CN115002159A - Sparse crowd sensing system-oriented community classification and user selection method - Google Patents
Sparse crowd sensing system-oriented community classification and user selection method Download PDFInfo
- Publication number
- CN115002159A CN115002159A CN202210630549.3A CN202210630549A CN115002159A CN 115002159 A CN115002159 A CN 115002159A CN 202210630549 A CN202210630549 A CN 202210630549A CN 115002159 A CN115002159 A CN 115002159A
- Authority
- CN
- China
- Prior art keywords
- sensing
- users
- community
- perception
- sparse
- 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
- 238000010187 selection method Methods 0.000 title claims abstract description 8
- 239000011159 matrix material Substances 0.000 claims abstract description 27
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000007115 recruitment Effects 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 9
- 230000008447 perception Effects 0.000 abstract description 36
- 238000001514 detection method Methods 0.000 abstract description 7
- 238000012358 sourcing Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000013507 mapping Methods 0.000 description 5
- 239000000126 substance Substances 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
- H04W4/21—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel for social networking applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
In sparse mobile crowd-sourcing perception, a key problem is user recruitment, that is, an organizer wants to recruit a limited number of users under budget constraints, and a complete perception map is obtained by performing data reasoning on data collected by the users in a sub-area. However, due to the variability of user mobility, it is not possible to predict exactly which sub-areas will be covered by the user and are more valuable. Aiming at the problem, the invention provides a community classification and user selection method facing to a sparse crowd sensing system. Firstly, considering that high-quality users are recruited directly by combining with social relations of the users, carrying out community detection by adopting a class depth automatic encoder non-negative matrix decomposition method, and classifying the perception users; then, matching the position attribute of the sensing task with a community center, determining a recruited community, and recruiting users from the community according to the limit of the sensing cost; and finally, reconstructing a perception map based on the obtained perception data.
Description
Technical Field
The invention belongs to the field of sparse mobile crowd sensing, and particularly relates to a community classification and user selection method for a sparse crowd sensing system.
Background
In recent years, with the popularity of smart phones equipped with rich sensors, Mobile Crowd Sensing (MCS) has become a promising paradigm for facilitating urban Sensing applications, such as traffic data acquisition, air quality detection, and noise detection. In order to obtain high-quality sensing results, the strategy adopted in the mobile crowd-sourcing sensing is to recruit enough participants as much as possible to improve the area coverage, but the strategy may cause high sensing cost, so that the sparse mobile crowd-sourcing sensing is proposed as a new solution, only a small part of urban partitions are sensed by the participants, and the data of the rest of the partitions are inferred based on the sensed data, and the MCS paradigm is called sparse MCS due to the sparsity of the sensing sub-areas.
Sparse mobile crowd sensing (Sparse MCS) is a new paradigm for large-scale fine-grained city monitoring applications that collects sensory data from relatively few areas and infers data for uncovered areas. Sparse mobile crowd sensing is an effective paradigm for reducing the sensing cost of large-scale regional global state monitoring by recruiting only a small number of users to sense data from a selected sub-region (i.e., cell). Since sensing data from different cells (sub-areas) of the target sensing area may result in different levels of inferred data quality, cell selection (i.e. selecting which cells of the target area collect sensing data from the participants) is a key issue that will affect the total amount of data that needs to be collected to ensure a particular quality (i.e. the data collection cost).
In sparse MCSs, one key issue is user recruitment, i.e., an organizer who wishes to recruit a limited number of users under budget constraints, can collect data from several useful sub-areas that are critical for data reasoning to achieve the highest data accuracy for the sensing service. However, due to the variability of user mobility, it is not possible to predict exactly which sub-areas will be covered by the user. Furthermore, it is difficult to predict which sub-regions are more conducive to complex data reasoning without knowing the true values of the sub-regions. Therefore, in sparse MCSs, recruiting the most efficient users is a challenging task. It should be noted that the perceptual data often have more complex and varied spatio-temporal associations, and it is difficult to measure the importance of each perceptual region, which makes the perceptual region selection problem more complex. In addition, the main focus of the current MCS is on the task, the task integrates the multidimensional environment information and the social attributes, the social information of the user is rarely considered, and the matching degree of the task and the node is ignored. Based on this, the present invention contemplates the direct recruitment of high quality users in conjunction with their social relationships.
