) integration method |
| CN106096830A (en) * | 2016-06-07 | 2016-11-09 | 武汉大学 | Relay protection method for evaluating state based on broad sense evidence theory and system |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN108734208A (en) * | 2018-05-15 | 2018-11-02 | 重庆大学 | Multi-source heterogeneous data fusion system based on multi-modal depth migration study mechanism |
| CN108985365A (en) * | 2018-07-05 | 2018-12-11 | 重庆大学 | Multi-source heterogeneous data fusion method based on depth subspace switching integrated study |
| CN109377034A (en) * | 2018-10-11 | 2019-02-22 | 国网新疆电力有限公司信息通信公司 | Risk profiles appraisal procedure based on smart grid information communication system |
| CN110188882A (en) * | 2018-12-28 | 2019-08-30 | 湖南大学 | A kind of high conflicting evidence fusion method based on fuzzy reasoning |
| CN110009251A (en) * | 2019-04-15 | 2019-07-12 | 西安邮电大学 | A kind of farmland multi-source information dynamic regulation fusion method and system |
| CN110441060A (en) * | 2019-08-07 | 2019-11-12 | 贵州电网有限责任公司 | One kind being based on mechanical failure diagnostic method combined of multi-sensor information |
Non-Patent Citations (3)
| Title |
|---|
| Data fusion algorithm based on fuzzy sets and D-S theory of evidence;Guangzhe Zhao等;Tsinghua Science and Technology;第25卷(第1期);第12-19页 * |
| 基于D-S证据理论的信息融合方法研究与应用;易革军;中国优秀硕士学位论文全文数据库信息科技辑(第3期);第I140-60页 * |
| 数控机床网络化集成运行模式及关键集成技术研究;童亮;中国博士学位论文全文数据库工程科技Ⅰ辑(第12期);第B022-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111950627A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111950627B (en) | Multi-source information fusion method and application thereof | |
| CN107169628B (en) | Power distribution network reliability assessment method based on big data mutual information attribute reduction | |
| CN110895878B (en) | Traffic state virtual detector generation method based on GE-GAN | |
| CN102393881B (en) | A kind of high-precision detecting method of real-time many sensing temperatures data fusion | |
| CN104361414B (en) | Power transmission line icing prediction method based on correlation vector machine | |
| CN110533239B (en) | Smart city air quality high-precision measurement method | |
| CN116150897A (en) | Machine tool spindle performance evaluation method and system based on digital twin | |
| CN114004137A (en) | Multi-source meteorological data fusion and pretreatment method | |
| CN110309609B (en) | Building indoor air quality evaluation method based on rough set and WNN | |
| CN110222411B (en) | Non-measurement-area solar radiation estimation method based on mRMR-DBN algorithm | |
| CN113065223B (en) | Multi-level probability correction method for digital twin model of tower mast cluster | |
| CN110601173B (en) | Distribution network topology identification method and device based on edge calculation | |
| CN111881124A (en) | Data processing method and system based on state estimation of improved algorithm | |
| CN111882198A (en) | Project performance evaluation method and system | |
| CN111242357A (en) | Neural network learning-based train-mounted equipment fault prediction method and device | |
| CN111680398B (en) | Single machine performance degradation prediction method based on Holt-windows model | |
| CN117235664A (en) | Fault diagnosis method and system for power distribution communication equipment and computer equipment | |
| CN117310361A (en) | Power distribution network fault patrol positioning method based on intelligent perception and equipment image | |
| CN113761806B (en) | Atmospheric visibility prediction method based on neural network | |
| CN111340975A (en) | Abnormal data feature extraction method, device, equipment and storage medium | |
| JP6950647B2 (en) | Data determination device, method, and program | |
| CN115983329A (en) | Method, device, equipment and storage medium for predicting air quality and meteorological conditions | |
| CN115510763A (en) | Air pollutant concentration prediction method and system based on data-driven exploration | |
| CN113849576A (en) | Specific group analysis method and system based on knowledge graph | |
| CN114363004A (en) | Risk assessment method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |