CN111787592A - Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm - Google Patents
Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm Download PDFInfo
- Publication number
- CN111787592A CN111787592A CN202010607907.XA CN202010607907A CN111787592A CN 111787592 A CN111787592 A CN 111787592A CN 202010607907 A CN202010607907 A CN 202010607907A CN 111787592 A CN111787592 A CN 111787592A
- Authority
- CN
- China
- Prior art keywords
- node
- community
- nodes
- message
- algorithm
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/04—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/04—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources
- H04W40/10—Communication route or path selection, e.g. power-based or shortest path routing based on wireless node resources based on available power or energy
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/02—Communication route or path selection, e.g. power-based or shortest path routing
- H04W40/12—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality
- H04W40/14—Communication route or path selection, e.g. power-based or shortest path routing based on transmission quality or channel quality based on stability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W40/00—Communication routing or communication path finding
- H04W40/24—Connectivity information management, e.g. connectivity discovery or connectivity update
- H04W40/248—Connectivity information update
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to an opportunistic routing implementation method based on spectral clustering and a C4.5 algorithm. The invention mainly comprises the following steps: (1) an intimacy weight calculation method; (2) a sub-community partitioning method based on spectral clustering; (3) a messenger node identification model based on a C4.5 algorithm; (4) an opportunistic routing implementation method based on a close community and a decision tree algorithm. The nodes are clustered through spectral clustering, and when the source node and the destination node are in the same community, the information is transmitted based on simple flooding, so that the information transmission efficiency is improved. When the source node and the destination node are different communities, the messenger node is determined through the decision tree model, and the messenger node is used as a medium to transmit the message to the destination community, so that the cross-community transmission of the message is realized.
Description
Technical Field
The invention relates to the field of machine learning and the technical field of wireless communication, in particular to an opportunistic routing implementation method based on spectral clustering and a C4.5 algorithm.
Background
With the rise of 5G and the rapid development of wireless communication technology, more and more mobile terminal devices with small volume, low cost and short-distance communication capability are popularized on a large scale. The wireless communication network is widely applied to various extreme and challenging special environments such as underground, underwater, deep space, hills and the like due to the characteristics of flexible communication, simple deployment, low cost and the like. In these applications, however, the network may not be able to connect most of the time due to various reasons such as node movement, node sparsity, radio frequency shutdown, or signal attenuation due to obstacles. In such a network environment, the conventional MANET communication mode cannot be applied. The opportunistic network can effectively solve the problems due to a special communication mode of storage-carrying-forwarding, but because the topology of the opportunistic network changes dynamically, no relatively stable data transmission path exists between nodes. Therefore, implementing a routing protocol with good routing performance is one of the most challenging issues in opportunistic network research.
To overcome the problems of unpredictability and high mobility in opportunistic networks, many routing protocols have been proposed that attempt to exploit the mobility of the nodes themselves to assist in routing, most employing a flooding-based approach in which messages are propagated throughout the network with a limited time-to-live (TTL). A node helps a message to reach its destination by sending copies to other nodes during flooding. While flooding increases the probability of delivery, it requires high overhead and consumes many nodes of energy. Thus, for mobile nodes with limited energy, simple flooding is impractical.
With the development of artificial intelligence, the machine learning algorithm makes great progress in the aspect of researching and optimizing problems. Therefore, optimization improvement can be considered in the opportunity network field by combining a machine learning method, and the message is forwarded in a self-adaptive mode. At present, Spectral Clustering (SC) is a widely used clustering algorithm, and compared with the traditional K-Means algorithm, the spectral clustering algorithm has stronger adaptability to data distribution, is effective for processing sparse data clustering, and has a much smaller calculation amount. The C4.5 algorithm is a classification decision tree algorithm in a machine learning algorithm, is an important algorithm improved based on the ID3 algorithm, and has a good effect on the aspect of data classification. Therefore, the invention utilizes the close communities divided by spectral clustering and a 'messenger node' identification model constructed based on the C4.5 algorithm to assist the message forwarding in the opportunity network.
Disclosure of Invention
The invention provides an opportunistic routing implementation method based on spectral clustering and a C4.5 algorithm, which mainly comprises the following four contents:
(1) an intimacy weight calculation method;
(2) a sub-community partitioning method based on spectral clustering;
(3) a messenger node identification model based on a C4.5 algorithm;
(4) an opportunistic routing implementation method based on a close community and a decision tree algorithm.
The specific contents are as follows:
(1) and (4) calculating the intimacy weight.
