CN107295453A - A kind of wireless sensor network data fusion method - Google Patents
A kind of wireless sensor network data fusion method Download PDFInfo
- Publication number
- CN107295453A CN107295453A CN201610197432.5A CN201610197432A CN107295453A CN 107295453 A CN107295453 A CN 107295453A CN 201610197432 A CN201610197432 A CN 201610197432A CN 107295453 A CN107295453 A CN 107295453A
- Authority
- CN
- China
- Prior art keywords
- node
- cluster head
- cluster
- data
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 10
- 210000002569 neuron Anatomy 0.000 claims abstract description 23
- 238000004891 communication Methods 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 230000001537 neural effect Effects 0.000 claims abstract description 3
- 241000854291 Dianthus carthusianorum Species 0.000 claims description 62
- 241000254158 Lampyridae Species 0.000 claims description 47
- 238000013528 artificial neural network Methods 0.000 claims description 28
- 238000000034 method Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 10
- GNBHRKFJIUUOQI-UHFFFAOYSA-N fluorescein Chemical compound O1C(=O)C2=CC=CC=C2C21C1=CC=C(O)C=C1OC1=CC(O)=CC=C21 GNBHRKFJIUUOQI-UHFFFAOYSA-N 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 abstract description 8
- 230000005540 biological transmission Effects 0.000 abstract description 3
- 241000131894 Lampyris noctiluca Species 0.000 abstract 1
- 238000004220 aggregation Methods 0.000 abstract 1
- 230000002776 aggregation Effects 0.000 abstract 1
- 230000006870 function Effects 0.000 description 12
- 238000004364 calculation method Methods 0.000 description 5
- 238000005265 energy consumption Methods 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000007177 brain activity Effects 0.000 description 1
- 230000003925 brain function Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 210000000225 synapse Anatomy 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W52/00—Power management, e.g. TPC [Transmission Power Control], power saving or power classes
- H04W52/02—Power saving arrangements
- H04W52/0209—Power saving arrangements in terminal devices
- H04W52/0212—Power saving arrangements in terminal devices managed by the network, e.g. network or access point is master and terminal is slave
- H04W52/0219—Power saving arrangements in terminal devices managed by the network, e.g. network or access point is master and terminal is slave where the power saving management affects multiple terminals
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W84/00—Network topologies
- H04W84/18—Self-organising networks, e.g. ad-hoc networks or sensor networks
-
- 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
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Arrangements For Transmission Of Measured Signals (AREA)
Abstract
The present invention proposes a kind of wireless sensor network data fusion method for optimizing RBF neural based on glowworm swarm algorithm, the data that each sensor node is collected to it carry out preliminary treatment according to input layer function, a small amount of characteristic is obtained, the leader cluster node of cluster where characteristic then is sent into it；Leader cluster node is further processed according to hidden neuron function and output layer neuron function to characteristic, data after being merged；Data after fusion are sent to aggregation node by leader cluster node.The present invention can effectively reduce transmission quantity of the information in net, can save network communication bandwidth while sensor node power consumption is reduced.
Description
Technical Field
The invention belongs to the technical field of wireless sensor networks, and particularly relates to a wireless sensor network data fusion method for optimizing RBF neural networks based on a firefly algorithm.
Background
The wireless sensor network is a multi-hop self-organizing network system formed by a large number of sensor nodes which are deployed in a monitoring area and communicated with each other, and is an important technical form of an Internet of things underlying network. Due to the small size and limited resources of the sensor nodes, the sensor nodes are distributed in the coverage area of the wireless sensor network, and the distribution of the sensor nodes is high in confidentiality and distribution nonuniformity, so that the data acquired by the sensor nodes has high redundancy. If all the information is sent to the sink node, the energy consumption of the sensor node is too high, and the service life of the wireless sensor network is seriously shortened. In order to avoid the problems, a data fusion technology is required to be used in the process of acquiring data by the wireless sensor network, so that the transmission quantity of information in the network is reduced, the power consumption of the sensor nodes is reduced, and meanwhile, the network communication bandwidth is saved.
