CN113705083B - Participant reliability assessment and true value inference method in mobile crowd sensing - Google Patents
Participant reliability assessment and true value inference method in mobile crowd sensing Download PDFInfo
- Publication number
- CN113705083B CN113705083B CN202110874280.9A CN202110874280A CN113705083B CN 113705083 B CN113705083 B CN 113705083B CN 202110874280 A CN202110874280 A CN 202110874280A CN 113705083 B CN113705083 B CN 113705083B
- Authority
- CN
- China
- Prior art keywords
- participant
- task
- reliability
- tasks
- participants
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000008447 perception Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 7
- 230000005484 gravity Effects 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/048—Activation functions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Abstract
The invention discloses a method for evaluating and deducing the reliability of a participant in mobile crowd sensing, which models the reliability of the participant through a sensing platform, wherein the current state of the participant refers to the instantaneous factor of the participant when executing the current task, and the reliability of the participant for completing the task is deduced through the current state; participant current state M i,j Further comprises the current state of the participant including the willingness W of the participant to execute the task i,j Familiarity degree W of participants with perceived locations i,j Preference degree of participants for perceived taskParticipant historical reliability assessment user history of performing tasksParticipant historical reliability further includes reliability of the participant under a certain class of tasksOverall reliability h (X) of the participant execution task; and carrying out true value inference to obtain a true value of the numerical task and a true value of the type task respectively. Compared with the prior art, the invention 1) constructs a unified participant fine granularity reliability assessment method; 2) The estimated true value with smaller error can be generated.
Description
Technical Field
The invention relates to the technical fields of Internet of things, crowd sensing and the like, in particular to a reliability evaluation method for participants in mobile crowd sensing.
Background
In recent years, mobile computing devices (such as mobile phones and tablet computers) are rapidly popularized in life of people, and an operating system mounted on the intelligent mobile device has programmable characteristics and embedded sensing devices (such as a GPS (global positioning system), a gyroscope, an acceleration sensor, a vibration sensor and a camera) built in the intelligent mobile device, so that an Internet of things sensing mode based on the sensing capability of the mobile device, namely 'mobile crowd sensing' (Mobile Crowdsensing) is generated. The mobile sensing network formed by the portable devices can sense the region where the human is frequently active anytime and anywhere, and acquire the information of physical environment, personal behaviors, vehicle states and the like of the crowd, so that the ubiquitous interconnection and thorough sensing requirements of the Internet of things are met. Compared with the traditional sensing mode of the Internet of things for fixedly deploying the sensor network, the mode overcomes the limitations of high networking cost, difficult system maintenance and inflexible service, greatly reduces the application cost of the Internet of things, improves the application efficiency of the Internet of things, and forms important complementation for the data collection mode of the sensor network which is intentionally and actively deployed.
A typical mobile crowd-sourced network is generally composed of two parts, a awareness platform and participants. The sensing platform consists of a plurality of sensing servers positioned in the data center; the participants can collect sensing data by using various mobile sensing terminals, and are connected with the sensing platform in a network manner by a mobile cellular network or short-distance wireless communication manner, and upload the sensing data. The workflow of the system can be described as the following steps.
(1) Issuing tasks: the perception platform divides a certain perception task into a plurality of perception sub-tasks, distributes the tasks to participants, and adopts a certain incentive mechanism to attract users to participate.
(2) Data perception: after receiving the perception task, the participators decide whether to participate in the perception task according to the actual situation of the participators, and after selecting to participate in the task, the participators use the proper sensors in the carried mobile equipment to acquire data.
(3) And (3) data transmission: the participants use some security and privacy protection means to upload the data to the perception platform.
(4) Data management and analysis: the sensing platform manages and analyzes the collected sensing data.
The mobile crowd sensing network becomes a novel and important sensing means of the Internet of things, and universal mobile sensing equipment can be utilized to complete large-scale and complex social sensing tasks which are difficult to achieve by individuals. The mobile perception network system can be applied to a plurality of application fields of the Internet of things which are increasingly important at present. Such as city management, intelligent transportation, environmental monitoring, public health, medical health, etc. While bringing these advantages, the crowd-sourced network allows common users to participate in the awareness activities, so that the reliability of the users is difficult to guarantee, and the collected data may be missing and noisy, and the data of different users even conflict with each other. How to process data, infer reliability and true values is a core problem of crowd-sourced networks. The present invention addresses such issues by constructing a comprehensive set of reliability evaluation indicators.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method for evaluating the reliability and deducing the true value of the participants in crowd sensing, simultaneously considers heterogeneous users, various tasks and space-time factors, and filters the data provided by the participants by analyzing the reliability of different participants to deduce the true value which is closer to the real value of the physical world.