The social relationship of the users is stable and has certain dependency, and certain aggregation phenomenon is formed in the network, so that different communities are formed. As shown in fig. 1, the communities are classified according to the friend relationship of the users, the classified users are divided into 4 different communities in a virtual space, the users in the same community have the same interest and have a tendency to select a perception task, but the users in the community do not show the characteristic of aggregation in the geographic location but are distributed in different sub-areas, when data collection is performed, the users in different sub-areas in the community upload data of the area, and the same user can reach different sub-areas in different recruitment periods to perform task perception, so that the users after community division can spread over more sub-areas and can provide sensing data with higher quality. When the task is distributed, the community users to be recruited are determined according to the position attribute of the perception task. And processing the users in the community, extracting the position center nodes of the community, matching the position attribute of the perception task with the divided community center positions so as to determine which community is recruited, and then selectively recruiting the users in the selected community according to the perception cost limit.
Disclosure of Invention
Aiming at the existing research methods and the existing problems, the invention provides a sparse crowd sensing user recruitment method based on non-negative matrix factorization of a depth-like automatic encoder. It can be seen from the social network that the social attributes of the users in reality form a community structure through aggregation and refinement, that is, the users in the unified community are closely related to each other and establish a certain trust relationship with each other, so that the social relationship is relatively fixed. In contrast, social attributes of users in different communities, including hobbies, range of activities, connections, etc., vary widely. Different users can be divided into different communities according to the behavior rules and the interaction frequency. The sparse MCS user recruitment problem is divided into three phases as shown in fig. 2, namely a community classification phase, a perceptual task matching phase, and perceptual map reconstruction.
And (4) community classification. The main research community classification of the invention is to divide the perception users into different communities through social relations. The invention adopts a non-negative matrix decomposition method of the class depth automatic encoder to process the friend relationship among users to obtain the community classification result of the users, thereby facilitating the perception task matching of the next stage.
And (5) sensing task matching. The result of community classification is once screened for users to a certain extent, and users in the same community have the same interest and preference due to friend relationships and have the same tendency in the aspect of task selection. And searching a matched community according to the position characteristic value of the task during task perception distribution, and finally selecting proper users in the community to recruit to complete the task perception.
And (5) perception map reconstruction. Due to the completion of the first two stages, the selected users reach the subareas in the recruitment period to collect the sensing data, and the invention utilizes the part of the collected subarea data to deduce a complete sensing map by utilizing a compressed sensing algorithm in combination with the space-time relationship so as to reduce the cost.
Compared with the prior art, the invention has the beneficial effects that: (1) a new idea of recruitment of sparse mobile crowd sensing users is provided, the social relation of the users is considered to perform community detection on the users, the users are reasonably divided into different communities, and the users are recruited based on the classified communities. (2) The sensing tasks are designed to be matched with the community classification center nodes, communities matched with the sensing tasks are selected, the most appropriate user groups in the communities are selected for recruitment, a task publisher is helped to obtain high-quality sensing data, and the task completion rate is improved. (3) Perception map reconstruction is performed through perception data provided by users, the number of recruits of the users is saved, and perception cost is reduced.
Drawings
Fig. 1 is a schematic diagram of user recruitment.
FIG. 2 is an overall flow chart of the present invention.
FIG. 3 is a diagram of user classification before community classification.
FIG. 4 is a diagram illustrating user classification after community classification.
Fig. 5 is a diagram illustrating perceptual task matching.
Fig. 6 is a schematic diagram of perceptual map reconstruction.