The neural network is a complex network system formed by widely interconnecting a large number of simple processing units (called neurons), reflects many basic characteristics of human brain functions, can simulate human brain activities, has the advantages of extremely strong nonlinear approximation, distributed storage, large-scale parallel processing, self-training learning, self-organization, fault-tolerant capability and the like, and is particularly suitable for processing inaccurate and fuzzy information processing problems needing to consider a plurality of factors and conditions simultaneously. Wireless sensor networks and neural networks have special similarities: the sensor nodes in the wireless sensor network are as good as neurons, and have sensing and processing functions; and the connection between the wireless sensor nodes is equivalent to synapse of connecting neurons, and the signal transmission is finished. The data fusion of the wireless sensor network and the neural network have a common basic characteristic, namely, a conclusive result capable of reflecting the characteristics of a large amount of data is obtained by performing certain operation and processing on the data. Therefore, the data fusion problem in the wireless sensor network can be realized and solved by using the method of the neural network. Neural networks have proven to be very effective for data fusion in wireless sensor networks.
The radial basis function neural network is a high-efficiency feedforward neural network, has a three-layer structure, has the optimal approximation performance and the global optimal characteristic which are not possessed by other forward networks, has simple structure and high training speed, and simultaneously is a neural network model which can be widely applied to the fields of pattern recognition, fault diagnosis, nonlinear function approximation and the like.
Disclosure of Invention
The invention aims to provide a wireless sensor network data fusion method for optimizing an RBF neural network based on a firefly algorithm, which effectively reduces the transmission amount of information in the network, and can save network communication bandwidth while reducing the power consumption of sensor nodes.
In order to solve the technical problem, the invention provides a data fusion method of a wireless sensor network, wherein each sensor node performs primary processing on the acquired data according to an input layer neuron function to obtain a small amount of characteristic data, and then sends the characteristic data to a cluster head node of a cluster where the sensor node is located; the cluster head node further processes the characteristic data according to the hidden layer neuron function and the output layer neuron function to obtain fused data; and the cluster head node sends the fused data to the sink node.
Further, the method comprises the following steps: the cluster head transmits the sensor node information table in the cluster to the sink node; the sink node constructs an RBF neural network according to the cluster head and the information of the sensor nodes in the cluster; the RBF neural network retrieves a sample database, and samples matched with the cluster member information are collected for training, so that neural network parameters of corresponding clusters are generated; the sink node sends the parameters of each neuron of the firefly-optimized RBF neural network to the corresponding sensor node; after the clustering is stably operated, the cluster head fuses the received information and transmits fused data to the sink node.
Further, the method for selecting cluster heads and clustering sensor nodes in the wireless sensor network comprises the following steps: in the initial stage of each round of clusters, each sensor node randomly generates a value between [0,1], and if the value is smaller than a set threshold value T (n), the sensor node is used as a cluster head, wherein the threshold value T (n) of the sensor node which has already passed through the cluster head is 0; after the cluster head is selected, the cluster head informs other sensor nodes which are not used as the cluster head of the information that the sensor nodes become the cluster head nodes through broadcasting, and the other sensor nodes which are not used as the cluster head are added into the corresponding cluster head according to the strength of the received signal so as to form a cluster; the cluster head establishes a time division multiple access communication scheme according to the number of the added sensor nodes, a certain communication time slot is allocated to each sensor node in the cluster, and the sensor nodes in the cluster send data to the cluster head in the communication time slot allocated to the sensor nodes.
Further, the whole wireless sensor network is used as an RBF neural system, each sensor node is used as a neuron of an input layer, a cluster head is used as a hidden layer neuron, a firefly algorithm is used for fuzzy clustering, and the radial base center and the base width of the neural network are confirmed, specifically: calculating the membership degree of the data object to each clustering center; calculating the fitness parameter value of each firefly and updating the fluorescein value of each firefly; selecting fireflies with a fluorescein value higher than that of the fireflies to form a dynamic decision domain within the radius of the decision domain of each firefly, selecting the fireflies by roulette, and updating the positions of the fireflies; updating the radius of each firefly dynamic decision domain; judging whether the maximum iteration times is reached, and if so, terminating; otherwise, returning and continuously calculating the fitness parameter value of each firefly.