The invention discloses a method for evaluating reliability and deducing true value of participants in mobile crowd sensing, which comprises the following steps:
modeling the reliability of the participant through a perception platform, wherein the reliability model comprises a current state and historical reliability of the participant; the current state of the participant refers to an instantaneous factor of the participant when the participant executes the current task, and the reliability of completing the task is deduced through the current state; participant current state M i,j Including willingness W of participants in performing tasks i,j Familiarity degree W of participants with perceived locations i,j Preference degree of participants for perceived task
Modeling of the participant's current state includes the following:
the willingness calculation formula when the participant executes the task is:
wherein ,Vi r For mobile device battery capacity, V i a D is the residual power of the mobile device θ Radius of crowd sensing task sensing area d i,j Distance from the participant to the perceived task location;
the calculation formula of the familiarity degree of the participator to the perception location is as follows:
wherein ,specific gravity for participants to perform tasks at the same place, < >>For the average time of stay of the participants in the task area, t j Is a threshold value;
participant preference for perceived taskThe calculation formula of (2) is as follows:
current state value M of participant i,j The calculation formula is as follows:
wherein ,to the participant to perceive the familiarity of the place, W i,j For the participant's wish, add>For the participant to have a perceived task preference, α=1 is that the participant has performed such tasks, and α=0 is that the participant has not performed such tasks;
evaluating the history condition of the user executing the task by utilizing the history reliability;
the total information entropy of the task executed by the participant is obtained, and the calculation formula is as follows:
wherein M is the number of sensing tasks, C is the number of categories of sensing tasks, M c For each class of task set, H (Y Mc ) Information entropy when executing a certain class of tasks for the participant, wherein delta is an introducing function;
the historical reliability of the participant in executing the task is obtained, and the calculation formula is as follows:
wherein ,providing high-quality data probability for the participants, wherein h (x) is the total information entropy of the tasks performed by the participants;
initializing the reliability value of the participant by using the participant reliability model to obtain a reliability initialization value q of each participant i,j The calculation formula is as follows:
wherein lambda is the slip factor,historical reliability of performing tasks for participants;
and carrying out true value inference by using the reliability initialization value, wherein the calculation formula is as follows:
wherein, if the task is a numerical task, the method causesSolving partial derivatives on two sides of the function, enabling the partial derivatives to be 0, and solving the true value of the numerical task;
if it is a classified task, ifThen-> Then->The true value of the score type task is solved.
Compared with the prior art, the invention can achieve the following beneficial effects:
1) A unified participant fine granularity reliability assessment method is constructed;
2) The estimated true value with smaller error can be generated.
Drawings
FIG. 1 is a flowchart showing a method for evaluating reliability and deducing true value of participants in mobile crowd sensing;
FIG. 2 is a block diagram of an embodiment of a system for performing the reliability assessment and true value inference method of participants in mobile crowd sensing according to the present invention;
FIG. 3 is a flow chart for modeling participant reliability in crowd sensing;
fig. 4 is a flow chart of true value inference in crowd-sourced perception.
Detailed Description
The technical scheme of the invention is further described in detail below with reference to the attached drawings and specific embodiments.
