CN107197476B - Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network - Google Patents
Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network Download PDFInfo
- Publication number
- CN107197476B CN107197476B CN201710362447.7A CN201710362447A CN107197476B CN 107197476 B CN107197476 B CN 107197476B CN 201710362447 A CN201710362447 A CN 201710362447A CN 107197476 B CN107197476 B CN 107197476B
- Authority
- CN
- China
- Prior art keywords
- wifi
- zigbee
- hidden markov
- markov model
- collision
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000005540 biological transmission Effects 0.000 claims abstract description 27
- 238000004891 communication Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 5
- 230000006870 function Effects 0.000 claims description 13
- 210000000349 chromosome Anatomy 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 10
- 230000035772 mutation Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000007476 Maximum Likelihood Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000005265 energy consumption Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036772 blood pressure Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a method for avoiding conflict between WiFi and ZigBee nodes in a wireless body area network, which comprises the steps of modeling the transmission channel states of the ZigBee and the WiFi through a hidden Markov model; learning all parameters in the hidden Markov model according to data traces obtained in advance in a network, training and predicting transmission modes of ZigBee and WiFi, and obtaining channel collision probability distribution of a current state and a next state; and when channel collision between ZigBee and WiFi is predicted, surrounding WiFi transmission is inhibited through collision of AP virtual WiFi data frames, and communication of ZigBee nodes with high priority is ensured. The invention can make the monitoring data of the patient more real-time, thus bringing convenience to both hospitals and patients.
Description
Technical Field
The invention relates to the technical field of communication networks, in particular to a method for avoiding conflict between WiFi and ZigBee nodes in a wireless body area network.
Background
A Wireless Body Area Network (WBAN) is a wireless communication dedicated system that targets biosensing nodes, implanted nodes, and the like around a human body. It delivers physiological data such as electrocardiogram, electroencephalogram, blood pressure, etc. The recorded physiological signals are transmitted to the coordinator via wireless technology and then to the medical monitoring center. Since sensing nodes with low speed and long battery life are required in WBANs, the most widely used wireless technology is ZigBee. However, ZigBee networks face a serious interference problem with WiFi networks because they all operate in the unlicensed ISM 2.4GHz band, which is the only public band worldwide, and many systems operate in this band, which leads to an increasing problem of mutual interference between different systems, and this interference is inevitable, with WiFi being the most serious interference to ZigBee.
On an unauthorized ISM 2.4GHz frequency band, the ZigBee node is interfered by WiFi equipment, because the transmitting power of WiFi is 5-20 dB stronger than that of ZigBee, the ZigBee signal can be barely detected by the WiFi equipment, and the WiFi signal is easily detected by the ZigBee equipment, which can cause the ZigBee node to actively retreat and collide. In the medical field of wireless body area networks, ZigBee is very critical, and is used for transmitting a large amount of human physiological data, and the reduction of the throughput of the ZigBee under the high interference of a WiFi network cannot be borne, so that the timeliness of sensitive data is lost. Therefore, it is necessary to provide a low-cost and low-energy interference avoidance scheme for medical production.
In the prior art, the solutions mostly focus on the physical layer, e.g. changing the type of modulation, the transmit power, the spread spectrum, switching channels, etc. Most of the methods are not feasible for ZigBee because the energy consumption of the nodes is wasted. The existing solution method for the conflict between ZigBee and WiFi in the wireless body area network can be mainly divided into coexistence and avoidance, wherein the interference avoidance method is to scan the channel intensity through a physical layer and find a relatively idle working channel so as to reduce the interference of WiFi, but with the continuous increase of WiFi equipment and hot spots, the idle channels are less and less, and frequent channel switching also causes the energy consumption of ZigBee, so that the method is not feasible; in general, the proposed technology for coexistence problem basically has several aspects, such as modulation type, transmission power, spread spectrum, load, packet size, geographical distribution of interacting nodes, etc. to solve. Although these research methods reduce WiFi interference to ZigBee communications to varying degrees, some research is impractical, such as using special hardware, controlling all WiFi access points, and system modifications. These requirements greatly increase the cost and energy consumption and are well realized in practical applications.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method for avoiding collision between WiFi and ZigBee nodes in a wireless body area network, which inhibits WiFi transmission by virtual WiFi data frame collision and further satisfies ZigBee node communication with higher priority.