Compared with the prior art, the method has the remarkable advantages that (1) the traditional RBF neural network is optimized to be combined with the wireless sensor network, and the data fusion method carries out data fusion processing on the original information in each cluster, so that the network convergence is accelerated, the energy consumption of the sensor nodes is reduced, and the service life of the wireless sensor network is remarkably prolonged; (2) the method can combine any clustering routing protocol to realize data fusion, can effectively reduce the energy consumption of the wireless sensor network, and improves the survival time of the network.
Drawings
FIG. 1 is a schematic diagram of a wireless sensor network in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of a data fusion process according to an embodiment of the present invention;
FIG. 3 is a flow chart of an embodiment of the present invention.
Detailed Description
It is easily understood that, according to the technical solution of the present invention, a person skilled in the art can imagine various embodiments of the wireless sensor network data fusion method of the present invention without changing the essential spirit of the present invention. Therefore, the following detailed description and the accompanying drawings are merely illustrative of the technical aspects of the present invention, and should not be construed as all of the present invention or as limitations or limitations on the technical aspects of the present invention.
According to the wireless sensor network data fusion method for optimizing the RBF neural network based on the firefly algorithm, each sensor node performs primary processing on the acquired data according to the neuron function of an input layer to obtain a small amount of characteristic data, and then sends the characteristic data to the cluster head node of the cluster where the sensor node is located; the cluster head node further processes the characteristic data according to the hidden layer neuron function and the output layer neuron function to obtain the final data to be transmitted, namely the fused data; and the cluster head node sends the fused data to the sink node. From the whole view of the wireless sensor network, the cluster member nodes, i.e. each sensor node, are equivalent to neurons of an input layer, the cluster head nodes are hidden layer neurons playing a role in convergence, and the whole wireless sensor network can be regarded as a complex nervous system. The method specifically comprises the following steps:
step one, sensor node clustering and cluster head node selection in wireless sensor network
1.1 select cluster head node. In the initial stage of each round of clusters, each sensor node randomly generates a number between [0,1], and if the number is smaller than a set threshold value T (n), the corresponding sensor node is selected as a cluster head, so that a message of becoming the cluster head is broadcasted. And when the sensor node of the cluster head is over, the threshold value T (n) is set to be 0. The threshold value t (n) is represented by the following formula:
wherein, P represents the percentage of the number of the cluster head nodes to the number of all the sensor nodes in the wireless sensor network, r represents the number of 'rounds' of selecting the current cluster head, n is the number of the sensor nodes, G represents a set, and the elements in the set are the sensor nodes of which the cluster heads are not selected in the 1/P round.
1.2 after selecting the cluster head node, the cluster head node informs other sensor nodes which are not used as the cluster head node in the whole wireless sensor network of the information that the sensor nodes become the cluster head node through broadcasting, and the other sensor nodes which are not used as the cluster head node decide to join the corresponding cluster head node according to the strength of the received signal so as to form a cluster set and inform the joined cluster head node;
1.3 the cluster head node establishes a Time Division Multiple Access (TDMA) communication scheme according to the number of the added sensor nodes, allocates a certain communication time slot for each sensor node in the cluster, and sends the communication scheme to the sensor nodes in the cluster. The sensor nodes in the cluster can send data to the cluster head node only in own communication time slot, and in order to save the limited energy of the sensor nodes, communication modules of the sensor nodes are set to be in a dormant state at other time;
and 1.4, entering the next round of data fusion after a period of time, reselecting the cluster heads, and keeping the energy consumption balance of the sensor nodes.
Thus, the cluster-based wireless sensor network shown in fig. 1 is constructed.
