CN104837155A - Back propagation (BP) neural network type clustered sensor network data collection method - Google Patents
Back propagation (BP) neural network type clustered sensor network data collection method Download PDFInfo
- Publication number
- CN104837155A CN104837155A CN201510153642.XA CN201510153642A CN104837155A CN 104837155 A CN104837155 A CN 104837155A CN 201510153642 A CN201510153642 A CN 201510153642A CN 104837155 A CN104837155 A CN 104837155A
- Authority
- CN
- China
- Prior art keywords
- network
- node
- cluster
- central point
- neural net
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013480 data collection Methods 0.000 title claims abstract description 13
- 238000013528 artificial neural network Methods 0.000 title abstract description 5
- 230000005540 biological transmission Effects 0.000 claims abstract description 18
- 241000854291 Dianthus carthusianorum Species 0.000 claims abstract description 15
- 238000003062 neural network model Methods 0.000 claims abstract description 11
- 230000001537 neural effect Effects 0.000 claims description 26
- 230000009191 jumping Effects 0.000 claims description 21
- 238000013481 data capture Methods 0.000 claims description 10
- 210000002364 input neuron Anatomy 0.000 claims description 7
- 230000003750 conditioning effect Effects 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000004807 localization Effects 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 238000009331 sowing Methods 0.000 claims description 2
- 238000005265 energy consumption Methods 0.000 abstract description 3
- 230000002035 prolonged effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000005284 excitation Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
-
- 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
- H04W52/0203—Power saving arrangements in the radio access network or backbone network of wireless communication 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
Abstract
The invention provides a back propagation (BP) neural network type clustered sensor network data collection method. A monitored wireless sensor network is initialized first, the geographic center position of the network is searched according to the GPS information of a node, a network cluster-head node is elected according to the positional information of the node, and a cluster is constructed, then a back propagation neural network model is established by a completed clustered network, finally, the clustering number of the network is dynamically adjusted according to the total transmission hop count of the network until the network reaches a stable state and has an optimal cluster-head number. The back propagation neural network type clustered sensor network data collection method is suitable for networks in different scales, and can collect network data with an optimal clustering number, and is advantaged in that the energy consumption of the network is reduced, the service cycle of the network can be prolonged, and network delay can be reduced and the like.
Description
Technical field
The present invention is mainly concerned with wireless communication field, is related specifically to wireless sensor network data assembling sphere.
Background technology
Wireless sensor network (WSN, Wireless Sensor Network) technology obtains wide application under the overall background of Current wireless communication technology develop rapidly.This network is generally made up of the sensor node of a large amount of energy constraint and one or several base station, and each sensor node random placement is needing the region of monitoring, forms self-organizing network perception and collects data.Sub-clustering type sensing network by bunch in units of carry out Data Collection, first network sensor node is divided into different bunches, elects leader cluster node fused data in bunch, secondly fused data is transferred to sink node by multiple bunches of heads, completes Data Collection.
BP neural net (Back Propagation Neural Network) is a kind of multilayer feedforward network adopting back propagation learning, is a kind of machine learning algorithm having supervision.BP neural network algorithm model is made up of an input layer, an output layer and one or more hidden layer usually.Neural net can by being obtained the output data required by specific input after training.The basic thought of BP algorithm is for input data, after weights, threshold value and excitation function computing, obtains exporting data, then compare with expectation sample data, by error back propagation, carry out weights, adjusting thresholds, network is exported consistent with desired output.
If sub-clustering quantity is very few in cluster-dividing sensing network, data are passed to leader cluster node and need transmit through multihop network by many ordinary nodes, and this will certainly increase total jumping figure of network, and the energy of loss sensor node makes Network morals greatly reduce; If sub-clustering quantity is too much, each leader cluster node needs responsible fusion treatment data and passes to sink node, and this will add the disposed of in its entirety amount of macroreticular, loss leader cluster node energy, makes this that Network morals also can be made greatly to reduce.So, need a kind of effective sub-clustering number adjusting method badly, obtain optimum sub-clustering number, extend network lifecycle.Based on this, devise the cluster-dividing sensing network method of data capture of a kind BP neural net.
Summary of the invention
The invention discloses the cluster-dividing sensing network method of data capture of a kind BP neural net, main application BP neural net adjusts sub-clustering quantity optimum in cluster-dividing sensing network, network is made to carry out Data Collection with optimum sub-clustering quantity, reduce the time delay of network, reduce the energy consumption of network, extend Network morals.