Detailed Description
According to the invention, a class depth encoder non-negative matrix decomposition method is adopted for carrying out community classification, as shown in figure 3, users are scattered and disorderly before the community classification, and after the classification is carried out by a community detection algorithm, the users with the same interest preference are aggregated in the same class of community through the processing of social relations, as shown in figure 4.
The existing community division algorithm has the problems of single characteristic factor for dividing communities, lack of specific quantification on social relations and the like, and in consideration of complex and diverse topological structures of real-world networks, the mapping between an original network and a community member space probably contains quite complex hierarchical information, which cannot be explained by a traditional method based on shallow NMF. Aiming at the problems, the invention adopts a depth-like automatic coding non-negative matrix decomposition method to carry out community classification.
NMF-based community detection algorithms typically use social relationships between users, i.e., adjacency matricesBDecomposing into mapping matrixXAnd community membership matrixYThe concrete decomposition formula is as follows:B≈XY. The formula shows that the social relationship between users can be learned to the mapping matrixXAnd community membership matrixYHowever, the structure of the community network in explicit life is very complex in general, and the mapping matrixXIncludes a relatively complex hierarchical structure, so that deep NMF is used to map the matrixXAnd then matrix decomposition is carried out to learn the hidden hierarchical structure.
Adjacency matrix of social networkBIs divided intop+1The matrix is as follows:B≈X 1 X 2 …X p Y p . Wherein the content of the first and second substances,Y p ∈R k n× ,X i ∈R ri-1 ri× (1≤i≤p)at the same timen=r 0 ≥r 1 ≥…≥r p-1 ≥r p =k. At the same time can also beBThe concrete decomposition is as follows:Y p-1 ≈X p Y p ,…,Y 2 ≈ X 3 …X p Y p ,Y 1 ≈X 2 …X p Y p . Obtaining the value of each layer by the formulaY i And further get betterY p Constructing the following objective function, calculatingX 1 ,X 2 ,…,X p ,Y p Equal matrix:min Xi,YpLD =||B-X 1 X 2 …X p Y p || F 2 ,s.t.Y p ≥0,X i ≥0,whereini= 1,2,…,p。
Similar to the depth autoencoder, the encoder component attempts to convert the original network into a community membership space using implicit low-dimensional hidden attributes captured in the middle layer. Each intermediate layer accounts for similarities between nodes of different levels of granularity. The decoder elements are symmetric to the encoder elements. It attempts to reconstruct the original network from the community membership space by means of hierarchical mapping learned in the encoder component. Unlike conventional NMF-based community detection methods that only consider the loss function of the decoder component, DANMF integrates the encoder and decoder components into one unified loss function.
The encoder component converts the network into a community membership space. The decoder component reconstructs the network from the community membership space. Objective function of encoder components:min Xi,YpLE =||Y p -X p T …X 2 T X 1 T B|| F 2 ,s.t.Y p ≥0,X i ≥0,whereini=1,2,…,p. Unified loss function:min Xi,YpL =L D +L E +wL reg =||B-X 1 X 2 …X p Y p || F 2 +||Y p -X p T …X 2 T X 1 T B|| F 2 +wtr (Y p LY p T ),s.t.Y p ≥0,X i ≥0,whereini=1,2,…,p. Wherein the content of the first and second substances,win order to regularize the parameters of the process,Lis a laplacian matrix. Matrix of communitiesX i ,Feature matrixY i ,Community membership matrixY p And carrying out iterative updating according to the updating rule until convergence.
The schematic diagram of the invention for matching with communities based on the location characteristics of the perception task is shown in fig. 5. After the users are reasonably divided into different communities, the matching degree of the perception tasks and the community behavior pattern characteristic values is calculated, and the users are selected from the matched communities to be recruited according to results. A perceptual task may be defined as a tuple (task content, location), where task content refers to various perceptual operations, such as air quality monitoring, temperature monitoring, perceptual noise, taking a picture, taking a video, etc. The location is the center coordinate and the perceived radius of the perceived task area.
