CN114971047A - Mobile crowd sensing-oriented user collaborative optimization method - Google Patents
Mobile crowd sensing-oriented user collaborative optimization method Download PDFInfo
- Publication number
- CN114971047A CN114971047A CN202210626610.7A CN202210626610A CN114971047A CN 114971047 A CN114971047 A CN 114971047A CN 202210626610 A CN202210626610 A CN 202210626610A CN 114971047 A CN114971047 A CN 114971047A
- Authority
- CN
- China
- Prior art keywords
- user
- task
- users
- sensing
- perception
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 23
- 238000000034 method Methods 0.000 title claims abstract description 17
- 230000008447 perception Effects 0.000 claims abstract description 27
- 238000010845 search algorithm Methods 0.000 claims abstract description 5
- 241000287127 Passeridae Species 0.000 claims abstract description 4
- 238000011160 research Methods 0.000 abstract description 3
- 230000000052 comparative effect Effects 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001953 sensory effect Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 241000283153 Cetacea Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 229940060587 alpha e Drugs 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000739 chaotic effect Effects 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000002789 length control Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012358 sourcing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
- G06F7/58—Random or pseudo-random number generators
- G06F7/588—Random number generators, i.e. based on natural stochastic processes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/101—Collaborative creation, e.g. joint development of products or services
-
- 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)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The task allocation problem of how to quickly allocate the sensing task to the optimal execution user on the premise of ensuring the sensing quality and reducing the cost in the existing mobile crowd sensing is the key point of research. In order to solve the problem, a CSSA optimization method for selecting a perception user based on a sparrow search algorithm is provided. The method comprises the steps of firstly modeling a perception user, proposing a concept of user fitness, sequentially classifying basic information of the user into four aspects of position, electric quantity, equipment and credit, and sequentially calculating the fitness. Secondly, the priorities of the perception users are comprehensively considered according to the fitness values, the users are classified according to the priorities of the users, the process that the users finish tasks is simulated by adopting an intelligent optimization algorithm, and finally the optimal users suitable for perception tasks are selected. Through a comparative experiment of the algorithm provided by the invention and other optimization algorithms under the same environment, the result shows that the algorithm has higher performance in solving the task allocation problem.
Description
Technical Field
The invention belongs to the field of mobile crowd sensing, and particularly relates to a user collaborative optimization method based on an intelligent optimization algorithm.
Background
Mobile Crowd Sensing (MCS) as a new Sensing paradigm combines artificial intelligence with the internet of things, and performs a Sensing task requested by a task requester by using a Mobile user with intelligent devices (including a Mobile phone, an intelligent car, a wearable device, and the like). The inherent mobility of mobile users makes mobile group awareness (MCS) a common platform that can replace or supplement existing static awareness infrastructure. These data acquisitions make MCS play a significant role in the fields of traffic monitoring, environmental phenomenon observation, mobile medicine, and the like. The perception system consists of a platform, a task publisher and participant users, wherein the task publisher can be a machine or a person, and the participation in the perception task needs to consume the time of the participant and the perception, calculation and communication resources of equipment. To stimulate widespread participation by users, some MCS systems provide rewards in return for valuable sensory reports submitted by users. The incentive may take different forms, including money, entertainment obtained through the game, or services provided by the system. These task budgets are allocated to participants who complete the sensing task, depending on whether it is the time it takes to perceive the data or the quality of the sensory report delivered. Therefore, it is an extremely important precondition to select a suitable user in order to improve the data quality of the perception task and reduce the task cost.
In the mobile crowd sensing system, a user participates in a task, and data are collected by mobile sensing equipment and uploaded to a platform, so that data collection is completed. How well the user is, has a critical impact on the overall task completion. In the task allocation process, the degree of engagement between the user and the task is found by analyzing the attributes of the user, and the method can be regarded as finding an optimal user selection scheme which meets a plurality of constraint conditions in a random environment. The previous methods usually focus on increasing the number of users and searching for the optimal solution of a single user, while the task of crowd sensing needs to be completed by a plurality of users, for example, the task needs a plurality of types of sensing data, the single user often cannot meet the task requirement, and the previous case of increasing the cost and data redundancy is caused by the collection of the same type of data by a plurality of users.
Task allocation is a main research direction of MCS, and a mobile user collects sensing data to obtain a sensing result so as to complete a task. In general, factors that affect the quality of a task are many, including the amount of data collected, the duration of the task, and the spatiotemporal coverage of the task. More sensory data collected generally means higher task quality; proper task spatio-temporal coverage also generally means higher task quality. There are also many factors that affect the cost of the mission, including the cost of recruiting users, the cost of moving users, and the cost of data transmission. In order to improve the perceived data quality and reduce the task incentive budget, the adaptive value of the user can be analyzed by analyzing the matching degree between the user and the task, so that the task is distributed to the user.