According to application background of the present invention, the cluster-dividing sensing network method of data capture of a kind BP neural net is provided, comprises the following steps:
The layout of step 1, network scenarios and the initialization process of network;
1) in the quantity of sowing that the region needing to monitor is random be
sensor node;
2) all the sensors node has identical primary power and transmission rate;
3) all the sensors node can obtain self geographical location information by localization methods such as GPS.
Step 2, obtain initial number according to the geographical location information of node and be set as
central point
.
Step 3, to be set as according to initial number
center position
, choose
individual leader cluster node, composition Cluster Networks, is characterized in that described clustering method is at least further comprising the steps of:
1) all distance center points are
within node be chosen as candidate cluster head node, wherein
for the transmission radius of node,
for the jumping figure of setting;
2) candidate cluster head node calculate self and central point distance size, each other broadcast such information, sort, be then elected as leader cluster node by apart from minimum candidate cluster head node.Leader cluster node ordinary node broadcast towards periphery comprises the jumping figure of its identity information, positional information and this information process, and the form of packets of information is
;
3) bunch head that ordinary node selects the jumping figure of information process in each leader cluster node minimum adds in its bunch, and network completes sub-clustering process.
Step 4, the network completed according to sub-clustering, is characterized in that described to set up BP neural network model at least further comprising the steps of:
1) in cluster structured, ordinary node is mapped in the input layer of BP neural net, serves as input neuron image data;
2) in cluster structured, leader cluster node is mapped in the hidden layer of BP neural net, is responsible for merging and transmitting data;
3) in cluster structured, sink node mapping, in the output layer of BP neural net, is responsible for receiving and deal with data;
4) data flow of input neuron, reaches output layer through hidden layer, and output layer to data analysis, and feeds back to network, so far, completes the foundation of BP neural network model.
Step 5, according to BP neural network model, dynamic conditioning is carried out to network, it is characterized in that described method of adjustment is at least further comprising the steps of:
1) if leader cluster node is dead, then again from candidate cluster head node, leader cluster node is reselected with beeline by center position;
2) sink node compares (wherein arranging the initial total jumping figure of network for infinitely great) according to total transmission jump number of front-wheel network and last round of transmission jump number, if jumping figure reduces, then continues with step-length
increase the quantity of central point; If jumping figure increases, then the central point quantity of setting network takes turns central point quantity on being, network carries out Data Collection with a bunch head number for this quantity, and network reaches stable state.
Compared with prior art, the advantage of this method is:
1, BP neural net is combined with cluster-dividing sensing network, the sub-clustering quantity of dynamic conditioning different scales network, data can be collected with optimum bunch head number by training network, reduce network power consumption, extend Network morals;
2, the sub-clustering of optimized network, can reduce total transmission jump number of boundary node and network, reduces the overall time delay of network.
Accompanying drawing explanation
Fig. 1 is flow chart of the present invention;
Fig. 2 is center position figure of the present invention;
Fig. 3 is 4 central point sub-clustering schematic diagrames of the present invention;
Fig. 4 is BP neural network model figure of the present invention;
Fig. 5 is 5 central point sub-clustering schematic diagrames of the present invention;
Fig. 6 is simulation result figure of the present invention.
Embodiment
As shown in Figure 1, the concrete steps of technical solution of the present invention are:
Step 1, as shown in Figure 2, the layout of network scenarios and the initialization process of network:
1) need monitoring region random sow sensor node and 1 the sink node that quantity is 51;
2) all the sensors node has identical primary power and transmission rate;
3) all the sensors node can obtain self geographical location information by localization methods such as GPS.
Step 2, obtain according to the geographical location information of node the network geographical central point that initial number is set as 4, as shown in Figure 2, the GPS location of 4 central points is
.
Step 3, to be set as according to initial number 4 center position
, as shown in Figure 3, choose 4 leader cluster nodes, composition Cluster Networks, is characterized in that described clustering method is at least further comprising the steps of:
1) node within all distance center point 1 jumpings is chosen as candidate cluster head node;
2) candidate cluster head node calculate self and central point distance size, each other broadcast such information, sort, be then elected as leader cluster node by apart from minimum candidate cluster head node.Leader cluster node ordinary node broadcast towards periphery comprises the jumping figure of its identity information, positional information and this information process, and the form of packets of information is
;
3) the ordinary node bunch head (namely in packets of information of selecting the jumping figure of information process in each leader cluster node minimum
size) add in its bunch, network completes sub-clustering process.