To further illustrate how data is transmitted in the wireless sensor network, taking the clustered wireless sensor network as an example, fig. 2 shows a process of data fusion of the wireless sensor network, (X1, X2, X3 … Xn) refers to data collected by member nodes in a cluster, (Y1, Y2, Y3 … Ym) refers to data transmitted to a sink node, and w is a connection weight between a hidden layer and an output layer. FIG. 3 is a technical flow diagram of a specific embodiment:
step two, fuzzy clustering is carried out by using a firefly algorithm, and the specific process of optimizing the RBF neural network is as follows
2.1 calculating the membership of the data object to each cluster center, in firefly fuzzy clustering, giving a data set X ═ { X ═ X1,x2,…xi…xnIn which xiFor a data object containing d attributes, each firefly is composed of c clustering centers, the position of each firefly is represented by the clustering center, and the position of each firefly is vector V ═ V1,v2,…vi…vc) Wherein v isiIs the ith cluster center, uijRepresenting a data object xiMembership to vjDegree of membership of, U ═ Uij) Is a membership matrix, m fuzzy weight coefficients, wherein the membership calculation formula is shown as the following;
2.2 calculating the fitness parameter value of each firefly, wherein the calculation formula is as follows:
and updating the fluorescein value of each firefly, wherein the calculation formula is as follows:
li(t)＝(1-ρ)li(t-1)+γJ(xi(t))
wherein li(t) is fluorescein of the ith firefly of the tth generation, n is the number of data in the data set, n iscIs the number of clustered samples, yiFor the ith sample, J (x)i(t)) represents all data to the cluster center cj(t) (j is the minimum value of 1,2, …, n), the optimal result of clustering is that the fitness function of all firefly groups takes the minimum value, xi(t) represents the position of the ith firefly in the tth generation, J (x)i(t)) fitness function value transformationIs fluorescein, wherein rho and gamma are parameters for controlling the fluorescein value and evaluating the function value respectively, and the value is between 0 and 1.
2.3 in the radius of the decision domain of each firefly, selecting the firefly with the value higher than the autofluorescence value to form a dynamic decision domain, and calculating the probability of movement of each firefly, wherein the calculation formula is as follows:
and updating the position of the firefly, the new position of the firefly being xi(t +1), the calculation formula is as follows
Wherein, Pij(t) is the probability of movement of each firefly j, d, into the decision domainij(t) is the distance between the generation t firefly i and firefly j,is the dynamic decision domain radius of the t-th generation firefly i, lj(t) is the fluorescein value of the dynamic decision domain firefly j selected by probability, Ni(t) is the dynamic decision domain of the t-th generation firefly i.
2.4 updating the dynamic decision domain radius of each firefly. The radius of the dynamic decision domain of the fireflies depends on the change of the radius of the current dynamic decision domain and the individual perception radius, and the method for updating the radius of the dynamic decision domain of each firefly is shown as the following formula:
wherein,is the sensing radius, r, of the t-th generation firefly isIndicating fluorescent screenInitial radius of perception of fire, β denotes dynamic decision Domain update factor, ntInitial threshold, N, representing dynamic decision Domaini(t) | represents the number of fireflies within the dynamic decision domain.
2.5 judging whether the maximum iteration times is reached, and if so, terminating; otherwise, go to step 2.2.
Step three, training the weight value between the hidden layer and the output layer of the RBF neural network
3.1 computing the output matrix phi of the hidden layer, where N column vectors of the output matrix phi Form an N-dimensional Euclidean space
3.2 calculating the output weight of the network by a pseudo-inverse method, and obtaining the output error of the sample at the moment; if the error is less than the target value, terminating the algorithm, otherwise performing the gray-Schmidt orthogonalization on the remaining N-1 vectors in the previous step to make the vectors orthogonal to E1 to obtain
3.3 finding the maximum projection with the output layer data ySelecting a sample corresponding to the data y of the input layer to be input into a 2 nd data center; calculating an output weight and a training error, and judging whether to terminate the algorithm;
3.4 repeating the steps 3.1-3.3, so that the training error of the network is smaller than a given value, and the weight training is finished, which is an important parameter for balancing the accuracy and complexity of the final network.
Step four, fusing the training data of the neural network by the sink node of the wireless sensor network
4.1 the cluster head node transmits the sensor node information table in the cluster to the sink node;
4.2, the sink node constructs an RBF neural network according to the cluster head and the information of the sensor nodes in the cluster;
4.3 the RBF neural network searches a sample database, collects samples matched with the cluster member information for training, and then generates neural network parameters of corresponding clusters;
4.4 the convergent node sends the parameters of each neuron of the firefly-optimized RBF neural network to corresponding sensor nodes, including cluster head nodes and member nodes;
4.5 after the stable operation of clustering, the cluster head node fuses the received information and transmits the fused data to the sink node. Historical records generated during the operation of the wireless sensor network can also be added to the sample database.
