CN109829518A - It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA - Google Patents
It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA Download PDFInfo
- Publication number
- CN109829518A CN109829518A CN201910196273.0A CN201910196273A CN109829518A CN 109829518 A CN109829518 A CN 109829518A CN 201910196273 A CN201910196273 A CN 201910196273A CN 109829518 A CN109829518 A CN 109829518A
- Authority
- CN
- China
- Prior art keywords
- degree
- data
- fusion
- belief
- wireless sensor
- 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
- 230000004927 fusion Effects 0.000 title claims abstract description 34
- 238000000034 method Methods 0.000 title claims abstract description 15
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 14
- 230000002068 genetic effect Effects 0.000 claims abstract description 13
- 238000009499 grossing Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 238000007499 fusion processing Methods 0.000 claims description 6
- 241001269238 Data Species 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 241000208340 Araliaceae Species 0.000 claims 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims 1
- 235000003140 Panax quinquefolius Nutrition 0.000 claims 1
- 235000008434 ginseng Nutrition 0.000 claims 1
- 238000012360 testing method Methods 0.000 abstract description 3
- 230000005856 abnormality Effects 0.000 abstract description 2
- 230000002776 aggregation Effects 0.000 abstract description 2
- 238000004220 aggregation Methods 0.000 abstract description 2
- 238000005286 illumination Methods 0.000 abstract description 2
- 238000002156 mixing Methods 0.000 abstract 1
- 230000035772 mutation Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 210000000349 chromosome Anatomy 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
Landscapes
- Complex Calculations (AREA)
Abstract
The invention discloses a kind of methods for being applied to wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA.The present invention sends gateway through aggregation node for the initial data that temperature and humidity, illumination, PH and conductivity wireless sensor node acquire first, is pre-processed using Three-exponential Smoothing to initial data in gateway, rejecting abnormalities data and noise data；Smoothed data is merged using the blending algorithm based on exponential type degree of belief, and Revised genetic algorithum is combined to optimize fusion estimated value.Test result shows that Three-exponential Smoothing can significantly reduce data fluctuations, improves system stability；Compared with the common data anastomosing algorithm such as arithmetic mean method and adaptive weighted method, fusion degree of belief and the data anastomosing algorithm for improving heredity can effectively improve fusion accuracy, reduce algorithm execution time.
Description
[technical field]
The present invention relates to greenhouse wireless sensor device network (WSN) system regions, especially for temperature and humidity in WSN system,
Illumination, PH and conductivity wireless sensor node Multisensor Data Fusion Algorithm.
[background technique]
In the greenhouse monitoring system based on WSN, a large amount of isomorphism redundant nodes usually are disposed in sensing region, are carried out
Periodic environmental data collecting and transmission.Meanwhile various parameters are unevenly distributed in greenhouse, are easy by sensor accuracy, are passed
The influence of the factors such as defeated error, ambient noise and human interference, by multisensor Data Fusion technology to certain redundancy
The data of degree are merged, and can be improved information collection precision and enhancing system stability.
[summary of the invention]
What the present invention designed is applied to the one of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA
Kind method, comprising the following steps:
(1) initial data is pre-processed: by taking temperature as an example, original temperature that temperature and humidity wireless sensor node is acquired
Degree is sent to gateway according to through routing node, carries out the data prediction based on Three-exponential Smoothing in gateway, obtains smooth
Value
(2) degree of belief function is set: by degree of belief function bijIt is defined as the form of exponential function
(3) establish trust degree matrix: setting synchronization has the n indoor temperature of temperature and humidity wireless sensor node measurement temperature
Parameter, according to degree of belief function bij, establish trust degree matrix B.
(4) weight is determined: present invention wiIndicate i-th of temperature and humidity wireless sensor node xiIt is shared in fusion process
Weight, utilize wiTo xiIt is weighted summation, defines one group of nonnegative number a1, a2..., an, it is used for concentrated expression wiAbout xi
Degree of belief system in each subsystem bi1, bi2..., binAll information so that wi=a1bi1+a2bi2+anbinI=1,
2 ..., n.
(5) normalized: w is considerediMeeting weighted sum is 1, to wiIt is normalized, obtains
(6) data fusion: according to determining weight, the final result that all smoothed datas are merged with estimation is obtained.
(7) utilize Revised genetic algorithum optimization fusion result: the present invention defines fusion estimated valueWith true valueBetween
Accidentally absolute value of the difference is objective function, i.e.,
Formula (3) is optimized using Revised genetic algorithum of the present invention, and then obtains optimal value.
[the advantages and positive effects of the present invention]
The present invention introduces the thought of Fuzzy Set Theory in data fusion process, in the number based on exponential type degree of belief
According in Fusion Model, by degree of belief function bijIt is defined as meeting the exponential function form of fuzzy quality, both take full advantage of in this way
The advantage that subordinating degree function range determines in fuzzy theory in turn avoids the absolutization of mutual trust degree between data, more
The authenticity for meeting practical problem keeps fusion results more accurate and stablizes.