Step 4, the network completed according to sub-clustering, as shown in Figure 3 and Figure 4, is characterized in that described to set up BP neural network model at least further comprising the steps of:
1) in cluster structured, ordinary node is mapped in the input layer of BP neural net, serves as input neuron image data, and the data collected, by shortest path first, are sent to leader cluster node by each ordinary node;
2) in cluster structured, leader cluster node is mapped in the hidden layer of BP neural net, is responsible for merging and transmitting data, by building the routing tree of an all leader cluster node of connection and sink node, by network collection to data pass to sink node;
3) in cluster structured, sink node mapping, in the output layer of BP neural net, is responsible for receiving and deal with data, sink node by the routing tree that builds to leader cluster node feedback information;
4) data flow of input neuron, reaches output layer through hidden layer, and output layer to data analysis, and feeds back to network, so far, completes the foundation of BP neural network model.
Step 5, according to BP neural network model, as shown in Figure 5, dynamic conditioning is carried out to network, it is characterized in that described method of adjustment is at least further comprising the steps of:
1) if leader cluster node is dead, then again from candidate cluster head node, leader cluster node is reselected with beeline by center position;
2) sink node compares (wherein arranging the initial total jumping figure of network for infinitely great) according to total transmission jump number of front-wheel network and last round of transmission jump number, if jumping figure reduces, then continues with step-length
increase the quantity of central point, for Fig. 5, increase the quantity of network center's point with step-length 1,
, network is divided into 5 bunches and carries out Data Collection; If jumping figure increases, then the central point quantity of setting network takes turns central point quantity on being, network carries out Data Collection with a bunch head number for this quantity, and network reaches stable state.
In order to verify validity of the present invention, this method is tested by Matlab emulation platform, and by 400 node deployments in guarded region, base station coordinates is
.Carry out Data Collection and total transmission jump number of computing network with different sub-clustering quantity to network, as can be seen from Figure 6, when network cluster dividing quantity increases, the transmission jump number of network reduces; After sub-clustering quantity reaches a value determined, along with the increase of sub-clustering quantity, the transmission jump number of network increases.In sum, in network, there is the optimal value of sub-clustering quantity, carry out Data Collection with this sub-clustering quantity, network energy consumption can be reduced, extend network lifecycle, reduce network delay.
Claims (6)
1. the cluster-dividing sensing network method of data capture of class BP neural net, is characterized in that described method at least comprises the following steps:
The layout of step 1, network scenarios and the initialization process of network;
Step 2, GPS information according to node, and the central point quantity of initializing set
(
number of nodes in network), find the geographic center position of network
;
Step 3, network are according to the geographic center position election bunch head obtained in step 2, and the node nearest apart from each central point will be chosen as leader cluster node, and ordinary node is selected to add in different bunches according to the positional information of acquired leader cluster node;
Step 4, obtain according to step 3 cluster structuredly set up BP neural network model, ordinary node serves as the input neuron image data of neural net, the hidden layer that leader cluster node serves as neural net carries out data fusion and transmission, and the output layer that sink node serves as neural net receives deal with data;
If step 5 this to take turns middle leader cluster node dead, then jump procedure 3, reselects leader cluster node with beeline again by geographic center point position from candidate cluster head node;
Hop count information, according to the total transmission jump number of network, is fed back to the whole network by step 6, output layer sink node, if jumping figure reduces, with step-length
increase the quantity jump procedure 2 of central point; If jumping figure increases, then the central point quantity of setting network takes turns central point quantity on being, network carries out Data Collection with a bunch head number for this quantity, and network reaches stable state.
2. the cluster-dividing sensing network method of data capture of class BP neural net according to claim 1, it is characterized in that described network scenarios arrange and netinit process at least further comprising the steps of:
1) in the quantity of sowing that the region needing to monitor is random be
sensor node;
2) all the sensors node has identical primary power and transmission rate;
3) all the sensors node can obtain self geographical location information by localization methods such as GPS.