In recent years, as si (sweep intelligence) optimization algorithms have been rapidly developed, more and more intelligent optimization algorithms with superior performance have been proposed, such as Grey Wolf Optimization (GWO) algorithm, Whale Optimization Algorithm (WOA), Gravity Search Algorithm (GSA), and the like. At present, the SI optimization algorithm is gradually becoming another main method for solving the task allocation problem in the crowd sensing, and there are many methods for combining the SI optimization algorithm with the task allocation of the crowd sensing.
Disclosure of Invention
The cooperative cooperation among multiple users has a great research space for improving the perception performance, and a new framework CSSA (crown sensing spark Search algorithm) is provided by combining a Sparrow Search algorithm with excellent performance in an intelligent optimization algorithm for user selection of perception tasks, so that the perception data quality and the distribution efficiency are improved. As shown in fig. 1, by coordinating a plurality of users and collecting and aggregating data by their own sensing devices, the quality of the collected sensing data can be further improved.
A user selection framework is proposed herein that leverages the impact of various attributes of users on task-aware data quality, as well as collaborative collaboration issues among multiple users. The objective of this strategy is to improve the perceived data quality while guaranteeing the task cost, while also considering the time of user selection, which mainly attributes the influencing factors to the following aspects: distance relationships between users and tasks; the matching degree of the user equipment sensor type and the task; the operational condition of the user equipment; the reputation of the user.
Because the complexity of the problem to be solved is high, a fitness concept is provided for the influence factors, and the fitness value is used as a reference for measuring the priority and the matching degree of the user. The data information to be acquired is divided into user position information acquired by positioning, device remaining capacity and device sensor type information uploaded by the state of the user device, and a platform estimates the currently used reputation value according to the historical task completion data record of the user, so that the control of the task data quality is completed, whether the user is suitable for completing the current task is analyzed, and the fitness values are used as important reference standards of an intelligent optimization algorithm, as shown in fig. 2.
The mobile crowd-sourcing sensing platform consists of a plurality of sensing users, U represents a set of users which can participate in the system when a task is released, and F = (F) 1 , f 2 , f 3 ,…, f n ) And representing the fitness values of all current users to the task, and sorting the fitness values into a user set. U = (U) 1 , u 2 , u 3 ,…, u n ) And dividing the users into explorers and followers according to a proportion, respectively carrying out task perception according to different responsibilities, and finally screening out proper perception users according to an intelligent optimization algorithm.
Meanwhile, in order to improve the selection efficiency and the data quality of the user, the task is completed in a participant cooperation mode. The data types required to be sensed by the current task are analyzed, the users are respectively responsible for the types of information which can be provided by the users according to the difference of the sensors of the users, and then the platform is combined with the contents uploaded by the users to perform summary analysis to finish the acquisition of the sensing data. The algorithm utilizes the characteristic of mutual cooperation among groups, which is beneficial to the group cooperation of the participator users in the group intelligent perception to complete the perception task, and simultaneously, the comprehensive analysis is carried out on the matching degree of the multi-attributes of the position, the equipment and the like of the perception user and the user. In the crowd sensing, the sensing data quality and the task allocation time can be improved by analyzing the multiple influence factors and the user selection strategy of the cooperation between the users, and the performance of the crowd sensing platform is greatly improved.
Drawings
FIG. 1 is a schematic diagram of promotion of user collaboration.
FIG. 2 is an overall flow chart of the present invention.
FIG. 3 is a diagram of the coverage relationship of sensor types.
Detailed Description
And the position fitness is obtained by calculating whether the position relation between the task and the user is matched, and when the user is far away from the task, the distance required to be moved by the user is increased, so that the task completion time and the higher task cost are improved. For the situation, the concept of location fitness is introduced, and the distance between a user and a task is compared to be used as an index for measuring the fitness. The calculation formula is as follows: locFit i =(d max -d i )/ d max (d i ≤d max ) Wherein d is i And calculating the distance between the user and the task by adopting the Euclidean distance. When the original path of the user approaches the task sensing area, the position adaptability between the user and the task is continuously improved along with the continuous approach between the user and the task, and the intention of the user for executing the task is increased, so that the user can actively improve the speed and reduce the moving time, the task completing speed is reduced, and the overall efficiency is improved.