The present invention introduces Revised genetic algorithum in data fusion process, first isolates variation from intersection
Come, becomes the independent optimizing operation for being listed in intersection, so that genetic algorithm can also be realized by parallel computation,
It improves algorithm and realizes efficiency.The different intersection of change intensity and mutation operation is respectively adopted in next.In genetic process, by chaos
Together with hereditary connection: in crossover operation, the pairing of individual is carried out with the principle of " well-matched in social and economic status ", it is true using chaos sequence
Determine crosspoint, carries out the most weak single point crossing of intensity and weaken and avoid due to cross-intensity is excessive to ensure algorithmic statement precision
Problem is buffeted in the optimizing of generation；In mutation operation, made a variation using chaos sequence to genes multiple in chromosome, to avoid
Algorithm is precocious.
Test result shows that the data prediction based on Three-exponential Smoothing can significantly reduce data fluctuations, improves system
Stability；Compared with the common data anastomosing algorithm such as arithmetic mean method and adaptive weighted method, based on degree of belief and something lost is improved
The data anastomosing algorithm fusion accuracy of biography is higher, and algorithm execution time is greatly decreased.
[Detailed description of the invention]
Fig. 1 is greenhouse wireless sensor device network (WSN) system data fusion structure illustraton of model；
Fig. 2~4 are respectively general flow chart, the data anastomosing algorithm flow chart based on exponential type degree of belief and improved heredity
Algorithm flow chart；
Fig. 5 is initial data and the effect picture that Three-exponential Smoothing is handled；
Fig. 6 is the objective function curve graph after being optimized using improved adaptive GA-IAGA；
Fig. 7 is arithmetic mean-improved adaptive GA-IAGA, adaptive weighted-improved adaptive GA-IAGA and degree of belief-improved genetic algorithms
The data fusion error curve diagram of method.
[specific embodiment]
The following further describes the present invention with reference to the drawings.
Greenhouse wireless sensor device network (WSN) system data fusion structure model is as shown in Figure 1.It is first that temperature and humidity is wireless
The initial data of sensor node acquisition is sent to region gateway by aggregation node, utilizes third index flatness in gateway
Smooth, rejecting abnormalities data and noise data are carried out to initial data.It is counted using the data anastomosing algorithm based on degree of belief
It is merged according to grade, quantification treatment is carried out to the trusting degree smoothed data according to the exponential type degree of belief function of definition, and pass through
Trust degree matrix measures the synthesis trusting degree of each smoothed data, with each sensor node of reasonable distribution in fusion process most
Excellent weight obtains the expression formula of data fusion estimation.Finally fusion results are optimized using Revised genetic algorithum, into one
Step improves fusion accuracy, to realize Fusion.
In conjunction with Fig. 2~Fig. 4, the algorithm flow designed the present invention is described below:
(1) initial data is pre-processed: by taking temperature as an example, original temperature that temperature and humidity wireless sensor node is acquired
Degree is sent to gateway according to through routing node, carries out the data prediction based on Three-exponential Smoothing in gateway, obtains smooth
Value
(2) degree of belief function is set: by degree of belief function bijIt is defined as the form of exponential function
(3) establish trust degree matrix: setting synchronization has the n indoor temperature of temperature and humidity wireless sensor node measurement temperature
Parameter, according to degree of belief function bij, establish trust degree matrix B.
(4) weight is determined: present invention wiIndicate i-th of temperature and humidity wireless sensor node xiIt is shared in fusion process
Weight, utilize wiTo xiIt is weighted summation, defines one group of nonnegative number a1, a2..., an, it is used for concentrated expression wiAbout xi
Degree of belief system in each subsystem bi1, bi2..., binAll information so that wi=a1bi1+a2bi2+anbinI=1,
2 ..., n.
(5) normalized: w is considerediMeeting weighted sum is 1, to wiIt is normalized, obtains
(6) data fusion: according to determining weight, the final result that all smoothed datas are merged with estimation is obtained.
(7) utilize Revised genetic algorithum optimization fusion result: the present invention defines fusion estimated valueWith true valueBetween
Accidentally absolute value of the difference is objective function, i.e.,
The intersection and mutation operation that the present invention is directed in standard genetic algorithm improve, and detailed process is as follows:
1) intersect
The present invention is intersected using modified, and specific design is as follows: first with " well-matched in social and economic status " principle, being carried out to parent individuality
Pairing, i.e., be ranked up parent with fitness function value, using objective function as fitness function, target function value is small
With small pairing, target function value is big with big pairing.The position that crosspoint is determined using chaos sequence, to determining intersection
Item is intersected.Such as (x1, x2) match, their chromosome is respectivelyIt adopts
One 1 is generated to the positive integer between n with Logistic chaos sequence x (n+1)=4x (n) (1-x (n)).