In order to solve the problems existing in the background technology, the technical scheme of the invention is as follows:
a method for avoiding conflict between WiFi and ZigBee nodes in a wireless body area network comprises the following steps:
1) modeling the transmission channel states of ZigBee and WiFi through a hidden Markov model;
2) learning all parameters in the hidden Markov model according to data traces obtained in advance in a network, training and predicting transmission modes of ZigBee and WiFi, and obtaining channel collision probability distribution of a current state and a next state;
3) and when channel collision between ZigBee and WiFi is predicted, surrounding WiFi transmission is inhibited through collision of AP virtual WiFi data frames, and communication of ZigBee nodes with high priority is ensured.
The step 1) is specifically as follows: the state space of the tradable object is modeled on a discretized temporal parameter space according to a hidden markov model.
The step 2) specifically comprises the following steps:
2.1, learning all parameters in the hidden Markov model by utilizing a forward and backward algorithm according to data traces obtained in advance in the network;
2.2, updating a parameter system in the hidden Markov model in a recursive mode to make the parameter system converge, wherein the obtained parameter system and the current sample are the best matched parameters;
2.3, predicting a possible channel transmission state sequence for the input test data by using a Viterbi algorithm according to the parameters obtained in the step 2.2;
and 2.4, estimating the channel collision probability distribution of the current state and the next state based on the maximum likelihood according to the trained hidden Markov model.
In the step 3), the AP position is obtained by adopting a multi-target genetic algorithm.
Acquiring the AP position by adopting a multi-target genetic algorithm comprises the following steps:
the method comprises the following steps that firstly, position information is coded into chromosomes of a genetic algorithm, each chromosome represents an AP position in a space, and a plurality of chromosomes formed by position codes are randomly and uniformly selected in a solution space to serve as an initial population;
step two, setting an objective function:
function one: collecting the signal intensity of all WiFi equipment at the position of the AP, and taking the maximum value; function two: setting a minimum signal strength threshold value, and calculating the number of WiFi equipment of which the signal strength is greater than the threshold value at the position of the AP;
thirdly, evaluating each individual of the initial population through an objective function, and selecting a plurality of solutions of pareto dominance as a next generation population;
fourthly, acquiring a crossover operator and a mutation operator to generate offspring;
and fifthly, taking the newly generated filial generation as a next generation parent population, if the iteration result is stable after a plurality of times or exceeds the preset iteration times, stopping the iteration and entering the sixth step, otherwise, entering the second step.
And sixthly, selecting the generated result as an optimal solution.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a method for avoiding conflict between WiFi and ZigBee nodes in a wireless body area network, which inhibits WiFi transmission through virtual WiFi data frame conflict so as to meet the communication of the ZigBee nodes with higher priority, so that a user does not need additional hardware equipment or change related parameters of the WiFi and ZigBee equipment, and avoids or reduces interference from the WiFi in the ZigBee transmission by only modifying AP (access point), thereby saving the energy consumption of a chip.
Drawings
FIG. 1 is a flow chart of a method for avoiding collision between WiFi and ZigBee nodes in a wireless body area network;
FIG. 2 is a comparison of the predicted results of the present invention with the original data;
FIG. 3 is a diagram of the prediction result of ZigBee-WiFi conflict in the present invention.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the present invention provides a method for avoiding collision between WiFi nodes and ZigBee nodes in a wireless body area network, comprising the following steps:
1) modeling the transmission channel states of ZigBee and WiFi through a hidden Markov model;
the method specifically comprises the following steps: the state space of the tradable object is modeled on a discretized temporal parameter space according to a hidden markov model. When channel collision analysis is carried out, a channel collision sequence is firstly segmented into a plurality of channel collisions (possibly overlapping) of different types, and each collision or non-collision signal is subjected to feature extraction, so that a one-dimensional feature vector sequence o-o is obtained1o2o3…oT. Each feature vector is considered to be a random vector satisfying a certain probability distribution, and this random vector sequence is time-varying, and thus can be regarded as a random process. Since the state space is continuous (i.e. the eigenvectors are not discrete), it is complicated to model the collision signal directly in such a continuous state space, and therefore the collision signal is modeled based on some sort of discrete state space. Considering that the collision signal has a certain short-time steady characteristic, namely the collision state can be considered to be unchanged in a short time, and the whole process of the state of a channel is composed of different states, a listed state space is extracted to model on a discretized time parameter space.