The invention considers the matching of the perception tasks and the communities according to the position characteristics of the perception tasks. The specific method comprises the steps of firstly determining the distribution of the perception tasks according to the position attributes of the perception tasks, matching the position attributes of the perception tasks with the centers of the divided communities, judging whether the perception tasks are included in the radius range of the communities, and secondly selecting the classified users in the communities for perception tasks.
Firstly, the distance between users is calculated through longitude and latitude according to the historical track data of the users, and the usersu 1 Has longitude and latitude coordinates of(a 1, b 1 )User u 2 Has latitude and longitude coordinates of(a 2 , b 2 )Distance, distancedThe calculation is as follows:haversin(d/R)= haversin(b 2 -b 1 )+cos(b 1 )cos(b 2 )haversin(a 2 -a 1 ). Wherein the content of the first and second substances,Rthe average value is 6371km for the radius of the earth. Selecting one user from the user set divided into the same community, calculating the distance between the user and the rest users, sequencing the obtained distances, comparing the results, screening out the users exceeding the threshold xi, and not incorporating the node when calculating the community center.
Secondly, the calculation of the community center point is carried out. Considering the longitude and latitude coordinates of a user, firstly converting the longitude and latitude coordinates from degree to radian:a 1 =a 1 ×PI/180,b 1 =b 1 ×PI/180. And then converting the longitude and latitude coordinates into Cartesian coordinates of the first position:X 1 =cos(a 1 )×cos(b 1 ),Y 1 = cos(a 1 )×sin(b 1 ),Z 1 =sin(a 1 ). Setting the position weights of the users to be all1And the coordinates of the other users are converted according to the formula. The total weight of all locations isn,x=(x 1 +x 2 +…+x n )/n,y=(y 1 +y 2 +…+y n )/n,z=(z 1 +z 2 +…+z n )/n. Get the averagex, y, z. Will average outx, y, zCoordinate conversion to latitude and longitude:lon=atan2(y, x),hyp=sqrt(x×x+y×y),lat=atan2(z, hyp). And finally, converting the longitude and latitude into a degree:lat=(lat×180)/PI,lon=(lon×180)/PI. And obtaining the coordinates of the community center point.
Determining perception tasks based on perception data collected as neededh j The position and the sensing radiusrAnd determining a sensing range as a characteristic value of the sensing task. Firstly, a plurality of community central points and perception tasks are comparedh j Selecting communities with small distances as alternatives according to the distance of the positions; and secondly, comparing whether the radius of the perception range is within the community perception range, deleting the community from the alternative community if the radius of the perception range is larger than the radius of the community perception range, and selecting the user in the community under the budget constraint by using the finally reserved community as an optimal choice.
The present invention reconstructs the perceptual map based on compressed sensing, as shown in fig. 6. And (3) recruiting users of partial subareas in sparse mobile crowd sensing, and inferring data of the rest subareas according to data provided by the recruited users to obtain an inference matrix close to a real environment matrix. The algorithm in which data inference is performed is typically represented by compressed sensing. The data is inferred by adopting a compressed sensing method, and the following description is provided for compressed sensing.