Claims (4)
1. A wireless sensor network data fusion method is characterized in that each sensor node performs primary processing on acquired data according to an input layer neuron function to obtain a small amount of characteristic data, and then sends the characteristic data to a cluster head node of a cluster where the sensor node is located; the cluster head node further processes the characteristic data according to the hidden layer neuron function and the output layer neuron function to obtain fused data; and the cluster head node sends the fused data to the sink node.
2. The method for fusing data in a wireless sensor network according to claim 1, comprising the steps of:
2.1 the cluster head transmits the sensor node information table in the cluster to the sink node;
2.2, constructing an RBF neural network by the sink node according to the cluster head and the information of the sensor nodes in the cluster;
2.3, the RBF neural network retrieves a sample database, collects samples matched with the cluster member information for training, and then generates neural network parameters of corresponding clusters;
2.4 the convergent node sends the parameters of each neuron of the firefly-optimized RBF neural network to the corresponding sensor node;
2.5 after the stable operation of clustering, the cluster head fuses the received information and transmits the fused data to the sink node.
3. The method for fusing data in a wireless sensor network according to claim 2, wherein the method for selecting cluster heads and clustering sensor nodes in the wireless sensor network comprises:
3.1 in the initial stage of each round of clusters, each sensor node randomly generates a value between [0,1], and if the value is smaller than a set threshold value T (n), the sensor node is used as a cluster head, wherein the threshold value T (n) of the sensor node which has already passed through the cluster head is 0;
3.2 after selecting the cluster head, the cluster head informs other sensor nodes which are not used as the cluster head of the information that the sensor nodes become the cluster head nodes through broadcasting, and the other sensor nodes which are not used as the cluster head are added into the corresponding cluster head according to the strength of the received signal so as to form a cluster set;
3.3 the cluster head establishes a time division multiple access communication scheme according to the number of the added sensor nodes, a certain communication time slot is allocated to each sensor node in the cluster, and the sensor nodes in the cluster send data to the cluster head in the communication time slot allocated to the sensor nodes.
4. The method for fusing data in a wireless sensor network according to claim 3, wherein the whole wireless sensor network is used as an RBF neural system, each sensor node is used as a neuron of an input layer, a cluster head is used as a hidden layer neuron, and a firefly algorithm is used to perform fuzzy clustering to determine a radial base center and a base width of the neural network, specifically:
4.1 calculating the membership degree of the data object to each clustering center;
4.2 calculating the fitness parameter value of each firefly and updating the fluorescein value of each firefly;
4.3 selecting the fireflies with the fluorescein value higher than the self-fireflies within the radius of the decision domain of each firefly to form a dynamic decision domain, selecting the fireflies by roulette, and updating the positions of the fireflies;
4.4, updating the radius of each firefly dynamic decision domain;
4.5 judging whether the maximum iteration times is reached, and if so, terminating; otherwise go to step 4.2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610197432.5A CN107295453A (en) | 2016-03-31 | 2016-03-31 | A kind of wireless sensor network data fusion method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610197432.5A CN107295453A (en) | 2016-03-31 | 2016-03-31 | A kind of wireless sensor network data fusion method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107295453A true CN107295453A (en) | 2017-10-24 |
Family
ID=60086828