As shown in FIG. 1, a flow chart of a method for evaluating reliability and deducing true value of participants in mobile crowd sensing is provided. The process comprises the following steps:
modeling the reliability of the participant through a perception platform, wherein the reliability model comprises a current state and historical reliability of the participant; the current state of the participant refers to an instantaneous factor of the participant when the participant executes the current task, and the reliability of the participant for completing the current task is deduced through the current state; participant current state M i,j Including willingness W of participants in performing tasks i,j Familiarity degree W of participants with perceived locations i,j Preference degree of participants for perceived task
Modeling is carried out on modeling of the current state of the participant, and the formula is as follows:
wherein ,Vi r For mobile device battery capacity, V i a D is the residual power of the mobile device θ Radius of crowd sensing task sensing area d i,j Distance from the participant to the perceived task location;
the participant models the familiarity of the perceived location, and the formula is:
wherein ,specific gravity for participants to perform tasks at the same place, < >>For the average time of stay of the participants in the task area, t j Is a threshold value;
participant preference for perceived taskModeling is carried out, and the formula is as follows:
current state value M of participant i,j Modeling is carried out, and the formula is as follows:
wherein ,to the participant to perceive the familiarity of the place, W i,j For the participant's wish, add>For the participant to have a perceived task preference, α=1 is that the participant has performed such tasks, and α=0 is that the participant has not performed such tasks;
and evaluating the history condition of the user executing the task by utilizing the historical reliability, and simultaneously calculating the information entropy of the participant executing a certain type of task and the total information entropy of the participant executing the task, wherein the specific process is as follows:
obtaining a probability that the participant provides high quality data, the formula is:
wherein M is the number of sensing tasks, C is the number of categories of sensing tasks, M c A task set for each category;the number of times high quality data is provided to the participants, +.>A total number of times a task is performed for the participant;
obtaining information entropy of a participant when the participant performs a certain type of task, wherein the formula is as follows:
the total information entropy of the participant executing the task is obtained, and the formula is as follows:
the historical reliability of the participant in executing the task is calculated by the following formula:
wherein ,the probability h (x) of high quality data is provided for the participants, and the total information entropy of the tasks performed for the participants.
Initializing the reliability value of the participant by using the participant reliability model to obtain a reliability initialization value q of each participant i,j The formula is:
where λ is the slip factor.
And carrying out true value inference by using the reliability initialization value, wherein the formula is as follows:
wherein, if the task is a numerical task, the method causesSolving partial derivatives on two sides of the function, enabling the partial derivatives to be 0, and solving the true value of the numerical task;
if it is a classified task, ifThen-> Then->The true value of the score type task is solved.
Referring to fig. 2, a whole architecture diagram of an embodiment of a system for performing the reliability evaluation and true value inference method of participants in mobile crowd sensing according to the invention is shown.
The perception platform 100 issues perception tasks to the participant execution end 200; after the participant execution end 200 executes the sensing task, the sensing data is uploaded to the sensing platform 100; the perception platform 100 classifies perceived tasks performed by participants, the task types obtained including noise, temperature, traffic, and weather; the perception platform 100 models the reliability of the participants, evaluating the reliability of each participant using a reliability model; based on the participant reliability, the awareness platform 100 infers a true value for each task. Wherein 1) participant reliability: the current status of the participant is assessed based on the instantaneous factors of the participant in performing the task. The participant's current status is measured by three factors. Willingness when executing tasks, familiarity of perceived locations, preference for certain classes of tasks. The participant history reliability is evaluated based on the participant performance task history. The historical reliability of the participant evaluates the historical condition of the user performing the task while taking into account its reliability under a certain class of tasks as well as the overall reliability of the performing task. According to the concept of information entropy, the uncertainty of providing high-quality data when a user performs a certain class of tasks is measured by the perceptual entropy. 2) True value inference: the overall reliability of the participant is initialized by adding a sliding factor based on the current status and historical reliability of the participant. The actual values of the data provided by the participants and the data contributed by the reliable users should be relatively close, and different truth inference models are designed to update task truth values for different numeric and categorical tasks based on the participant reliability initialization values.
As shown in fig. 3, a flow chart for modeling participant reliability in crowd sensing is shown. The modeling includes two parts, the current state of the participant and the historical reliability. The current state of the participant refers to the instantaneous factor of the participant when the participant performs the current task, and the reliability of the participant for completing the current task is inferred through the current state. Participant historical reliability refers to the historical condition of a participant performing a task, from which the overall reliability of its performing task, as well as the reliability under a certain class of tasks, is inferred. The method comprises the following steps:
participant current state M i,j -the current state of the participant comprises the willingness W of the participant to perform the task i,j Familiarity of perceived locationsPerception task preference degree->Three parts.
Willingness: at the bookIn the invention, participant willingness W i,j The electric quantity condition of the mobile device and the distance d from the participant to the perceived task location of the participant in the task execution will be comprehensively considered i,j . Wherein, mobile device battery capacityRemaining power of mobile deviceRadius d of crowd sensing task sensing area θ . The formula for calculating the intention of the participants is as follows:
wherein ,dθ The closer the participants are to the sensing region, the higher the probability of providing high quality data for the radius of the task sensing region.