3. the cluster-dividing sensing network method of data capture of class BP neural net according to claim 1 and 2, is characterized in that obtaining initial number according to the geographical location information of node is set as
central point
.
4. the cluster-dividing sensing network method of data capture of class BP neural net according to claim 1, is characterized in that described clustering method is at least further comprising the steps of:
1) all distance center points are
within node be chosen as candidate cluster head node, wherein
for the transmission radius of node,
for the jumping figure of setting;
2) candidate cluster head node calculate self and central point distance size, each other broadcast such information, sort, be then elected as leader cluster node by apart from minimum candidate cluster head node; Leader cluster node ordinary node broadcast towards periphery comprises the jumping figure of its identity information, positional information and this information process, and the form of packets of information is
;
3) bunch head that ordinary node selects the jumping figure of information process in each leader cluster node minimum adds in its bunch, and network completes sub-clustering process.
5. the cluster-dividing sensing network method of data capture of the class BP neural net according to claim 1 or 4, is characterized in that described to set up BP neural network model at least further comprising the steps of:
1) in cluster structured, ordinary node is mapped in the input layer of BP neural net, serves as input neuron image data;
2) in cluster structured, leader cluster node is mapped in the hidden layer of BP neural net, is responsible for merging and transmitting data;
3) in cluster structured, sink node mapping, in the output layer of BP neural net, is responsible for receiving and deal with data;
4) data flow of input neuron, reaches output layer through hidden layer, and output layer to data analysis, and feeds back to network, so far, completes the foundation of BP neural network model.
6. the cluster-dividing sensing network method of data capture of class BP neural net according to claim 1, is characterized in that described dynamic conditioning central point quantity is at least further comprising the steps of:
1) if leader cluster node is dead, then again from candidate cluster head node, leader cluster node is reselected with beeline by center position;
2) sink node compares (wherein arranging the initial total jumping figure of network for infinitely great) according to total transmission jump number of front-wheel network and last round of transmission jump number, if jumping figure reduces, then continues with step-length
increase the quantity of central point; If jumping figure increases, then the central point quantity of setting network takes turns central point quantity on being, network carries out Data Collection with a bunch head number for this quantity, and network reaches stable state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153642.XA CN104837155B (en) | 2015-04-02 | 2015-04-02 | The cluster-dividing sensing network method of data capture of class BP neutral net |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510153642.XA CN104837155B (en) | 2015-04-02 | 2015-04-02 | The cluster-dividing sensing network method of data capture of class BP neutral net |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104837155A true CN104837155A (en) | 2015-08-12 |
| CN104837155B CN104837155B (en) | 2016-08-31 |
Family
ID=53814733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510153642.XA Expired - Fee Related CN104837155B (en) | 2015-04-02 | 2015-04-02 | The cluster-dividing sensing network method of data capture of class BP neutral net |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104837155B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647292A (en) * | 2018-05-07 | 2018-10-12 | 前海梧桐（深圳）数据有限公司 | Enterprise's property sort computational methods based on neural network algorithm and system |
| CN109032225A (en) * | 2018-09-27 | 2018-12-18 | 东莞幻鸟新材料有限公司 | Greenhouse intelligent control system |
| 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 |
| CN110851265A (en) * | 2018-07-25 | 2020-02-28 | 华为技术有限公司 | Data processing method, related equipment and system |
| CN111935747A (en) * | 2020-08-17 | 2020-11-13 | 南昌航空大学 | Method for predicting link quality of wireless sensor network by adopting GRU (generalized regression Unit) |
| CN113452629A (en) * | 2021-07-15 | 2021-09-28 | 深圳市高德信通信股份有限公司 | Route switching system |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100090823A1 (en) * | 2008-10-09 | 2010-04-15 | Electronics And Telecommunications Research Institute | Hybrid clustering based data aggregation method for multi-target tracking in wireless sensor network |