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610197432.5A Pending CN107295453A (en) | 2016-03-31 | 2016-03-31 | A kind of wireless sensor network data fusion method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107295453A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107911804A (en) * | 2017-12-30 | 2018-04-13 | 天津科技大学 | A kind of wireless sensor network data fusion method |
| CN108512754A (en) * | 2018-03-23 | 2018-09-07 | 南京邮电大学 | A kind of wireless sense network cluster algorithm based on mobile sink |
| CN109640283A (en) * | 2018-12-28 | 2019-04-16 | 北京航天测控技术有限公司 | A kind of low-consumption wireless sensing network design method based on self energizing technology |
| CN110161861A (en) * | 2019-05-30 | 2019-08-23 | 上海航天测控通信研究所 | Aircraft ad hoc network route decision method and device based on fuzzy neural network |
| CN111970218A (en) * | 2020-08-27 | 2020-11-20 | 泰山学院 | Method for carrying out communication automatic modulation recognition based on deep multi-hop network |
| CN112188518A (en) * | 2020-09-07 | 2021-01-05 | 北京燧昀科技有限公司 | Sensor node communication optimization method and device and readable storage medium |
| CN112911599A (en) * | 2021-01-20 | 2021-06-04 | 沈阳化工大学 | Low-energy-consumption data fusion recessive method supporting integrity verification of wireless sensor network |
| CN114465909A (en) * | 2022-02-09 | 2022-05-10 | 哈尔滨工业大学 | Intelligent sensing edge calculation fusion nano networking structure |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835237A (en) * | 2010-05-14 | 2010-09-15 | 南京邮电大学 | Data aggregation method in wireless sensor network |
| CN102238705A (en) * | 2011-07-04 | 2011-11-09 | 南京邮电大学 | Wireless sensor network topology control method based on artificial neural network (ANN) |
| CN103338494A (en) * | 2013-07-04 | 2013-10-02 | 东南大学 | Heterogenous cluster routing method of wireless sensor network based on energy collection |
| CN103686925A (en) * | 2013-11-22 | 2014-03-26 | 天津工业大学 | Multi-hopping clustering fusion router of wireless sensing monitoring network for water environment |
| CN104578051A (en) * | 2014-12-28 | 2015-04-29 | 张海梁 | Power distribution network state estimation method based on firefly algorithm |
| CN105430598A (en) * | 2015-11-04 | 2016-03-23 | 刘运成 | Layered data transmission method and device of wireless sensor network |
-
2016
- 2016-03-31 CN CN201610197432.5A patent/CN107295453A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101835237A (en) * | 2010-05-14 | 2010-09-15 | 南京邮电大学 | Data aggregation method in wireless sensor network |
| CN102238705A (en) * | 2011-07-04 | 2011-11-09 | 南京邮电大学 | Wireless sensor network topology control method based on artificial neural network (ANN) |
| CN103338494A (en) * | 2013-07-04 | 2013-10-02 | 东南大学 | Heterogenous cluster routing method of wireless sensor network based on energy collection |
| CN103686925A (en) * | 2013-11-22 | 2014-03-26 | 天津工业大学 | Multi-hopping clustering fusion router of wireless sensing monitoring network for water environment |
| CN104578051A (en) * | 2014-12-28 | 2015-04-29 | 张海梁 | Power distribution network state estimation method based on firefly algorithm |
| CN105430598A (en) * | 2015-11-04 | 2016-03-23 | 刘运成 | Layered data transmission method and device of wireless sensor network |
Non-Patent Citations (3)
| Title |
|---|
| MING-HUWI HORNG ET AL: "Firefly Meta-Heuristic Algorithm for Training the Radial Basis Function Network for Data Classification and Disease Diagnosis", 《THEORY AND NEW APPLICATIONS OF SWARM INTELLIGENCE》 * |
| 李斌: "基于WSN的分层路由算法研究", 《扬州大学硕士学位论文》 * |
| 林睦纲 刘芳菊 童小娇: "一种基于萤火虫算法的模糊聚类方法", 《计算机工程与应用》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107911804A (en) * | 2017-12-30 | 2018-04-13 | 天津科技大学 | A kind of wireless sensor network data fusion method |
| CN108512754A (en) * | 2018-03-23 | 2018-09-07 | 南京邮电大学 | A kind of wireless sense network cluster algorithm based on mobile sink |
| CN108512754B (en) * | 2018-03-23 | 2020-12-01 | 南京邮电大学 | Wireless sensor network clustering method based on mobile sink |
| CN109640283A (en) * | 2018-12-28 | 2019-04-16 | 北京航天测控技术有限公司 | A kind of low-consumption wireless sensing network design method based on self energizing technology |
| CN110161861A (en) * | 2019-05-30 | 2019-08-23 | 上海航天测控通信研究所 | Aircraft ad hoc network route decision method and device based on fuzzy neural network |