2) it makes a variation
The mutation operator design that the present invention uses is as follows: first according to given aberration rate, randomly selecting 1 between n
Integer makes a variation to the gene of the two number corresponding positions, and specific variation utilizes chaos sequence using current genic value as initial value
Column x (n+1)=4x (n) (1-x (n)) are iterated, new genic value after being made a variation, to obtain new chromosome.
Formula (3) is optimized using Revised genetic algorithum of the present invention, and then obtains optimal value.
Setting coding mode is decimal coded, and Population Size is set as 50, and algorithm carries out 500 iteration, repeats
100 tests are averaged, and by improved intersection, mutation operation, are selected defect individual, are repeated aforesaid operations, when reaching
When the number of iterations, the optimal value of fusion estimation is obtained.
By taking the raw temperature data of some temperature and humidity wireless sensor node acquisition as an example, Fig. 5 is initial data and process
(smoothing factor α takes 0.1,0.2 and 0.3) treated effect to Three-exponential Smoothing respectively.As can be seen that initial data fluctuation compared with
Greatly, by Three-exponential Smoothing, treated that temperature curve is more smooth, and data fluctuations are small.When α takes 0.2, smooth effect is most
It is good, but there is apparent lag deviation；When α takes 0.3, smoothed data being capable of preferably tracking data variation tendency, but fluctuation
It is larger；When α takes 0.1, smooth effect is preferable, and lags less, thus α take it is 0.1 more appropriate.
From fig. 6, it can be seen that the optimal estimation value after 500 iterationTrue value can be acquired using formula (3)
Be ρ=0.0043 with the error of optimal estimation value, and after iteration (evolutions) number is 50 times, the average fitness of population and
Maximum adaptation degree has mutually convergent form, indicates that algorithmic statement carries out very smooth, does not shake, in this premise
Under, in maximum adaptation degree individual continuous several generations, all show that population is mature, have reached evolution and required there is no evolving.
The data fusion curve of three kinds of algorithms is as shown in Figure 7.It can be calculated using MATLAB, after 500 iteration, base
It is lost in degree of belief-improved adaptive GA-IAGA (F-IGA), arithmetic average-improved adaptive GA-IAGA (AA-IGA) and adaptive weighted-improvement
The fusion error of propagation algorithm (AW-IGA) is respectively 0.0043,0.0107 and 0.0076；Fusion accuracy based on F-IGA algorithm is
2.49 times of AA-IGA algorithm are 1.78 times of AW-IGA algorithm.It can be seen that being based on degree of belief-using proposed
After the data anastomosing algorithm for improving heredity, fusion error is obviously reduced, and effectively increases fusion accuracy and system stability.
The average operating time that three kinds of algorithm operations execute 100 times respectively is calculated using the explorer of MATLAB, is as a result seen
Shown in table 1.
The average operating time (s) of 1 three kinds of algorithms of table
As shown in Table 1, the average operating time of F-IGA algorithm ratio AA-IGA algorithm shortens 64.63%, calculates than AW-IGA
Method shortens 54.24%, greatly improves algorithm performance, while effectively reducing sensor node energy consumption, extends sensor
Service life.
Claims (1)
1. one kind for being applied to wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA that the present invention designs
Method, comprising the following steps:
(1) initial data is pre-processed: by taking temperature as an example, original temperature number that temperature and humidity wireless sensor node is acquired
It is sent to gateway according to through routing node, the data prediction based on Three-exponential Smoothing is carried out in gateway, obtains smooth value
(2) degree of belief function is set: by degree of belief function bijIt is defined as the form of exponential function
(3) establish trust degree matrix: setting synchronization has the n indoor temperature ginseng of temperature and humidity wireless sensor node measurement temperature
Number, according to degree of belief function bij, establish trust degree matrix B.
(4) weight is determined: present invention wiIndicate i-th of temperature and humidity wireless sensor node xiThe shared power in fusion process
Weight, utilizes wiTo xiIt is weighted summation, defines one group of nonnegative number a1, a2..., an, it is used for concentrated expression wiAbout xiLetter
Appoint each subsystem b in degree systemi1, bi2..., binAll information so that wi=a1bi1+a2bi2+anbinI=1,2 ...,
n。
(5) normalized: w is considerediMeeting weighted sum is 1, to wiIt is normalized, obtains
(6) data fusion: according to determining weight, the final result that all smoothed datas are merged with estimation is obtained.