The nodes for changing the channel state are divided into three types, namely ZigBee type, WiFi type and ZigBee-WiFi type, wherein the ZigBee type node sends a ZigBee signal and a ZigBee self collision signal, the WiFi type node sends a WiFi signal and a WiFi self collision signal, and the ZigBee-WiFi type node and the WiFi self collision signal send collision signals in transmission. Similarly, the null signals are regarded as null signals sent by different types of nodes, and are classified into three types, one type is the null signal sent by the ZigBee type node, the other type is the null signal sent by the WiFi type node, and the last type is the null signal sent by the ZigBee-WiFi type node. Thus we can divide the states according to the signal type following the null signal and treat these states as hidden states. For example: this is considered to be the case for state one by the ZigBee signal following the null signal.
2) Learning all parameters in the hidden Markov model according to data traces obtained in advance in a network, training and predicting transmission modes of ZigBee and WiFi, and obtaining channel collision probability distribution of a current state and a next state;
the method specifically comprises the following steps:
2.1, learning all parameters in the hidden Markov model by utilizing a forward and backward algorithm according to data traces obtained in advance in the network;
2.2, updating a parameter system in the hidden Markov model in a recursive mode to make the parameter system converge, wherein the obtained parameter system and the current sample are the best matched parameters;
2.3, predicting a possible channel transmission state sequence for the input test data by using a Viterbi algorithm according to the parameters obtained in the step 2.2;
and 2.4, estimating the channel collision probability distribution of the current state and the next state based on the maximum likelihood according to the trained hidden Markov model.
3) When channel collision between ZigBee and WiFi is predicted, collision of data frames of the WiFi is virtualized through an AP (wireless access point), surrounding WiFi transmission is restrained, and communication of ZigBee nodes with high priority is guaranteed.
In the invention, a multi-objective genetic algorithm is adopted to optimize the traditional AP placing method. The traditional AP setting method selects a position according to signal strength, the stronger the signal strength is, the closer the AP is to WiFi equipment, when the AP is close enough to certain WiFi equipment, the distance between the AP and other WiFi equipment becomes relatively far, so that the signal strength of other equipment is low, the method inevitably ignores some WiFi equipment in position selection, the obtained result is often closer to equipment with higher signal strength, and the error is different from that in a coverage overlapping area to the maximum extent.
Therefore, the method adopts a multi-target genetic algorithm to select a proper AP position in a two-dimensional space, evaluates the quality of the position by setting a proper objective function, increases the diversity of solutions for the primarily selected dominant solution set by means of crossing, variation and the like, and then performs multiple iterations to optimize, thereby finally obtaining the optimal solution of the AP position in the two-dimensional space.
Acquiring the AP position by adopting a multi-target genetic algorithm comprises the following steps:
the method comprises the following steps that firstly, position information is coded into chromosomes of a genetic algorithm, each chromosome represents an AP position in a space, a plurality of chromosomes formed by the position codes are randomly and uniformly selected in a solution space to serve as an initial population, and the chromosome format is a coordinate in a two-dimensional space;
step two, setting an objective function:
function one: collecting the signal intensity of all WiFi equipment at the position of the AP, and taking the maximum value; function two: setting a minimum signal strength threshold value, and calculating the number of WiFi equipment of which the signal strength is greater than the threshold value at the position of the AP;
thirdly, evaluating each individual of the initial population through an objective function, and selecting a plurality of solutions of pareto dominance as a next generation population; an exemplary solution of 100 pareto dominances is selected;
fourthly, acquiring a crossover operator and a mutation operator to generate offspring;
and (3) a crossover operator:
(1) setting the probability of cross to be 90%;
(2) calculating whether cross occurs to each pair of solutions selected in the last step;
(3) if the intersection occurs: interchanging the ordinate of the pair of solutions to generate a new pair of solutions, and merging the pair of solutions into a filial generation population;
mutation operator:
(1) setting the probability of variation as 10%;
(2) setting the range of variation as a solution space;
(3) calculating whether variation occurs to each digit of each solution selected in the last step;
(4) if mutation occurs: and randomly acquiring a value in a preset range as a coordinate variation result, and merging the varied solution into a filial generation population.
And fifthly, taking the newly generated filial generation as a next generation parent population, if the iteration result is stable after a plurality of times or exceeds the preset iteration times, stopping the iteration and entering the sixth step, otherwise, entering the second step.
And sixthly, selecting the generated result as an optimal solution.
The invention provides a hidden Markov model-based method for training and predicting the transmission modes of ZigBee and WiFi. After the transmission modes of the ZigBee and the ZigBee are known, the transmission of the WiFi is restrained through AP virtual WiFi data frame collision before each ZigBee-WiFi collision, the ZigBee node with higher priority is ensured to communicate, and meanwhile, the related parameters of the WiFi and the ZigBee device are not changed. The invention can predict about 90% of ZigBee-WiFi conflict and inhibit, and avoid or reduce the interference of WiFi signals on ZigBee.
And (3) experimental verification:
for hidden markov models, the method first trains data to derive specific model parameters, and then uses the model parameters to predict the upcoming collisions. To prove the effectiveness of the proposed method, experimental evaluations were performed. The test platform is established on matlab of the notebook computer, the data set adopts real data of WiFi and ZigBee, and as shown in figure 2, the prediction result of the method is compared with the original data.
In the figure, comparing the real hidden state change and the predicted state change in the observation state chain, it can be seen that when the observation state length is 100, the accuracy of the prediction result by the hidden markov model accounts for about 50% of the whole state, but because each state has the possibility of sending null signals, there are three cases when determining the ZigBee-WiFi collision state and suppressing:
1. when the channel state is idle, misjudging the channel state as ZigBee-WiFi conflict so as to inhibit the channel state;
2. when the channel state is busy, misjudging the channel state as ZigBee-WiFi conflict so as to inhibit the channel state;
3. and when the channel state is the other two kinds of conflicts, misjudging the channel state as ZigBee-WiFi conflict so as to inhibit.
In the first case, the sending of the suppression signal does not affect the normal transmission of other signals, and the misjudgment in other cases may affect the normal transmission of the wifi signal, resulting in an increase in the time delay of the wifi signal.
As shown in fig. 3, for the prediction result of the ZigBee-WiFi collision, it can be seen that the prediction rate of the state three in the predicted state chain is more than 90%, that is, the (ZigBee-WiFi) null signal collides with the ZigBee-WiFi, so that about 90% of WiFi transmission can be suppressed, and the priority of the ZigBee transmission is ensured, and the required link throughput and the packet delivery rate are ensured. The experimental results show the effectiveness of the invention.
It will be appreciated by those skilled in the art that the foregoing embodiments are merely preferred embodiments of the invention, and thus, modifications, variations and equivalents of the parts of the invention may be made by those skilled in the art, which are still within the spirit of the invention and which are intended to be within the scope of the invention.
Claims (4)
1. A method for avoiding conflict between WiFi and ZigBee nodes in a wireless body area network is characterized by comprising the following steps:
1) modeling the transmission channel states of ZigBee and WiFi through a hidden Markov model;
2) learning all parameters in the hidden Markov model according to data traces obtained in advance in a network, training and predicting transmission modes of ZigBee and WiFi, and obtaining channel collision probability distribution of a current state and a next state;
3) when channel collision between ZigBee and WiFi is predicted, surrounding WiFi transmission is inhibited through collision of AP virtual WiFi data frames, and communication of ZigBee nodes with high priority is guaranteed;
the step 2) specifically comprises the following steps:
2.1, learning all parameters in the hidden Markov model by utilizing a forward and backward algorithm according to data traces obtained in advance in the network;
2.2, updating a parameter system in the hidden Markov model in a recursive mode to make the parameter system converge, wherein the obtained parameter system and the current sample are the best matched parameters;
2.3, predicting a possible channel transmission state sequence for the input test data by using a Viterbi algorithm according to the parameters obtained in the step 2.2;
and 2.4, estimating the channel collision probability distribution of the current state and the next state based on the maximum likelihood according to the trained hidden Markov model.
2. The method for avoiding collision between WiFi and ZigBee nodes in a wireless body area network according to claim 1, wherein the step 1) is specifically: the state space of the tradable object is modeled on a discretized temporal parameter space according to a hidden markov model.
3. The method of claim 1, wherein in step 3), the AP position is obtained by using a multi-objective genetic algorithm.
4. The method of claim 3, wherein the step of obtaining the AP position using a multi-objective genetic algorithm comprises:
the method comprises the following steps that firstly, position information is coded into chromosomes of a genetic algorithm, each chromosome represents an AP position in a space, and a plurality of chromosomes formed by position codes are randomly and uniformly selected in a solution space to serve as an initial population;
step two, setting an objective function:
function one: collecting the signal intensity of all WiFi equipment at the position of the AP, and taking the maximum value; function two: setting a minimum signal strength threshold value, and calculating the number of WiFi equipment of which the signal strength is greater than the threshold value at the position of the AP;
thirdly, evaluating each individual of the initial population through an objective function, and selecting a plurality of solutions of pareto dominance as a next generation population;
fourthly, acquiring a crossover operator and a mutation operator to generate offspring;
fifthly, taking the newly generated offspring as a next generation parent population, if the iteration result is stable after a plurality of times or exceeds the preset iteration times, stopping the iteration and entering the sixth step, otherwise, entering the second step;
and sixthly, selecting the generated result as an optimal solution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710362447.7A CN107197476B (en) | 2017-05-12 | 2017-05-12 | Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710362447.7A CN107197476B (en) | 2017-05-12 | 2017-05-12 | Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107197476A CN107197476A (en) | 2017-09-22 |
| CN107197476B true CN107197476B (en) | 2020-03-31 |
Family
ID=59875375
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710362447.7A Expired - Fee Related CN107197476B (en) | 2017-05-12 | 2017-05-12 | Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107197476B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108668376B (en) * | 2018-04-13 | 2021-06-29 | 烽火通信科技股份有限公司 | WLAN and ZigBee coexisting wireless network cooperative work system and method |
| CN108770001B (en) * | 2018-04-20 | 2021-02-12 | 西安电子科技大学 | Wireless chargeable sensor network optimization method based on memetic algorithm |
| CN110278590B (en) * | 2019-06-21 | 2021-05-25 | 合肥工业大学智能制造技术研究院 | Intelligent lighting lamp communication transmission channel selection method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103002457A (en) * | 2012-12-06 | 2013-03-27 | 南京邮电大学 | Interference coexistence model and conflict time analysis method in short-distance coexistence system |
| US8914019B1 (en) * | 2011-08-09 | 2014-12-16 | Marvell International Ltd. | Feedback spoofing for coexistence among multiple wireless communication technologies |
| CN104902545A (en) * | 2015-05-27 | 2015-09-09 | 厦门盈趣科技股份有限公司 | Coexisting method for Zigbee and WiFi (Wireless Fidelity) |
-
2017
- 2017-05-12 CN CN201710362447.7A patent/CN107197476B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8914019B1 (en) * | 2011-08-09 | 2014-12-16 | Marvell International Ltd. | Feedback spoofing for coexistence among multiple wireless communication technologies |
| CN103002457A (en) * | 2012-12-06 | 2013-03-27 | 南京邮电大学 | Interference coexistence model and conflict time analysis method in short-distance coexistence system |
| CN104902545A (en) * | 2015-05-27 | 2015-09-09 | 厦门盈趣科技股份有限公司 | Coexisting method for Zigbee and WiFi (Wireless Fidelity) |
Non-Patent Citations (4)
| Title |
|---|
| AP –Assisted CTS-Blocking for WiFi-ZigBee Coexistence;Shigemi Ishida etc;《2015 Third International symposium on computing and Networking》;20151231;正文第I-V节 * |
| HMM-driven Smart White-space-aware Frame Control Protocol for Coexistence of ZigBee and WiFi;Jie Yuan etc;《Work in Progress at PerCom》;20130319;正文第I-V节 * |
| WiFi-ZigBee coexistence based on collision avoidance for wireless body area network;Lan Yao etc;《IEEE》;20170811;全文 * |
| 基于ZigBee和WiFi网络的抗同频干扰技术研究;吴琼等;《仪表技术与传感器》;20131231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107197476A (en) | 2017-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107197476B (en) | Method for avoiding conflict between WiFi (Wireless Fidelity) node and ZigBee node in wireless body area network | |
| Tumuluru et al. | A neural network based spectrum prediction scheme for cognitive radio | |
| Gholipour et al. | Hop‐by‐Hop Congestion Avoidance in wireless sensor networks based on genetic support vector machine | |
| Zhou et al. | Deep-learning-based spatial–temporal channel prediction for smart high-speed railway communication networks | |
| Han et al. | Reinforcement learning for efficient and fair coexistence between LTE-LAA and Wi-Fi | |
| Agrawal et al. | Spectrum sensing in cognitive radio networks and metacognition for dynamic spectrum sharing between radar and communication system: A review | |
| CN105915300B (en) | It is a kind of that spectrum prediction method being kept out of the way based on RLNC in CR networks | |
| Khalek et al. | From cognitive to intelligent secondary cooperative networks for the future internet: Design, advances, and challenges | |
| Sinclair et al. | A kernel methods approach to reducing handover occurrences within LTE | |
| Li et al. | Artificial immune network-based anti-collision algorithm for dense RFID readers | |
| JP6801564B2 (en) | Parameter determination method, interference classification identification method and its device | |
| Solanki et al. | Spectrum sensing in cognitive radio using CNN-RNN and Transfer learning | |
| Silva et al. | Throughput and latency in the distributed Q-learning random access mMTC networks | |
| Jothiraj et al. | An efficient adaptive threshold‐based dragonfly optimization model for cooperative spectrum sensing in cognitive radio networks | |
| Bhutani | Application of machine-learning based prediction techniques in wireless networks | |
| Ghanshala et al. | Self-organizing sustainable spectrum management methodology in cognitive radio vehicular adhoc network (CRAVENET) environment: a reinforcement learning approach | |
| KR20230079436A (en) | Learning-Based Spectrum Occupancy Prediction Using Multidimensional Correlation | |
| Taleb et al. | Energy efficient selection of spreading factor in LoRaWAN-based WBAN medical systems | |
| EP3790303A1 (en) | Predicting a radio spectrum usage | |
| Salgado et al. | Collaborative algorithm for the spectrum allocation in distributed cognitive networks | |
| Zhang et al. | Deep Reinforcement Learning-based Distributed Dynamic Spectrum Access in Multi-User Multi-channel Cognitive Radio Internet of Things Networks | |
| WO2015073069A1 (en) | Method and apparatus for enhanced multi-node utilization of an electromagnetic state space | |
| KR20230094922A (en) | Intelligent dynamic real-time spectrum resource management system and intelligent dynamic real-time spectrum resource management method using data mining and case-based reasoning | |
| Sun et al. | A stochastic geometry analysis of inter-user interference in IEEE 802.15. 6 body sensor networks | |
| Wei et al. | Intelligent channel allocation for age of information optimization in internet of medical things |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200331 |