Definition 1 the higher the intimacy between nodes, the easier it is considered to communicate. The invention takes the reciprocal of the average interval communication time between nodes in unit time as the intimacy. Its meaning means that the shorter the time for two nodes to wait for the next communication, the more intimate they are. The average inter-communication time is calculated by the following formula:
wherein Intervals(i,j)Represents the average interval communication time, delay _ time, between node i and node j(i,j,n)The nth interval duration of the node i and the node j is represented, and the count represents the total number of times of communication between the node i and the node j in unit time. The interval duration is equal to the communication starting time minus the last communication ending time.
The intimacy between nodes can be calculated by the following formula:
wherein λ(i,j)Representing the degree of closeness between node i and node j. If the communication between the nodes is performed only once in a unit time, the intimacy degree between the node pair is simply considered to be 0.
Considering the importance of the node communication frequency in unit time, the final affinity definition comprehensively considers the node communication frequency, and the specific formula is as follows:
Intimacy(i,j)＝count*λ(i,j)
wherein Intimacy(i,j)Representing the final affinity between node i and node j. And finally, calculating the intimacy between the nodes according to the formula, taking the intimacy as the weight of the intimacy, constructing an undirected weighted communication graph, and storing the communication graph information by using a matrix so as to analyze and mine important information such as community characteristics between the nodes.
(2) A sub-community division method based on spectral clustering.
Spectral Clustering (SC) is a graph theory-based Clustering method, and the purpose of Clustering is achieved by cutting a graph formed by all nodes, so that the sum of edge weights among different subgraphs after the graph is cut is as low as possible, and the sum of edge weights in the subgraphs is as high as possible. The invention divides the communication graph by adopting spectral clustering to construct a plurality of sub-communities. The method comprises the following specific steps:
constructing an adjacency matrix: and (3) acquiring the weight information of the edges in the communication graph obtained in the method (1) to construct an adjacent matrix W.
And (3) constructing a degree matrix: for any point v in the figureiIts degree diDefined as the sum of the weights of all edges connected to it, i.e.
Based on the constructed adjacency matrix, an n-dimensional degree matrix D is obtained by using the degrees of each point, wherein the n-dimensional degree matrix D is a diagonal matrix, and only the main diagonal has values and corresponds to the degrees of the ith point of the ith row.
The laplacian matrix is calculated and normalized: the Laplace matrix is defined as follows:
L＝D-W
the normalized laplacian matrix can be calculated by the following formula:
k for computing normalized Laplace matrix Q1The feature vector f corresponding to each feature value: the step skillfully converts the problem of graph cutting into the problem of characteristic values of a Laplace matrix, and relaxes the discrete clustering problem into continuous characteristic vectors, wherein the minimum series characteristic vectors correspond to the optimal series division method of the graph.
Finally, standardizing the matrixes formed by the characteristic vectors f corresponding to the characteristic vectors f according to rows to form n × k1The feature matrix F of the dimension. For each row in F as a k1N samples are clustered by input clustering method, and the clustering dimension is k2. To obtain clusters
A plurality of sub-communities is constructed.
(3) The messenger node recognition model is based on the C4.5 algorithm.
Due to the opportunistic network, nodes in the same community often meet with each other frequently, and message forwarding is facilitated. When the message is forwarded to a certain node, the message can be forwarded to other nodes in the community where the node is located, and the other nodes flood in the sub-community, so that the message transmission efficiency can be improved, and the message can be quickly transmitted to the target node. After obtaining the plurality of sub-communities in the method (2), if the source node and the destination node are in the same sub-community, the message can be successfully transmitted to the destination node with high probability only by simply flooding the community. If the source node and the destination node are not in the same community, and when the message needs to be transmitted across communities, messenger nodes which are free in a plurality of sub-communities need to be searched. Therefore, by acquiring some attribute characteristics of the nodes, a model capable of identifying the messenger nodes is constructed by using the C4.5 algorithm, and the messenger nodes are determined by using the model. The method comprises the following specific steps:
selecting characteristics: in an opportunistic network, the following attribute features tend to be of interest for determining "messenger nodes".