The electric quantity fitness is taken as the consideration of the residual electric quantity of the mobile equipment, because the sensor sensing data is required to be continuously utilized in the process of completing the task, and the sensing data is uploaded through a communication network and transmitted to the platform in real time, the electric quantity of the mobile equipment is required to be continuously consumed in the process. Therefore, the power fitness is also an important consideration parameter to determine whether the mobile device is capable of completing the sensing data collection, and when the power is low, the user is likely not to participate in the task. The calculation of the electric quantity fitness is expressed as [0,1 ] according to the electric quantity remaining percentage]The data in the formula is represented in a specification mode, and the formula is as follows: eltFit i =CE i /E i 。
The equipment adaptability is different according to the data types required to be sensed by the tasks, and the requirements for sensing the user equipment are different, so that the equipment adaptability is high, and the requirements for sensing the user equipment are differentThe availability of the required sensors on the sensing devices of the candidate participants needs to be considered, which significantly affects the reliability of the data and the quality of the sensing results. In order to quantify the matching degree, the hardware capability matching degree between the user and the task is expressed by the device fitness, the task is sequentially distributed to the optimal user, the cost required by the task can be reduced, the data quality can be improved, and the matching degree of the device information and the perception content is shown in fig. 3. Wherein, Samesen i =UserSen i And n is TaskSen which is a sensor coincidence set and represents a part of coincidence of the user equipment sensor category set and the task perception content set. Some of them are indispensable sensors, and other non-critical categories are that the contact ratio is better and better, so the contact ratio of the sensors is: equFit i =η 1 *(Sig i /Sig max )+η 2 *(SameSen i and/TaskSen), each sensing user does not need to have all the required sensing sensor types, and the acquisition of various types of sensing data can be completed through the cooperative cooperation among multiple users.
Reputation fitness, and thus its reputation is evaluated based on the user's previous participation in the perception task. Evaluation criteria include whether they are dedicated to completing tasks assigned to them, and their ability to successfully complete these tasks. The following equations are used to evaluate the reputation parameters of each participant separately: CT i =Spt i /Ct i ，SCT i =Sct i /Ft i 。Spt i Wherein a collection of tasks, Ct, is represented for the user to participate in i Representing a collection of tasks selected by the user, Sct i A set of tasks, Ft, representing successful completion of the user i Representing the set of tasks completed by the user. Since these two parameters vary in a relative manner, their collective average is used to give the overall reputation of the participant. Therefore, the individual reputation fitness calculation formula for each user is as follows: reppit i =sqrt(CT i *SCT i )。
When the perception task is released, a perception user reporting platform with the intention of participating in the task exists, and the set of participants is U = (U) 1 , u 2 , u 3 ,…, u n ) Platform, platformFirstly, according to user attribute and historical data, making said data pass through formula F i =locFit i +eltFit i +equFit i +repFit i Calculating a fitness value F for each user i . Initializing the positions of all users in an optimization algorithm, and in order to improve the global search capability of the algorithm and avoid the reduction of population diversity in the later iteration stage, generating random numbers by adopting a chaotic mapping method instead of the random numbers, so that the positions have randomness and regularity, and the formula is as follows: u. of i+1 =u i *μ*(1-u i )，μ∈[3.5,4],u i E (0,1), recording the positions of the n participants in the d dimension by adopting a matrix, and simultaneously respectively calculating corresponding fitness values.
By a fitness value F i The users are sorted, and are divided into two different identities of an explorer and a follower through a set value Pr. By array ID n]The identity of the current user is recorded, 0 represents follower and 1 represents explorer. The seeker is responsible for acquiring main perception data as a main accomplishment of the perception task due to high task adaptability; the follower corresponds to the identity of the seeker, and the follower performs data acquisition along with the seeker due to low fitness and is responsible for supplementing data and perfecting the perception data type. Such as: when the value of Pr is set to 0.2, the ratio of the seeker to the follower is 2: 8. Wherein, the position of the seeker is updated as follows: when Pn<In CT, U i,j t+1 = U i,j t *exp(-i/α*iter max ) (ii) a When Pn is greater than or equal to CT, U i,j t+1 =U i,j t + Q.L. Where t represents the current number of iterations, j =1,2,
d, represents the current dimension, U i,j t Representing the position of the ith sensing user in the jth dimension of the iteration t, iter max Is the constant with the largest number of iterations. Alpha e (0,1) is a random number, Pn (Pn e [0,1 ]]) And CT (CT ∈ [0.5,1.0 ]]) Representing the task completion of the sub-region and the completion threshold of the sub-region, respectively. Q is a random number following a normal distribution, and I is a matrix of dimensions 1 x d, whereinEach element is 1. When Pn<In CT, the number of task completion people in the current region does not reach the threshold value, and the current searcher can continue to complete the task in the sub-region; when Pn is larger than or equal to CT, the number of participants in the current area meets the requirement of task completion, and all explorers need to go to other sub-areas to complete the perception task.