Perceived location familiarity: in the present invention, participants perceive location familiarityThe specific gravity of the participants to perform the task at the same place is comprehensively considered>And the average time the participant stays in the task area +.>When the participator is familiar with the perception place, the enthusiasm of executing the task is high, and the corresponding provided data quality is higher.
The above two factors are positively correlated with the familiarity of the participant with the perceived location. Considering that perceived tasks generally have spatiotemporal characteristics, perceived platforms require that the time for participants to complete the task does not exceed a threshold t j . Therefore, the formula for the familiarity of the participant with the perceived location is:
perception of task preference level: in the invention, the preference degree of participants on the perception taskConsideration of the specific gravity of participants to perform the same class of tasks is taken into account>Mean time to complete tasks of the same class +.>The higher the proficiency of a participant in a task of a certain category, the fewer errors in performing the task, the closer the data it provides to the true value. Thus the participant prefers about the task of a certain category>Is-> and />The product of the two.
In the present invention, the current state value of the participant is defined as [0,1 ]]Considering that the three factors are proportional to the current state of the participant, and considering that when the current state value of the participant is large or small, the value thereof is infinitely close to 1 or 0, the current state value M i,j The calculation formula is shown below. Simultaneous use of Sigmoid function current state value M i,j Normalization processing is performed.
Where α=1 represents that the participant performed such tasks, and α=0 represents that the participant did not perform such tasks.
Participant history reliabilityIn the present invention, the historical reliability of the participant will comprehensively consider the reliability of the participant under a certain class of tasks +.>And the overall reliability h (X) of the execution task. The perception platform divides M perception tasks into C categories, and the task set of each category is defined as M c. wherein ,/>Executing M for the user history task list c The number of class tasks, wherein the number of times to provide high quality data is recorded as +.>Let random variable->For participant pair M c The quality of the data provided by the class task is +.>The value is 1, i.e. the probability that a participant provides high quality data for such tasks +.>The method comprises the following steps:
for numerical tasks, ifThe error between the data provided by the participant in performing the task and the predicted truth value is less thanAt some threshold, it is shown that the participant is providing high quality data in this time the numerical task. For classified tasks, if->When the value provided by the participant in executing the task is consistent with the value of the estimated true value, the participant is indicated to provide high-quality data in the classified task.
Meanwhile, according to the concept of information entropy, defineThe uncertainty of providing high quality data when a user performs a class of tasks is measured for the perceived entropy of the participants when performing such tasks. The information entropy has symmetry, and the value range of the entropy value is [0,1 ]]. Considering that the smaller the entropy value, the higher the creditworthiness of the participants should be, and therefore +.>The value is [0,0.5]Entropy mapping to [1,2 ]]Within the range. In which it is considered that if the user has not performed M c Class aware tasks, then pair M c The entropy of the class task is initialized to 0.5./>Calculated from the following formula:
the overall information entropy of the participant in performing the task, i.e., the overall reliability of the participant in performing the task, is calculated by the following formula:
wherein delta is introduced as an introduction parameter to ensure that whenAt 0 the formula is still valid. The smaller the user total information entropy, the higher its overall reliability. The historical reputation also takes into account the historical reliability of the user for different tasks. For the historical credibility of the user for different tasks, the higher the historical credibility of the user is, the higher the reliability of the task is. The historical reliability of the participant's performance of the task is calculated by the following formula:
as shown in fig. 4, a flow chart of true value inference in crowd-sourced perception is shown. The data should be relatively close in view of the true value of the data and the reliable user contribution. Thus, in inferring the true value of a taskWhen first, the reliability value q for each participant participating in the task i,j Initializing, wherein an initialization calculation formula is as follows:
where λ is the slip factor.
The true value inference formula is:
wherein if the task is a numerical task, then the method causesAnd solving the bias guide on two sides of the function to make the bias guide be 0, so that the true value of the numerical task can be solved.
If it is a classified task, ifThen-> Then->The true value of the score type task is solved.