(7) utilize Revised genetic algorithum optimization fusion result: the present invention defines fusion estimated valueWith true valueBetween error
Absolute value be objective function, i.e.,
Formula (3) is optimized using Revised genetic algorithum of the present invention, and then obtains optimal value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196273.0A CN109829518A (en) | 2019-03-15 | 2019-03-15 | It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196273.0A CN109829518A (en) | 2019-03-15 | 2019-03-15 | It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109829518A true CN109829518A (en) | 2019-05-31 |
Family
ID=66870144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910196273.0A Pending CN109829518A (en) | 2019-03-15 | 2019-03-15 | It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109829518A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110798848A (en) * | 2019-09-27 | 2020-02-14 | 国家电网有限公司 | Wireless sensor data fusion method and device, readable storage medium and terminal |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236074A (en) * | 2008-03-06 | 2008-08-06 | 中国科学院力学研究所 | Method for measuring strain distribution using optical fier grating |
| JP6240804B1 (en) * | 2017-04-13 | 2017-11-29 | 大▲連▼大学 | Filtered feature selection algorithm based on improved information measurement and GA |
| CN107423384A (en) * | 2017-07-17 | 2017-12-01 | 国网河南省电力公司检修公司 | Live detection job analysis management method based on information integration technology |
| CN108734009A (en) * | 2018-05-14 | 2018-11-02 | 天津大学 | The optimal inspection vector generation method merged based on genetic algorithm and MERS |
-
2019
- 2019-03-15 CN CN201910196273.0A patent/CN109829518A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101236074A (en) * | 2008-03-06 | 2008-08-06 | 中国科学院力学研究所 | Method for measuring strain distribution using optical fier grating |
| JP6240804B1 (en) * | 2017-04-13 | 2017-11-29 | 大▲連▼大学 | Filtered feature selection algorithm based on improved information measurement and GA |
| CN107423384A (en) * | 2017-07-17 | 2017-12-01 | 国网河南省电力公司检修公司 | Live detection job analysis management method based on information integration technology |
| CN108734009A (en) * | 2018-05-14 | 2018-11-02 | 天津大学 | The optimal inspection vector generation method merged based on genetic algorithm and MERS |
Non-Patent Citations (1)
| Title |
|---|
| 初洪龙，马玉强: ""基于信任度的多传感器数据融合在农业物联网的应用"" * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110798848A (en) * | 2019-09-27 | 2020-02-14 | 国家电网有限公司 | Wireless sensor data fusion method and device, readable storage medium and terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109634121B (en) | Multi-parent genetic algorithm air source heat pump multi-objective optimization control method based on radial basis function neural network | |
| CN110366193B (en) | Slice deployment method and device for network arrangement layer bearing of smart grid | |
| CN106789320B (en) | Multi-population coevolution method for optimizing wireless sensor network topology | |
| CN110458187A (en) | A kind of malicious code family clustering method and system | |
| CN108564592A (en) | Based on a variety of image partition methods for being clustered to differential evolution algorithm of dynamic | |
| CN113573322B (en) | Multi-target area sensor network coverage optimization method based on improved genetic algorithm | |
| CN104268077A (en) | Chaos genetic algorithm based test case intensive simple algorithm | |
| CN107944617A (en) | A kind of doubtful stealing theme influence factor weight optimization method that logic-based returns | |
| CN109829518A (en) | It is applied to a kind of method of wireless sensor network data fusion based on degree of belief and improved adaptive GA-IAGA | |
| CN113705098A (en) | Air duct heater modeling method based on PCA and GA-BP network | |
| Yang et al. | Dynamic Population Structures-Based Differential Evolution Algorithm | |
| CN117234251A (en) | Electrical appliance pressure control method and system based on artificial intelligence | |
| CN107396375A (en) | Heterogeneous sensor network optimum target covering method based on quantum brainstorming | |
| CN102141935A (en) | Job scheduling method based on dual target optimization genetic algorithm | |
| CN107767035A (en) | A kind of electric energy meter detection mixed production line dispatching method based on genetic algorithm | |
| CN111813669A (en) | Adaptive random test case generation method based on multi-target group intelligence | |
| CN116010291A (en) | Multipath coverage test method based on equalization optimization theory and gray prediction model | |
| CN111047465A (en) | Power grid friendly load response method based on electric power big data | |
| CN116070853A (en) | Autonomous emergency scheduling method and system under accident condition of heating system | |
| TWI474210B (en) | A method of applying a genetic algorithm to automatically group and filter the independent variables to synchronize the regression model parameters | |
| CN109934344A (en) | A kind of multiple target Estimation of Distribution Algorithm of improved rule-based model | |
| CN109002877A (en) | Multiple dimensioned collaboration differential evolution optimization method | |
| CN111933226A (en) | Artificial intelligence material screening method based on classification model | |
| CN113111308A (en) | Symbolic regression method and system based on data-driven genetic programming algorithm | |
| CN103177299A (en) | Method and system for optimizing smart energy network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190531 |