As for the follower, the follower explorer moves nearby to assist in completing tasks, when the current explorer is found to have a lower fitness value than the follower explorer, a competition relationship occurs, the identities of the two are changed, and the current user ID [ i [ ]]The value of (b) is also inverted when i>n/2, position U i,j t+1 =Q*exp((U worst t -U i,j t )/i 2 ) (ii) a When i is less than or equal to n/2, U i,j t+1 = U p t+1 +|U i,j t - U p t+1 |*A + L. Wherein, U p Best position occupied by the seeker, U worst Representing the current global worst position. A represents a matrix of dimension 1 x d, wherein each element is randomly assigned a value of 1 or-1, and A + =A T (AA T ) -1 . When the fitness value is appropriate, moving near the position of the current seeker; when i is>n/2, this means that the follower has a very low fitness value in the current sensing user queue, and cannot complete the current task, and then search for sensing tasks in other areas.
In addition, a part of all task participants is selected as a monitor, the monitoring is generated randomly in the crowd and is responsible for preventing users from concentrating on the optimal sensing position and falling into the local optimal sensing position, 10% -20% of sensing users are selected as the monitor, and when f is the optimal sensing position, the monitoring is performed i ≠f g While, U i,j t+1 = U p t+1 +β*(U worst t - U best t ) When f is i =f g While, U i,j t+1 = U p t+1 +β*(U i,j t - U best t ). Wherein U is best And U is worst Respectively representing the current global optimum position and worst position, taking beta as a step length control parameter, and being clothesFrom a normally distributed random number with mean 0 and variance 1, f i Is the fitness value of the current sparrow individual, f g Is the current global best fitness value. To prevent getting into local optima, the user escapes to a random position between the optimal position and the worst position if he is in the optimal position, otherwise to a random position between himself and the random position.
Based on the above user selection model, considering data quality, task cost, and allocation time, the user selection problem herein can be defined as: f = max Σ i=1 k [(equFit i +eltFit i )*repFit i ]Satisfy the min Σ i=1 k (d i )、∑ i=1 k M i =I
Wherein, I is a full 1 matrix of 1 × j for controlling the sum of all user sensor types to meet the types required by the task, wherein j is the number of the types required by the task, sigma i=1 k (d i ) By minimizing the total distance for the sum of all user-to-task distances, the distance that the user is perceived to move to complete the task may be reduced, thereby reducing costs. The purpose of the optimization algorithm is to find the maximum value of the objective function, namely to find the user most suitable for the task requirement, so that the data quality is improved.
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 (3)
1. A user collaborative optimization method facing mobile crowd sensing is characterized by comprising a user fitness processing module, an iteration updating module and a sensing user selection module.
2. The mobile swarm intelligence perception user collaborative optimization method based on swarm intelligence optimization according to claim 1, wherein position, electric quantity, equipment and credit fitness are respectively calculated according to matching degrees between users and tasks, and priorities of the users are quantitatively sorted to form a priority sequence of the users for the tasks.