Perception matrix considering partial collectionF’Compressed sensing reconstructs complete inferred sensing matrix based on low rank attributesF * :minrank(F * ),s.t., F * 。S=F’. Wherein the content of the first and second substances,Smatrices are collected for the subregions.S[i, j]Indicating whether the corresponding region in the real environment matrix is selected for data collection, if at a periodjIn which a sub-region is selectediTo perform perception, thenS [i, j]=1Otherwise isS[i, j]=0. It is difficult to solve this problem directly due to its non-convexity, based on singular value decomposition, e.g.F * =LR T And a compressed sensing theory, an optimization problem is established, and the minimization rank is converted into minimizationLAndRthe Frobenius norm of (a) is as follows:minw(||L|| F 2 +||R|| F 2 )+||LR T 。S-F’|| F 2 。wherein, the first and the second end of the pipe are connected with each other,wthe method is used for carrying out balance between rank minimization and precision fitness. In order to obtain optimumF * Iteratively estimated using an alternating least squares methodLAndR(F * = LR T )。
in order to better utilize spatio-temporal correlation in perceptual data, explicit spatio-temporal correlation is introduced into compressed sensing, and the optimization function is as follows:minw r (||L|| F 2 +||R|| F 2 )+ ||LR T 。S-F’|| F 2 +w s ||G(LR T )|| F 2 +w t ||(LR T ) H T || F 2 . Wherein the content of the first and second substances,GandHare the spatial and temporal constraint matrices respectively,Gthe matrix controls the correlation of different sub-areas at the same time,Hthe matrix controls the data correlation at different times of the same sensing area,w r, w s, w t come to be flatThe weights of the different elements in the optimization problem are balanced.
The above-described embodiments are not intended to limit the present invention, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (4)
1. A community classification and user selection method for a sparse crowd sensing system is characterized by comprising a community classification module, a sensing task matching module and a sensing map reconstruction module.
2. The sparse crowd sensing system-oriented community classification and user selection method as claimed in claim 1, wherein the sensing users are divided into different communities by a community classification module by using a class depth automatic encoder non-negative matrix decomposition method and aggregated into different communities.
3. The sparse-crowd-sourcing-sensing-system-oriented community classification and user selection method as claimed in claim 1, wherein the sensing tasks are distributed through a sensing task matching module, matchable communities are searched through feature values of the sensing tasks, and finally, appropriate users in the communities are selected for recruitment to complete the sensing tasks.
4. The sparse-crowd-sourcing-sensing-system-oriented community classification and user selection method as claimed in claim 1, wherein a complete sensing map is obtained through a sensing map reconstruction module, sensing data are collected by the fact that selected sensing users reach a sub-area within an recruitment period, and the complete sensing map is deduced through a compressed sensing algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210630549.3A CN115002159B (en) | 2022-06-06 | 2022-06-06 | Community classification and user selection method for sparse group intelligent perception system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210630549.3A CN115002159B (en) | 2022-06-06 | 2022-06-06 | Community classification and user selection method for sparse group intelligent perception system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115002159A true CN115002159A (en) | 2022-09-02 |
CN115002159B CN115002159B (en) | 2023-10-03 |
Family
ID=83033221
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210630549.3A Active CN115002159B (en) | 2022-06-06 | 2022-06-06 | Community classification and user selection method for sparse group intelligent perception system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115002159B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115964626A (en) * | 2022-10-27 | 2023-04-14 | 河南大学 | Community detection method based on dynamic multi-scale feature fusion network |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103533078A (en) * | 2013-10-24 | 2014-01-22 | 无锡赛思汇智科技有限公司 | Method and system for generating map |
US20140343984A1 (en) * | 2013-03-14 | 2014-11-20 | University Of Southern California | Spatial crowdsourcing with trustworthy query answering |
CN107563616A (en) * | 2017-08-17 | 2018-01-09 | 上海大学 | A kind of user task distribution and the quorum-sensing system system and method for incentives strategy |