1) Node activity: representing the activity capabilities of the node. The number of neighbor nodes is measured by averaging the number of the neighbor nodes in a period of time;
2) node centrality: indicating the degree of importance of the node. And analyzing the node encounter history to obtain the type number of other nodes connected with the node. The more types, the larger the node center point;
3) node recency: establishing connection between the node and any other node based on the latest time;
4) node reliability: based on the ratio of the number of successful times of the past message transmission of the node to the total number of times;
5) node free buffer space: if there is little or no free cache space remaining, the chance of message delivery is small;
6) node transmission speed: the transmission speeds of different nodes are often inconsistent, and the faster the transmission speed is, the stronger the transmission capability of the node is;
7) node transmission range: the larger the transmission range is, the easier the node discovers the destination node;
8) node residual energy: each node consumes energy, and when the energy is consumed, the node falls into a dead halt state.
And (3) decision tree construction: the key issue in decision tree construction is which attributes are selected as root nodes, which attributes are internal nodes, and when to stop and get the target state, i.e., leaf nodes. The invention adopts C4.5 algorithm, and the information gain ratio of each attribute is calculated and compared to be used as the characteristic selection criterion. The method comprises the following specific steps:
training data preparation: based on the node communication history, the attribute characteristics of the node are calculated and counted, and the format is as follows.
| Numbering | Degree of liveness | Degree of centrality | Degree of recency | Degree of reliability | Free buffer | Speed of transmission | Transmission range | Residual energy | Free community |
| 1 | 5 | 8 | 3 | 0.2 | 10 | 20 | 10 | 50 | Whether or not |
| … | … | … | … | … | … | … | … | … | … |
| n | 10 | 8 | 5 | 0.6 | 50 | 15 | 10 | 100 | Is that |
And (3) information entropy calculation: in information theory, entropy is a measure of uncertainty in random variables. The larger the entropy, the greater the uncertainty of the random variable. The information entropy of each node attribute can be calculated by the following formula:
where Encopy (t) denotes the entropy of the information, pk|tRepresenting the probability that node t is class k.
And (3) information gain calculation: the information gain represents the degree of uncertainty reduction of the information of the class Y due to the knowledge of the attribute feature X, and can be calculated by the following formula:
gain (N, i) represents information Gain, N is a parent node, NkIs a child node, and i in Gain (N, i) is selected as the attribute of the N node.
And (3) information gain ratio calculation: the ID3 tends to select attributes that take a large number of values when computed. To avoid this problem, C4.5 is modified to select the attributes in the form of information gain ratio. The specific formula is as follows:
finally, according to the calculation result, selecting the attribute with the largest information gain ratio as a root node, and establishing child nodes according to different values of the attribute; and generating a new child node by using the same mode for each child node until the information gain ratio is small or no characteristic can be selected, and completing the construction of the decision tree.
(4) An opportunistic routing implementation method based on a close community and a decision tree algorithm.
The opportunistic routing implementation method based on the intimate community and the decision tree algorithm can be divided into 3 stages, namely a community division stage, a decision tree model training stage and a transmission stage. In the community division stage, all communication nodes are divided into a plurality of sub-communities by using spectral clustering based on the method (2). In the training stage of the decision tree model, a C4.5 algorithm is adopted based on the method (3), training data are collected, and a messenger node decision tree model capable of being identified is trained by obtaining some attribute characteristics of the nodes. In the transmission phase, two message transmission modes are adopted: messaging with and across communities. When the source node and the destination node are in the same community, the same-community message transmission mode is adopted: and when the source node meets the neighbor node, judging whether the neighbor node and the destination node are in the same community, if so, copying the forwarding message, otherwise, continuously moving the node. When the source node and the destination node are different from each other, a cross-community message transmission mode is adopted: and if the source node meets the neighbor node, judging whether the neighbor node and the destination node are in the same community, if so, copying the forwarding message, otherwise, judging whether the node is a messenger node based on the trained decision tree model, if so, copying the forwarding message, and otherwise, continuously moving the node.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The invention relates to an opportunistic routing implementation method based on spectral clustering and a C4.5 algorithm, which comprises the following specific steps of:
the method comprises the following steps: data preparation
The node movement always has certain regularity and periodicity, so that the node communication history in a specific time range is collected according to the periodicity of the node movement, the intimacy degree between the nodes is calculated based on the intimacy degree function, and the intimacy degree function is used as the weight of the node communication history to construct an undirected weighted communication graph.
Step two: sub-community partitioning
Based on a spectral clustering method, clustering and dividing the undirected authorized communication graph to obtain a plurality of sub-communities. Nodes in different communities are marked by adopting different marks, and a table structure is defined for storage.
Step three: decision tree model construction
When the message is transmitted across communities, the message is often transmitted to a target community by taking a messenger node as a medium, so that training data is collected based on a C4.5 algorithm, and a decision tree model capable of identifying the messenger node is trained by acquiring some attribute characteristics of the node.