3. The mobile swarm intelligence perception user collaborative optimization method based on swarm intelligence optimization according to claim 1, wherein a task user selection optimal solution is formed through user collaborative cooperation and by a sparrow search algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210626610.7A CN114971047A (en) | 2022-06-04 | 2022-06-04 | Mobile crowd sensing-oriented user collaborative optimization method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210626610.7A CN114971047A (en) | 2022-06-04 | 2022-06-04 | Mobile crowd sensing-oriented user collaborative optimization method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114971047A true CN114971047A (en) | 2022-08-30 |
Family
ID=82960083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210626610.7A Pending CN114971047A (en) | 2022-06-04 | 2022-06-04 | Mobile crowd sensing-oriented user collaborative optimization method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114971047A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115865476A (en) * | 2022-11-29 | 2023-03-28 | 中南大学 | Credible data perception method based on participant reliability and task matching |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210903A (en) * | 2019-05-31 | 2019-09-06 | 南京邮电大学 | A kind of intelligent perception motivational techniques based on user location and credit worthiness |
| CN111432361A (en) * | 2020-03-19 | 2020-07-17 | 长春理工大学 | User incentive strategy determination method and system based on crowd sensing network |
| CN113344464A (en) * | 2021-07-12 | 2021-09-03 | 哈尔滨理工大学 | Task and user potential relation mining method facing mobile crowd sensing system |
| CN113516229A (en) * | 2021-07-09 | 2021-10-19 | 哈尔滨理工大学 | Credible user optimization selection method facing crowd sensing system |
| WO2021213293A1 (en) * | 2020-04-24 | 2021-10-28 | 西北工业大学 | Ubiquitous operating system oriented toward group intelligence perception |
| CN114501470A (en) * | 2022-01-11 | 2022-05-13 | 南京邮电大学 | Crowd-sourcing spectrum monitoring method based on two-stage user selection |
-
2022
- 2022-06-04 CN CN202210626610.7A patent/CN114971047A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110210903A (en) * | 2019-05-31 | 2019-09-06 | 南京邮电大学 | A kind of intelligent perception motivational techniques based on user location and credit worthiness |
| CN111432361A (en) * | 2020-03-19 | 2020-07-17 | 长春理工大学 | User incentive strategy determination method and system based on crowd sensing network |
| WO2021213293A1 (en) * | 2020-04-24 | 2021-10-28 | 西北工业大学 | Ubiquitous operating system oriented toward group intelligence perception |
| CN113516229A (en) * | 2021-07-09 | 2021-10-19 | 哈尔滨理工大学 | Credible user optimization selection method facing crowd sensing system |
| CN113344464A (en) * | 2021-07-12 | 2021-09-03 | 哈尔滨理工大学 | Task and user potential relation mining method facing mobile crowd sensing system |
| CN114501470A (en) * | 2022-01-11 | 2022-05-13 | 南京邮电大学 | Crowd-sourcing spectrum monitoring method based on two-stage user selection |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115865476A (en) * | 2022-11-29 | 2023-03-28 | 中南大学 | Credible data perception method based on participant reliability and task matching |
| CN115865476B (en) * | 2022-11-29 | 2024-04-16 | 中南大学 | Trusted data perception method based on participant reliability and task matching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tanzil et al. | Adaptive scheme for caching YouTube content in a cellular network: Machine learning approach | |
| Yang et al. | An efficient hybrid data clustering method based on K-harmonic means and Particle Swarm Optimization | |
| CN111770454B (en) | Game method for position privacy protection and platform task allocation in mobile crowd sensing | |
| CN110069706A (en) | Method, end side equipment, cloud side apparatus and the end cloud cooperative system of data processing | |
| Leung et al. | Explainable artificial intelligence for data science on customer churn | |
| Jiau et al. | Services-oriented computing using the compact genetic algorithm for solving the carpool services problem | |
| CN114971047A (en) | Mobile crowd sensing-oriented user collaborative optimization method | |
| CN107066322B (en) | A kind of online task allocating method towards self-organizing intelligent perception system | |
| CN110059770A (en) | Adaptive task distribution method, device and associated component based on position prediction | |
| CN113537509A (en) | Collaborative model training method and device | |
| Jiang et al. | Federated learning based mobile crowd sensing with unreliable user data | |
| Soula et al. | Intelligent tasks allocation at the edge based on machine learning and bio-inspired algorithms | |
| Mozaffari et al. | E2FL: Equal and equitable federated learning | |
| Gong et al. | Evolutionary computation in China: A literature survey | |
| CN113688200B (en) | Decision tree-based special population action track collection method and system | |
| CN117035305A (en) | Stable task allocation method based on deterministic track in crowdsourcing positioning scene | |
| Cui et al. | The learning stimulated sensing-transmission coordination via age of updates in distributed uav swarm | |
| CN109685238A (en) | Resource Exchange method and apparatus, storage medium and electronic device | |
| Abegaz et al. | Multi-agent Federated Reinforcement Learning for Resource Allocation in UAV-enabled Internet of Medical Things Networks | |
| CN113516229A (en) | Credible user optimization selection method facing crowd sensing system | |
| Grimes et al. | An agent-based approach to predicting lymph node metastasis status in breast cancer | |
| Li et al. | Solving fuzzy scheduling using clustering method and bacterial foraging algorithm | |
| Liu et al. | Application of distributed probability model in sports based on deep learning: deep belief network (DL-DBN) algorithm for human behaviour analysis | |
| Lin et al. | Fuzzy similarity clustering for consumer-centric QOS-aware selection of web services | |
| de Souza et al. | ATHENA-FL: Avoiding Statistical Heterogeneity with One-versus-All in Federated Learning |
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 |