CN109347924A (en) * | 2018-09-20 | 2019-02-15 | 西北大学 | A kind of recommended method based on intelligent perception |
CN110061863A (en) * | 2019-03-25 | 2019-07-26 | 浙江理工大学 | A kind of distributed multi-task intelligent perception method based on fairness in sparse network |
CN113191023A (en) * | 2021-05-28 | 2021-07-30 | 中国人民解放军国防科技大学 | Crowd-sourcing-aware task allocation and user recruitment model cross-validation method and system |
CN114745465A (en) * | 2022-03-24 | 2022-07-12 | 马斌斌 | Interactive noise self-prior sensing analysis system for smart phone |
-
2022
- 2022-06-06 CN CN202210630549.3A patent/CN115002159B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140343984A1 (en) * | 2013-03-14 | 2014-11-20 | University Of Southern California | Spatial crowdsourcing with trustworthy query answering |
CN103533078A (en) * | 2013-10-24 | 2014-01-22 | 无锡赛思汇智科技有限公司 | Method and system for generating map |
CN107563616A (en) * | 2017-08-17 | 2018-01-09 | 上海大学 | A kind of user task distribution and the quorum-sensing system system and method for incentives strategy |
CN109347924A (en) * | 2018-09-20 | 2019-02-15 | 西北大学 | A kind of recommended method based on intelligent perception |
CN110061863A (en) * | 2019-03-25 | 2019-07-26 | 浙江理工大学 | A kind of distributed multi-task intelligent perception method based on fairness in sparse network |
CN113191023A (en) * | 2021-05-28 | 2021-07-30 | 中国人民解放军国防科技大学 | Crowd-sourcing-aware task allocation and user recruitment model cross-validation method and system |
CN114745465A (en) * | 2022-03-24 | 2022-07-12 | 马斌斌 | Interactive noise self-prior sensing analysis system for smart phone |
Non-Patent Citations (1)
Title |
---|
向罗勇;陈文;张陆洋;: "联合区域热度和社交属性感知的移动群智感知参与者选择机制", 电信科学, no. 02 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115964626A (en) * | 2022-10-27 | 2023-04-14 | 河南大学 | Community detection method based on dynamic multi-scale feature fusion network |
Also Published As
Publication number | Publication date |
---|---|
CN115002159B (en) | 2023-10-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Song et al. | A novel convolutional neural network based indoor localization framework with WiFi fingerprinting | |
Ahmad et al. | Toward modeling and optimization of features selection in Big Data based social Internet of Things | |
CN111756848B (en) | QoS optimization method based on federal learning and mobile perception under mobile edge environment | |
CN108804551B (en) | Spatial interest point recommendation method considering diversity and individuation | |
Chang et al. | A graph-based QoS prediction approach for web service recommendation | |
Mo et al. | Event recommendation in social networks based on reverse random walk and participant scale control | |
CN109614458A (en) | Community in urban areas structure method for digging and device based on navigation data | |
CN111222847B (en) | Open source community developer recommendation method based on deep learning and unsupervised clustering | |
CN105024886B (en) | A kind of Fast W eb service QoS Forecasting Methodologies based on user metadata | |
CN110297875A (en) | It is a kind of to assess the method and apparatus that demand tightness is contacted between each functional areas in city | |
CN115002159A (en) | Sparse crowd sensing system-oriented community classification and user selection method | |
Shi et al. | QoS prediction for smart service management and recommendation based on the location of mobile users | |
Wang et al. | Hierarchical and overlapping social circle identification in ego networks based on link clustering | |
Xu et al. | Deep convolutional recurrent model for region recommendation with spatial and temporal contexts | |
CN112954624B (en) | Hybrid land use form estimation method based on mobile phone signaling big data | |
Huan et al. | Indoor location fingerprinting algorithm based on path loss parameter estimation and bayesian inference | |
CN112508408B (en) | Mapping model construction method of radio resource management index under edge calculation | |
Yuan | Representing spatiotemporal processes to support knowledge discovery in GIS databases | |
CN110837540A (en) | Method and system for processing spatial position data | |
CN114385376B (en) | Client selection method for federal learning of lower edge side of heterogeneous data | |
CN117079124B (en) | Urban and rural landscape image quantification and promotion method based on community differentiation | |
Zhu et al. | SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis | |
Pan et al. | Global mean estimation using a self-organizing dual-zoning method for preferential sampling | |
Peng et al. | A node selection paradigm for crowdsourcing service based on region feature in crowd sensing | |
Manetos et al. | Integrating Data Mining Methods for modeling urban growth dynamics |
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 |