Step four: message delivery
When the source node and the destination node are in the same community, the same-community message transmission mode is adopted: and when the source node moves and meets the neighbor node, judging whether the neighbor node and the destination node are in the same community, if so, copying the forwarding message, otherwise, continuously moving the node. When the source node and the destination node are different from each other, a cross-community message transmission mode is adopted: and if the source node moves and meets the neighbor node, judging whether the neighbor node and the destination node are in the same community, if so, copying and forwarding the message, otherwise, judging whether the node is a messenger node based on the trained decision tree model, if so, copying and forwarding the message, otherwise, continuing to move.
Claims (5)
1. An opportunistic routing implementation method based on spectral clustering and a C4.5 algorithm is characterized by comprising the following steps:
(1) an intimacy weight calculation method;
(2) a sub-community partitioning method based on spectral clustering;
(3) a messenger node identification model based on a C4.5 algorithm;
(4) an opportunistic routing implementation method based on a close community and a decision tree algorithm.
2. The intimacy degree weight calculation method according to claim 1, wherein: because node communication often has certain regularity and social attributes, based on historical communication records of nodes, the intimacy degree between the nodes is calculated by using a newly defined intimacy degree function and is used as the weight of the intimacy degree function, and an undirected weighted communication graph is constructed so as to analyze and mine important information such as community characteristics between the nodes.
3. The method for sub-community partitioning based on spectral clustering according to claim 1, wherein: in the opportunistic network, nodes in the same community often meet the situation frequently, and message forwarding is facilitated, so that a communication graph is divided into a plurality of subgraphs based on spectral clustering, a plurality of sub-communities are constructed, when a message is forwarded to a certain node, the message can be forwarded to other nodes in the community where the node is located, and other nodes are copied and forwarded in the community, so that the message transmission efficiency can be improved, and the message can be quickly transmitted to a destination node.
4. The messenger node recognition model based on the C4.5 algorithm of claim 1, wherein: the message transmission of the nodes in the same community is fast and reliable, and when the message is transmitted across communities, some messenger nodes which are free in a plurality of sub-communities need to be searched, so that a model capable of identifying the messenger nodes is constructed by adopting a C4.5 algorithm by acquiring the attribute characteristics of the activity, the centrality, the recency, the reliability, the free cache space, the transmission speed, the transmission range, the residual energy and the like of the nodes, and the messenger nodes are determined by utilizing the model.
5. The method for implementing opportunistic routing based on intimate communities and decision tree algorithms according to claim 1, wherein: based on the divided sub-communities and the trained decision tree model, when a source node and a destination node are in the same community, the message is copied and forwarded only in the sub-communities, when the source node and the destination node are in different community, the messenger node is identified by using the decision tree model, the message is transmitted to the destination community through the messenger node, and the node in the destination community copies and forwards the message and finally transmits the message to the destination node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010607907.XA CN111787592B (en) | 2020-06-30 | 2020-06-30 | Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010607907.XA CN111787592B (en) | 2020-06-30 | 2020-06-30 | Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111787592A true CN111787592A (en) | 2020-10-16 |
| CN111787592B CN111787592B (en) | 2022-07-19 |
Family
ID=72759878
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010607907.XA Active CN111787592B (en) | 2020-06-30 | 2020-06-30 | Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111787592B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112291827A (en) * | 2020-10-29 | 2021-01-29 | 王程 | Social attribute driven delay tolerant network route improvement algorithm |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107071844A (en) * | 2017-06-13 | 2017-08-18 | 湘潭大学 | A kind of opportunistic network routing method divided based on spectral clustering community |
| CN108809709A (en) * | 2018-06-06 | 2018-11-13 | 山东大学 | It is a kind of based on the close nature community discovery method propagated with label of node |
| US20190019254A1 (en) * | 2017-07-14 | 2019-01-17 | Allstate Insurance Company | Distributed data processing systems for processing remotely captured sensor data |