| CN102244882A (en) * | 2011-08-15 | 2011-11-16 | 南通大学 | Mobility-agent-based intelligent data acquisition method for wireless sensor network |
| CN103619021A (en) * | 2013-12-10 | 2014-03-05 | 天津工业大学 | Neural network-based intrusion detection algorithm for wireless sensor network |
-
2015
- 2015-04-02 CN CN201510153642.XA patent/CN104837155B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100090823A1 (en) * | 2008-10-09 | 2010-04-15 | Electronics And Telecommunications Research Institute | Hybrid clustering based data aggregation method for multi-target tracking in wireless sensor network |
| CN102244882A (en) * | 2011-08-15 | 2011-11-16 | 南通大学 | Mobility-agent-based intelligent data acquisition method for wireless sensor network |
| CN103619021A (en) * | 2013-12-10 | 2014-03-05 | 天津工业大学 | Neural network-based intrusion detection algorithm for wireless sensor network |
Non-Patent Citations (1)
| Title |
|---|
| 孔玉静: "基于BP神经网络的无线传感器网络路由协议的研究", 《传感技术学报》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647292A (en) * | 2018-05-07 | 2018-10-12 | 前海梧桐（深圳）数据有限公司 | Enterprise's property sort computational methods based on neural network algorithm and system |
| CN110851265A (en) * | 2018-07-25 | 2020-02-28 | 华为技术有限公司 | Data processing method, related equipment and system |
| CN110851265B (en) * | 2018-07-25 | 2023-09-08 | 华为云计算技术有限公司 | Data processing method, related equipment and system |
| CN109032225A (en) * | 2018-09-27 | 2018-12-18 | 东莞幻鸟新材料有限公司 | Greenhouse intelligent control system |
| CN109032225B (en) * | 2018-09-27 | 2020-07-14 | 长治市佳垚农业开发有限公司 | Greenhouse intelligent control system |
| 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 |
| CN111935747A (en) * | 2020-08-17 | 2020-11-13 | 南昌航空大学 | Method for predicting link quality of wireless sensor network by adopting GRU (generalized regression Unit) |
| CN113452629A (en) * | 2021-07-15 | 2021-09-28 | 深圳市高德信通信股份有限公司 | Route switching system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104837155B (en) | 2016-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104837155A (en) | Back propagation (BP) neural network type clustered sensor network data collection method | |
| Piltyay et al. | Wireless sensor network connectivity in heterogeneous 5G mobile systems | |
| Takaishi et al. | Toward energy efficient big data gathering in densely distributed sensor networks | |
| Rezaeipanah et al. | A Hybrid Approach for Prolonging Lifetime of Wireless Sensor Networks Using Genetic Algorithm and Online Clustering. | |
| Malik et al. | Leveraging fog computing for sustainable smart farming using distributed simulation | |
| CN102413509A (en) | Construction method of time-delay-constrained energy consumption balance data acquisition tree in WSN (Wireless Sensor Network) | |
| CN107360612B (en) | A kind of data transmission method of the wireless sensor network based on ant colony multipath | |
| CN105959987A (en) | Data fusion algorithm for improving energy utilization rate and service performance of wireless sensor network | |
| CN103228023A (en) | Wireless sensor network clustering routing method based on particle swarm optimization and ant colony optimization | |
| CN109936865A (en) | A kind of mobile sink paths planning method based on deeply learning algorithm | |
| Liu et al. | Wireless distributed learning: A new hybrid split and federated learning approach | |
| Yang et al. | Path planning of unmanned aerial vehicles for farmland information monitoring based on WSN | |
| CN103874158A (en) | Novel clustering routing algorithm | |
| CN113411766B (en) | Intelligent Internet of things comprehensive sensing system and method | |
| CN102595546A (en) | Wireless sensor actuator network data collecting and clustering method based on event driving | |
| CN110113807A (en) | Based on the node dormancy dispatching method of data similarity in wireless sensor network | |
| Akbaş et al. | A preferential attachment model for primate social networks | |
| Bomnale et al. | Power optimization in wireless sensor networks | |
| Britto et al. | A hybrid soft computing: SGP clustering methodology for enhancing network lifetime in wireless multimedia sensor networks | |
| Abd Ellatief et al. | Energy efficient density-based clustering technique for wireless sensor network | |
| Rao et al. | Empirical study on energy-efficient IoT-based WSN routing protocols for smart agriculture system | |
| Mulyana et al. | Internet of Things (IoT) Device Management in Rural Areas to Support Precision Agriculture | |
| Xiao et al. | A new clustering routing algorithm for wsn based on brief artificial fish-school optimization and ant colony optimization | |
| Gil et al. | Analysis of topo-morphological influence of vineyards in the design of wireless sensor networks for smart viticultural management | |
| Fan et al. | A low energy algorithm of wireless sensor networks based on fractal dimension |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160831 |