| CN110161861B (en) * | 2019-05-30 | 2022-05-27 | 上海航天测控通信研究所 | Aircraft ad hoc network routing decision method and device based on fuzzy neural network |
| CN111970218B (en) * | 2020-08-27 | 2021-09-14 | 泰山学院 | Method for carrying out communication automatic modulation recognition based on deep multi-hop network |
| CN111970218A (en) * | 2020-08-27 | 2020-11-20 | 泰山学院 | Method for carrying out communication automatic modulation recognition based on deep multi-hop network |
| CN112188518A (en) * | 2020-09-07 | 2021-01-05 | 北京燧昀科技有限公司 | Sensor node communication optimization method and device and readable storage medium |
| CN112188518B (en) * | 2020-09-07 | 2024-02-13 | 北京燧昀科技有限公司 | Sensor node communication optimization method and device and readable storage medium |
| CN112911599A (en) * | 2021-01-20 | 2021-06-04 | 沈阳化工大学 | Low-energy-consumption data fusion recessive method supporting integrity verification of wireless sensor network |
| CN114465909A (en) * | 2022-02-09 | 2022-05-10 | 哈尔滨工业大学 | Intelligent sensing edge calculation fusion nano networking structure |
| CN114465909B (en) * | 2022-02-09 | 2024-03-22 | 哈尔滨工业大学 | Intelligent perception edge calculation fusion nano networking device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107295453A (en) | A kind of wireless sensor network data fusion method | |
| Wang et al. | Genetic algorithm for energy-efficient clustering and routing in wireless sensor networks | |
| Chen et al. | iRAF: A deep reinforcement learning approach for collaborative mobile edge computing IoT networks | |
| Hussain et al. | Genetic algorithm for hierarchical wireless sensor networks. | |
| Cao et al. | Swarm intelligence-based performance optimization for mobile wireless sensor networks: survey, challenges, and future directions | |
| CN112491712B (en) | Data packet routing algorithm based on multi-agent deep reinforcement learning | |
| Romoozi et al. | A positioning method in wireless sensor networks using genetic algorithms | |
| CN102238705B (en) | Wireless sensor network topology control method based on artificial neural network (ANN) | |
| He et al. | Three-stage Stackelberg game enabled clustered federated learning in heterogeneous UAV swarms | |
| Wu et al. | Joint traffic control and multi-channel reassignment for core backbone network in SDN-IoT: a multi-agent deep reinforcement learning approach | |
| CN104135752B (en) | A kind of wireless sensor network cluster head node system of selection and cluster-dividing method | |
| Ajay et al. | Smart Spider Monkey Optimization (SSMO) for Energy‐Based Cluster‐Head Selection Adapted for Biomedical Engineering Applications | |
| Sanhaji et al. | Cluster head selection based on neural networks in wireless sensor networks | |
| Chithaluru et al. | Computational-intelligence-inspired adaptive opportunistic clustering approach for industrial IoT networks | |
| CN117042083A (en) | Distributed reliable transmission guarantee method for unmanned cluster networking | |
| CN106789320A (en) | A kind of multi-species cooperative method for optimizing wireless sensor network topology | |
| Punithavathi et al. | Hybrid BWO-IACO Algorithm for Cluster Based Routing in Wireless Sensor Networks. | |
| Li et al. | Fedvanet: Efficient federated learning with non-iid data for vehicular ad hoc networks | |
| Tuba et al. | Energy efficient sink placement in wireless sensor networks by brain storm optimization algorithm | |
| Agrawal et al. | Optimization of the selection of cluster‐head using fuzzy logic and harmony search in wireless sensor networks | |
| Guo et al. | A novel cluster-head selection algorithm based on hybrid genetic optimization for wireless sensor networks | |
| Wu et al. | Fedle: Federated learning client selection with lifespan extension for edge iot networks | |
| Darji et al. | Genetic algorithm for energy harvesting-wireless sensor networks | |
| CN113938978B (en) | Heterogeneous wireless sensor path finding method based on reinforcement learning | |
| Chen et al. | The contract net based task allocation algorithm for wireless sensor 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 |
Application publication date: 20171024 |
|
| RJ01 | Rejection of invention patent application after publication |