| CN109492673A (en) * | 2018-10-19 | 2019-03-19 | 南京理工大学 | A kind of unbalanced data prediction technique based on spectral clustering sampling |
| CN109716346A (en) * | 2016-07-18 | 2019-05-03 | 河谷生物组学有限责任公司 | Distributed machines learning system, device and method |
| CN110493142A (en) * | 2019-07-05 | 2019-11-22 | 南京邮电大学 | Mobile applications Activity recognition method based on spectral clustering and random forests algorithm |
| CN111343690A (en) * | 2020-03-01 | 2020-06-26 | 内蒙古科技大学 | Opportunistic network routing method based on fine-grained social relationship and community cooperation |
-
2020
- 2020-06-30 CN CN202010607907.XA patent/CN111787592B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109716346A (en) * | 2016-07-18 | 2019-05-03 | 河谷生物组学有限责任公司 | Distributed machines learning system, device and method |
| CN107071844A (en) * | 2017-06-13 | 2017-08-18 | 湘潭大学 | A kind of opportunistic network routing method divided based on spectral clustering community |
| US20190019254A1 (en) * | 2017-07-14 | 2019-01-17 | Allstate Insurance Company | Distributed data processing systems for processing remotely captured sensor data |
| CN108809709A (en) * | 2018-06-06 | 2018-11-13 | 山东大学 | It is a kind of based on the close nature community discovery method propagated with label of node |
| CN109492673A (en) * | 2018-10-19 | 2019-03-19 | 南京理工大学 | A kind of unbalanced data prediction technique based on spectral clustering sampling |
| CN110493142A (en) * | 2019-07-05 | 2019-11-22 | 南京邮电大学 | Mobile applications Activity recognition method based on spectral clustering and random forests algorithm |
| CN111343690A (en) * | 2020-03-01 | 2020-06-26 | 内蒙古科技大学 | Opportunistic network routing method based on fine-grained social relationship and community cooperation |
Non-Patent Citations (2)
| Title |
|---|
| LAXMI SUBEDI等: "SeScR: SDN-Enabled Spectral Clustering-Based Optimized Routing Using Deep Learning in VANET Environment", 《PROCEEDINGS OF 2010 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS》 * |
| 张沪寅等: "认知无线车载自组织网络中的联合路由调度", 《计算机研究与发展》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112291827A (en) * | 2020-10-29 | 2021-01-29 | 王程 | Social attribute driven delay tolerant network route improvement algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111787592B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | Deep reinforcement learning paradigm for performance optimization of channel observation–based MAC protocols in dense WLANs | |
| Hegeman et al. | Near-constant-time distributed algorithms on a congested clique | |
| Konstantopoulos et al. | Clustering in mobile ad hoc networks through neighborhood stability-based mobility prediction | |
| US20060146791A1 (en) | Network coding approach to rapid information dissemination | |
| Kuo et al. | Quantum-inspired algorithm for cyber-physical visual surveillance deployment systems | |
| Zhou et al. | Algebraic connectivity of degree constrained spanning trees for FSO networks | |
| CN111787592B (en) | Opportunistic routing implementation method based on spectral clustering and C4.5 algorithm | |
| Yousefiankalareh et al. | Tree-based routing protocol in wireless sensor networks using optimization algorithm batch particles with a mobile sink | |
| Shahina et al. | Clustering and data aggregation in wireless sensor networks using machine learning algorithms | |
| CN113516501A (en) | User communication behavior prediction method and device based on graph neural network | |
| Jyothi et al. | MSoC: Multi-scale optimized clustering for energy preservation in wireless sensor network | |
| Ebrahimi et al. | A new meta-heuristic approach for efficient search in the internet of things | |
| Zhou et al. | Maintaining approximate minimum steiner tree and k-center for mobile agents in a sensor network | |
| CN111597139B (en) | Communication method, system, equipment and medium of GPU | |
| Albalas et al. | Detecting black hole attacks in MANET using relieff classification algorithm | |
| KR101609457B1 (en) | Method for searching median node in big graph database based on low boundary | |
| Verma et al. | Neural based energy-efficient stable clustering for multilevel heterogeneous WSNs | |
| Eliiyi et al. | Parallel identification of central nodes in wireless multi-hop networks | |
| Patil et al. | Energy-efficient cluster-based aggregation protocol for heterogeneous wireless sensor networks | |
| Marian et al. | Sensing clouds: A distributed cooperative target tracking with tiny binary noisy sensors | |
| Kashyap et al. | Fuzzy-kohonen self-organizing clustering algorithm in wireless sensor networks | |
| Lakshmi et al. | Socialized Proficient Routing in Opportunistic Mobile Network Using Machine Learning Techniques. | |
| Chouhan et al. | A survey on the applications of machine learning in wireless sensor networks | |
| CN116367178B (en) | Unmanned cluster self-adaptive networking method and device | |
| Iovanovici et al. | Design space exploration for optimizing wireless sensor networks using social network analysis |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |