CN102521981A - Computation method for traffic situation based on information-oriented middleware - Google Patents
Computation method for traffic situation based on information-oriented middleware Download PDFInfo
- Publication number
- CN102521981A CN102521981A CN2011104299108A CN201110429910A CN102521981A CN 102521981 A CN102521981 A CN 102521981A CN 2011104299108 A CN2011104299108 A CN 2011104299108A CN 201110429910 A CN201110429910 A CN 201110429910A CN 102521981 A CN102521981 A CN 102521981A
- Authority
- CN
- China
- Prior art keywords
- traffic situation
- message
- computing method
- oriented middleware
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention discloses a computation method for traffic situation based on information-oriented middleware. The computation method is characterized by comprising steps of acquiring multi-source heterogeneous data in a uniform interface mode of the information-oriented middleware, adopting generated character strings as information of the information-oriented middleware, and transmitting the information of the information-oriented middleware to a theme; and actively subscribing the information on the theme by a traffic situation computing unit, and analyzing and computing the traffic situation. By the aid of the computation method, uniform processing of the acquired multi-source heterogeneous traffic information data is realized on the basis of the information-oriented middleware, problems that an existing method of the prior art is troublesome, program is complicated and errors are easy to be caused due to the fact that multi-source heterogeneous traffic information data are respectively processed are solved, the traffic situation is computed by the aid of advanced neural network algorithm, the algorithm is practical, a training process is speedy, and a good effect is realized.
Description
Technical field
The present invention relates to a kind of traffic situation computing method, belong to traffic information collection, processing technology field based on message-oriented middleware.
Background technology
Intelligent transportation has at present obtained significant progress at home, and the data acquisition system (DAS) of various scales has been built up in each big and medium-sized cities, has had the ability of collection, processing and the issue of transport information.How to obtain extensive and traffic image data accurately, carry out the calculating of traffic situation and study and judge, improve the problem that solves for traffic control department provides decision support to become present urgent need.
The urban road traffic information collection has the multi-source heterogeneous characteristic of separate sources, different medium and different expressions.How to merge the isomery transport information height of separate sources with shared, be the key of extensively and accurately gathering traffic data.And multi-source heterogeneous data are handled in the many employings of method that present intelligent transportation field is handled multi-source heterogeneous data respectively; Be processed into the unified data structure type, then data merged, it is more that such way takies resource; Need different programs to handle; And finally merge to get up trouble, and causing easily makeing mistakes, the utmost point is not intelligent.
After realizing traffic collection and filtration treatment, the calculating of traffic situation is studied and judged most important, and for obtaining accurately real-time traffic situation, wherein, traffic situation can simply be interpreted as judges whether road conditions block up unimpededly, more effectively is that traffic administration person, participant serve.
Summary of the invention
Method was loaded down with trivial details when the present invention had field of traffic extraction, the multi-source heterogeneous traffic data of Treatment Analysis now in order to solve, and the problem of easy error provides a kind of traffic situation computing method based on message-oriented middleware, simply is easy to realize that the result is accurate.
In order to solve the problems of the technologies described above, the present invention adopts following technical scheme to be achieved:
A kind of traffic situation computing method based on message-oriented middleware may further comprise the steps:
Adopt the unified interface mode of message-oriented middleware to gather multi-source heterogeneous data, the character string of generation is sent to theme as the message of message-oriented middleware;
Message on the traffic situation computing unit active topic of subscription is resolved and is also calculated traffic situation.
Further; At least comprise average discharge, average speed and three key elements of average occupancy in the described message; Wherein, Average discharge is the mean value of the vehicle flowrate in the unit interval, and average speed is the average speed in the unit interval, and average occupancy is a ratio of spending car sensitive time and total detection time in the unit interval.
Further again, said traffic situation computing unit opening relationships model extracts in three key elements two or three key elements and carries out traffic situation and calculate.
Preferably, described relational model adopts improved neural network algorithm to set up, and comprises 3 layers feedforward network: input layer X, output layer y and hidden layer, and traffic situation calculates as follows:
Wherein, m is a positive integer, and w is a hidden layer and the weights that are connected of output layer, c
iBe the center of hidden layer node, σ
iBe the standard deviation of i node,
Output for hidden layer.
Wherein, the computing method at the center of said hidden layer node are a kind of in random initializtion method, quadrature least square method and the Fuzzy C-Means Clustering algorithm.
The computing method at the center of said hidden layer node preferably adopt the Fuzzy C-Means Clustering algorithm, and said Fuzzy C-Means Clustering algorithm is specially:
Suppose to have known n
*Individual type, finite set
Belong to p dimension Euclidean space R
p, i.e. x
k∈ R
p, k=1,2, L, n
*, adopt sum of squared errors function as the clustering criteria function:
Wherein, u
IjBe data x
jPoint is with respect to c
iDegree of membership, d
Ij=‖ c
i-x
j‖ is c
iAnd the Euclidean distance between the j data points, and m
*∈ (1 ,+∞) be a weighted index, calculate two J values at least continuously, and calculate both range difference ε=‖ J
i-J
I-1‖ as if ε=Δ t in the permissible error scope, then stops to adjust u
Ij, and utilize u
IjCalculate c
i
c
iComputing method be:
u
IjComputing method be:
If ε not in the permissible error scope, then adjusts u
IjAnd u
Ij, constantly carry out interative computation, satisfy error condition until ε.
Compared with prior art, advantage of the present invention and good effect are: traffic situation computing method of the present invention, based on message-oriented middleware; Multi-source heterogeneous traffic information data to being gathered carries out Unified Treatment; Solved prior art and respectively multi-source heterogeneous traffic information data has been handled and caused that method is loaded down with trivial details, program is complicated and the problem of easy error, utilized improved neural network algorithm to calculate traffic situation, algorithm is practical; Training process is quick, obtains effect preferably.
After the detailed description in conjunction with the advantages embodiment of the present invention, other characteristics of the present invention and advantage will become clearer.
Description of drawings
Fig. 1 is a kind of example structure synoptic diagram of the traffic situation computing method based on message-oriented middleware proposed by the invention;
Fig. 2 is the network structure based on neural network algorithm among a kind of embodiment of traffic situation computing method of message-oriented middleware proposed by the invention.
Embodiment
, adopt and handle multi-source data respectively when the multi-source heterogeneous data processing to existing transport information field, final arrangement merges; Cause each association that the handling procedure of oneself is all arranged like this, it is loaded down with trivial details, complicated that data processing is got up, easy error; When the calculating of the traffic data of being gathered being carried out traffic situation was studied and judged, algorithm was reasonable inadequately, and the result is accurate inadequately; To the problems referred to above, the invention provides a kind of traffic situation computing method based on message-oriented middleware, adopt and handle multi-source heterogeneous data based on the method for message-oriented middleware; Implement simple and be not easy to make mistakes, adopt improved neural network algorithm to calculate traffic situation, algorithm is practical; Training process is quick, and is effective.
Do explanation in further detail below in conjunction with the accompanying drawing specific embodiments of the invention.
Embodiment one, and the traffic situation computing method based on message-oriented middleware of present embodiment may further comprise the steps:
The unified interface mode of S1, employing message-oriented middleware is gathered multi-source heterogeneous data, and the character string of generation is sent to theme as the message of message-oriented middleware;
Message on S2, the traffic situation computing unit active topic of subscription is resolved and is also calculated traffic situation.
Referring to shown in Figure 1; In the urban highway traffic acquisition system; Use comparatively stable have coil checker, microwave detector, video detector etc., just said multi-source heterogeneous traffic data, such data are carried out data transmission through serial ports or network communication mode; Equipment producer is numerous, and data protocol differs greatly.Because the message-oriented middleware major function is between various network agreement, operating system and application program, to provide reliable and recoverable message to transmit.Adopt in the present embodiment and gather based on the unified interface mode of message-oriented middleware.
The ActiveMQ message-oriented middleware is wherein to use the middleware of increasing income comparatively widely, uses formation (Queue) or theme (Topic) transmission/reception message, and therefore, the preferred ActiveMQ of employing message-oriented middleware is realized in the present embodiment.
The isomery transport information of gathering through the program adjustment after, generate character string according to uniform data format, to fixing theme (Topic) the transmission message of message-oriented middleware.Realized conversion, the parsing of message through receiving messaging program again, obtained the traffic element information in each isomery information, supplied situation to calculate and utilize.
Further, comprise average discharge, average speed and three key elements of average occupancy in the described message at least, wherein, three above-mentioned key elements are the field of traffic proper noun, do not do detailed description at this.
As a concrete embodiment, such as, in the program of present embodiment, the uniform data of collection be adjusted into data layout can for:
DATASOURCE,SECTIONID,SECTIONNAME,LARGECOUNT,SMALLCOUNT,COMMCOUNT,AVGVOLUME,AVGSPEED,OCCUPANCY,QUEUE,TRAVALTIME,POINTID,POINTNAME,DEVICEID,DEVICENAME,UPTIME
Each field implication is respectively Data Source, highway section numbering, highway section title, oversize vehicle number, dilly number, crosses car number, average discharge, average speed, average occupancy, row to length, hourage, collection point numbering, collection point title, checkout equipment numbering, checkout equipment title, uplink time; Separate with the half-angle comma between the field, generate unified character string.Each field was with 5 minutes integral points (0-5,6-10,11-15 ...) traffic flow data calculates, so traffic key element average discharge wherein, average speed, average occupancy all will carry out 5 minutes progressive means and calculate.
Said traffic situation computing unit opening relationships model extracts in average discharge noted earlier, average speed and three key elements of average occupancy two or three key elements and carries out traffic situation and calculate.
Preferably, in the present embodiment, relational model adopts improved neural network algorithm to set up; Referring to shown in Figure 2; Structural drawing for basic neural network basic definition comprises 3 layers feedforward network: input layer X, output layer y and hidden layer, and traffic situation calculates as follows:
Wherein, m is a positive integer, and w is a hidden layer and the weights that are connected of output layer, c
iBe the center of hidden layer node, σ
iBe the standard deviation of i node,
Output for hidden layer.
Mainly improved the central point choosing method of hidden layer in the present embodiment, the center c of hidden node
iBe the key issue of modified Learning Algorithm, its activation function is made up of the neuron of radial function, in the present embodiment, and the output of hidden layer
The preferred Gaussian function calculation that adopts:
What wherein, the computing method at the center of said hidden layer node can be in random initializtion method, quadrature least square method and the Fuzzy C-Means Clustering algorithm is a kind of.
Yet, in the modified neural network, conceal the approximation capability that directly affects network of choosing at layer center.Therefore, the key of setting up the modified neural network model is to select suitable latent layer center.Practical application shows that random initializtion is responsive to initial value, and the quadrature least-squares algorithm ill-condition matrix occurs easily when the input data volume is big.
Therefore, the computing method at the center of said hidden layer node preferably adopt the Fuzzy C-Means Clustering algorithm, can with the organic integration of modified neural network, first Application has obtained good effect in the traffic situation computing field.Said Fuzzy C-Means Clustering algorithm is specially:
Suppose to have known n
*Individual type, finite set
Belong to p dimension Euclidean space R
p, i.e. x
k∈ R
p, k=1,2, L, n
*, adopt sum of squared errors function as the clustering criteria function:
Wherein, u
IjBe data x
jPoint is with respect to c
iDegree of membership, d
Ij=‖ c
i-x
j‖ is c
iAnd the Euclidean distance between the j data points, and m
*∈ (1 ,+∞) be a weighted index, calculate two J values at least continuously, and calculate both range difference ε=‖ J
i-J
I-1‖ as if ε=Δ t in the permissible error scope, then stops to adjust u
Ij, and utilize u
IjCalculate c
i
The modified neural network algorithm carries out cluster analysis through making squared error function J reach minimum, in the present embodiment,
c
iComputing method be:
u
IjComputing method be:
If ε not in the permissible error scope, then adjusts u
IjAnd u
Ij, constantly carry out interative computation, satisfy error condition until ε, be the optimal classification result.
The traffic situation computing method of present embodiment; Based on message-oriented middleware, the multi-source heterogeneous traffic information data of being gathered is carried out Unified Treatment, solved prior art and respectively multi-source heterogeneous traffic information data has been handled and caused that method is loaded down with trivial details, program is complicated and the problem of easy error; Utilize improved neural network algorithm to calculate traffic situation; Algorithm is practical, and training process is quick, obtains effect preferably.
Preferred forms of the present invention is the form with the backstage service, and the traffic data that timing scan is uploaded sends message according to unified interface rules, resolves original traffic data, calls the traffic situation calculation procedure and carries out the analysis of city-level traffic situation.
Certainly; Above-mentioned explanation is not to be limitation of the present invention; The present invention also is not limited in above-mentioned giving an example, and variation, remodeling, interpolation or replacement that those skilled in the art are made in essential scope of the present invention also should belong to protection scope of the present invention.
Claims (10)
1. the traffic situation computing method based on message-oriented middleware is characterized in that, may further comprise the steps:
Adopt the unified interface mode of message-oriented middleware to gather multi-source heterogeneous data, the character string of generation is sent to theme as the message of message-oriented middleware;
Message on the traffic situation computing unit active topic of subscription is resolved and is also calculated traffic situation.
2. the traffic situation computing method based on message-oriented middleware according to claim 1 is characterized in that, comprise average discharge, average speed and three key elements of average occupancy in the described message at least.
3. the traffic situation computing method based on message-oriented middleware according to claim 2 is characterized in that, said traffic situation computing unit opening relationships model extracts in said three key elements two or three key elements and carries out traffic situation and calculate.
4. the traffic situation computing method based on message-oriented middleware according to claim 3; It is characterized in that; Described relational model adopts improved neural network algorithm to set up, and comprises 3 layers feedforward network: input layer X, output layer y and hidden layer, and traffic situation calculates as follows:
6. according to the described traffic situation computing method of each claim of claim 1-5 based on middleware; It is characterized in that the computing method at the center of said hidden layer node are a kind of in random initializtion method, quadrature least square method and the Fuzzy C-Means Clustering algorithm.
7. the traffic situation computing method based on middleware according to claim 6 is characterized in that, said Fuzzy C-Means Clustering algorithm is:
Suppose to have known n
*Individual type, finite set
Belong to p dimension Euclidean space R
p, i.e. x
k∈ R
p, k=1,2, L, n
*, adopt sum of squared errors function as the clustering criteria function:
Wherein, u
IjBe data x
jPoint is with respect to c
iDegree of membership, d
Ij=‖ c
i-x
j‖ is c
iAnd the Euclidean distance between the j data points, and m
*∈ (1 ,+∞) be a weighted index, calculate two J values at least continuously, and calculate both range difference ε=‖ J
i-J
I-1‖ as if ε=Δ t in the permissible error scope, then stops adjustment and calculates the J value, and utilize u
IjCalculate c
i
8. the traffic situation computing method based on middleware according to claim 7 is characterized in that c
iComputing method be:
9. the traffic situation computing method based on middleware according to claim 7 is characterized in that u
IjComputing method be:
10. the traffic situation computing method based on middleware according to claim 9 is characterized in that, if ε not in the permissible error scope, then adjusts u
IjAnd c
i, constantly carry out iterative computation J value, satisfy error condition until ε.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011104299108A CN102521981A (en) | 2011-12-20 | 2011-12-20 | Computation method for traffic situation based on information-oriented middleware |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011104299108A CN102521981A (en) | 2011-12-20 | 2011-12-20 | Computation method for traffic situation based on information-oriented middleware |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102521981A true CN102521981A (en) | 2012-06-27 |
Family
ID=46292880
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011104299108A Pending CN102521981A (en) | 2011-12-20 | 2011-12-20 | Computation method for traffic situation based on information-oriented middleware |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102521981A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106023325A (en) * | 2016-05-11 | 2016-10-12 | 贵州车秘科技有限公司 | Cloud-platform highway toll service system |
CN106408977A (en) * | 2016-12-09 | 2017-02-15 | 思建科技有限公司 | Traffic condition monitoring system and method |
CN107215362A (en) * | 2017-06-12 | 2017-09-29 | 上海自仪泰雷兹交通自动化系统有限公司 | Middleware adaptation method for trackside system compatible different vendor onboard system |
CN107231290A (en) * | 2017-04-19 | 2017-10-03 | 中国建设银行股份有限公司 | A kind of instant communicating method and system |
CN107819831A (en) * | 2017-10-23 | 2018-03-20 | 丹露成都网络技术有限公司 | A kind of universal message system based on metaq and mns |
CN109035777A (en) * | 2018-08-23 | 2018-12-18 | 河南中裕广恒科技股份有限公司 | Traffic circulation Situation analysis method and system |
CN109063752A (en) * | 2018-07-17 | 2018-12-21 | 华北水利水电大学 | The method for sorting of the multiple dimensioned real-time stream of multi-source higher-dimension neural network based |
US10915812B2 (en) | 2016-11-09 | 2021-02-09 | Samsung Electronics Co., Ltd. | Method and system of managing computing paths in an artificial neural network |
CN113837446A (en) * | 2021-08-30 | 2021-12-24 | 航天科工广信智能技术有限公司 | Multi-source heterogeneous data-based airport land side area traffic situation prediction method |
CN114495494A (en) * | 2022-01-06 | 2022-05-13 | 电子科技大学 | Traffic situation assessment method based on traffic flow parameter prediction |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101046919A (en) * | 2006-10-12 | 2007-10-03 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
CN101086804A (en) * | 2006-06-06 | 2007-12-12 | 杜存君 | A method and system for traffic information management |
CN101383091A (en) * | 2008-10-14 | 2009-03-11 | 北京交通大学 | Network control system for traffic induction outdoor screen |
CN101547172A (en) * | 2009-05-05 | 2009-09-30 | 南京信息工程大学 | RBF-based blind equalization method for fuzzy-neural network |
CN101673463A (en) * | 2009-09-17 | 2010-03-17 | 北京世纪高通科技有限公司 | Traffic information predicting method based on time series and device thereof |
CN101719315A (en) * | 2009-12-23 | 2010-06-02 | 山东大学 | Method for acquiring dynamic traffic information based on middleware |
-
2011
- 2011-12-20 CN CN2011104299108A patent/CN102521981A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101086804A (en) * | 2006-06-06 | 2007-12-12 | 杜存君 | A method and system for traffic information management |
CN101046919A (en) * | 2006-10-12 | 2007-10-03 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
CN101383091A (en) * | 2008-10-14 | 2009-03-11 | 北京交通大学 | Network control system for traffic induction outdoor screen |
CN101547172A (en) * | 2009-05-05 | 2009-09-30 | 南京信息工程大学 | RBF-based blind equalization method for fuzzy-neural network |
CN101673463A (en) * | 2009-09-17 | 2010-03-17 | 北京世纪高通科技有限公司 | Traffic information predicting method based on time series and device thereof |
CN101719315A (en) * | 2009-12-23 | 2010-06-02 | 山东大学 | Method for acquiring dynamic traffic information based on middleware |
Non-Patent Citations (3)
Title |
---|
于德新等: "自适应信号控制系统流量预测模型研究", 《系统工程理论与实践》, no. 12, 25 December 2006 (2006-12-25) * |
刘兴彬等: "RBF神经网络主成分分析法在交通量预测中应用", 《山西科技》, no. 01, 25 January 2007 (2007-01-25) * |
欧阳等: "基于遗传算法的模糊c-均值聚类算法", 《重庆大学学报(自然科学版)》, no. 06, 30 June 2004 (2004-06-30) * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106023325A (en) * | 2016-05-11 | 2016-10-12 | 贵州车秘科技有限公司 | Cloud-platform highway toll service system |
US10915812B2 (en) | 2016-11-09 | 2021-02-09 | Samsung Electronics Co., Ltd. | Method and system of managing computing paths in an artificial neural network |
CN106408977A (en) * | 2016-12-09 | 2017-02-15 | 思建科技有限公司 | Traffic condition monitoring system and method |
CN107231290A (en) * | 2017-04-19 | 2017-10-03 | 中国建设银行股份有限公司 | A kind of instant communicating method and system |
CN107215362A (en) * | 2017-06-12 | 2017-09-29 | 上海自仪泰雷兹交通自动化系统有限公司 | Middleware adaptation method for trackside system compatible different vendor onboard system |
CN107819831B (en) * | 2017-10-23 | 2020-09-01 | 丹露成都网络技术有限公司 | Metaq and mns-based universal message system |
CN107819831A (en) * | 2017-10-23 | 2018-03-20 | 丹露成都网络技术有限公司 | A kind of universal message system based on metaq and mns |
CN109063752A (en) * | 2018-07-17 | 2018-12-21 | 华北水利水电大学 | The method for sorting of the multiple dimensioned real-time stream of multi-source higher-dimension neural network based |
CN109063752B (en) * | 2018-07-17 | 2022-06-17 | 华北水利水电大学 | Multi-source high-dimensional multi-scale real-time data stream sorting method based on neural network |
CN109035777A (en) * | 2018-08-23 | 2018-12-18 | 河南中裕广恒科技股份有限公司 | Traffic circulation Situation analysis method and system |
CN109035777B (en) * | 2018-08-23 | 2021-03-26 | 河南中裕广恒科技股份有限公司 | Traffic operation situation analysis method and system |
CN113837446A (en) * | 2021-08-30 | 2021-12-24 | 航天科工广信智能技术有限公司 | Multi-source heterogeneous data-based airport land side area traffic situation prediction method |
CN113837446B (en) * | 2021-08-30 | 2024-01-09 | 航天科工广信智能技术有限公司 | Airport land side area traffic situation prediction method based on multi-source heterogeneous data |
CN114495494A (en) * | 2022-01-06 | 2022-05-13 | 电子科技大学 | Traffic situation assessment method based on traffic flow parameter prediction |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102521981A (en) | Computation method for traffic situation based on information-oriented middleware | |
Hamdi et al. | A review of applications, characteristics and challenges in vehicular ad hoc networks (VANETs) | |
Zhao et al. | Novel online sequential learning-based adaptive routing for edge software-defined vehicular networks | |
CN101719315B (en) | Method for acquiring dynamic traffic information based on middleware | |
Zhang et al. | A multilevel information fusion approach for road congestion detection in VANETs | |
Singh et al. | Optimized Node Clustering based on Received Signal Strength with Particle Ordered-filter Routing Used in VANET. | |
CN109687964B (en) | Novel data coordination method for continuous variable quantum key distribution | |
Sangaiah et al. | Hierarchical clustering based on dendrogram in sustainable transportation systems | |
CN104954210A (en) | Method for matching different service types in power distribution communication network with wireless communication modes | |
CN109361725A (en) | Car networking cloud system resource allocation methods based on multi-objective genetic algorithm | |
CN111263331A (en) | Internet of vehicles node reputation evaluation method based on crowd sensing | |
Zhao et al. | Cross-layer-aided opportunistic routing for sparse underwater wireless sensor networks | |
CN105335476A (en) | Method and device for classifying hot event | |
Khan et al. | Smart-City-based data fusion algorithm for internet of things. | |
Bhabani et al. | CluRMA: A cluster-based RSU-enabled message aggregation scheme for vehicular ad hoc networks | |
Pei et al. | Joint optimization of multi-hop broadcast protocol and MAC protocol in vehicular Ad Hoc Networks | |
Liang et al. | Study on DTN routing protocol of vehicle ad hoc network based on machine learning | |
Shoaib et al. | Data aggregation for Vehicular Ad-hoc Network using particle swarm optimization | |
CN112105089A (en) | Communication signal correlation method based on response time probability distribution | |
CN106603197B (en) | A kind of high energy efficiency wireless sensing network data transmission method based on compression network coding | |
CN116805020A (en) | Interest point recommendation method based on graphic neural network and context information perception | |
CN103096412B (en) | Data fusion method with time delay restriction in delay tolerant network | |
Allani et al. | Towards better data management/gathering in connected environments | |
CN114390550A (en) | Network type identification method, related device, equipment and storage medium | |
Wang et al. | RSSI-based node selection using neural network parameterised by particle swarm optimisation |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120627 |