The technical scheme of the invention has the following advantages:
1) The unified participant fine granularity reliability assessment method is constructed, and simultaneously, the instantaneous factors and the historical factors of the participant in executing the task are considered, so that the quality of the data provided by the participant can be estimated correctly under the condition that the true value is unknown, and a larger weight is given to the trusted participant;
2) Designing true value inference methods under different numerical types based on the reliability of participants, and generating estimated true values with smaller errors even when most of data provided by users are unreliable;
3) The method has the advantages that the definition of the perception entropy is introduced according to the concept of the information entropy, the historical reliability of the participant in executing the perception task can be better measured by using the perception entropy, and the uncertainty of the participant in executing the perception task to provide high-quality data is deduced;
4) The participant reliability value is initialized by using the participant reliability model, and the method has better effect under the condition that most participants are unreliable.
Claims (1)
1. A method for participant reliability assessment and true value inference in mobile crowd sensing, the method comprising the steps of:
modeling the reliability of the participant through a perception platform, wherein the reliability model comprises a current state and historical reliability of the participant; the current state of the participant refers to an instantaneous factor of the participant when the participant executes the current task, and the reliability of completing the task is deduced through the current state; participants act asFront state M i,j Including willingness W of participants in performing tasks i,j Familiarity degree W of participants with perceived locations i,j Preference degree of participants for perceived task
Modeling of the participant's current state includes the following:
the willingness calculation formula when the participant executes the task is:
wherein ,Vi r For mobile device battery capacity, V i a D is the residual power of the mobile device θ Radius of crowd sensing task sensing area d i,j Distance from the participant to the perceived task location;
the calculation formula of the familiarity degree of the participator to the perception location is as follows:
wherein ,specific gravity for participants to perform tasks at the same place, < >>For the average time of stay of the participants in the task area, t j Is a threshold value;
participant preference for perceived taskThe calculation formula of (2) is as follows:
wherein ,specific gravity for executing the same class of tasks for participants, < ->Average time to complete the same class of tasks;
current state value M of participant i,j The calculation formula is as follows:
wherein ,to the participant to perceive the familiarity of the place, W i,j For the participant's wish, add>For the participant to have a perceived task preference, α=1 is that the participant has performed such tasks, and α=0 is that the participant has not performed such tasks;
evaluating the history condition of the user executing the task by utilizing the history reliability;
the total information entropy of the task executed by the participant is obtained, and the calculation formula is as follows:
wherein M is the number of sensing tasks, C is the number of categories of sensing tasks, M c For each set of tasks of a category,information entropy when executing a certain class of tasks for the participant, wherein delta is an introducing function;
the historical reliability of the participant in executing the task is obtained, and the calculation formula is as follows:
wherein ,providing high-quality data probability for the participants, wherein h (x) is the total information entropy of the tasks performed by the participants;
initializing the reliability value of the participant by using the participant reliability model to obtain a reliability initialization value q of each participant i,j The calculation formula is as follows:
wherein lambda is the slip factor,historical reliability of performing tasks for participants;
and carrying out true value inference by using the reliability initialization value, wherein the calculation formula is as follows:
wherein ,representing true values of the tasks;
if the task is a numerical task, thenSolving partial derivatives on two sides of the function, enabling the partial derivatives to be 0, and solving the true value of the numerical task;
if it is a classified task, ifThen-> Then->The true value of the score type task is solved.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874280.9A CN113705083B (en) | 2021-07-30 | 2021-07-30 | Participant reliability assessment and true value inference method in mobile crowd sensing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110874280.9A CN113705083B (en) | 2021-07-30 | 2021-07-30 | Participant reliability assessment and true value inference method in mobile crowd sensing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113705083A CN113705083A (en) | 2021-11-26 |
| CN113705083B true CN113705083B (en) | 2023-09-12 |
Family
ID=78651036
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110874280.9A Active CN113705083B (en) | 2021-07-30 | 2021-07-30 | Participant reliability assessment and true value inference method in mobile crowd sensing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705083B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114978550B (en) * | 2022-05-25 | 2023-05-16 | 湖南第一师范学院 | Trusted data perception method based on historical data backtracking |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108337656A (en) * | 2018-01-16 | 2018-07-27 | 武汉工程大学 | A kind of mobile intelligent perception motivational techniques |
| CN108600271A (en) * | 2018-05-10 | 2018-09-28 | 重庆邮电大学 | A kind of method for secret protection of trust state assessment |
| CN112153648A (en) * | 2020-09-02 | 2020-12-29 | 大连理工大学 | Mobile crowd sensing reliable data collection method based on D2D communication technology |
| CN113034250A (en) * | 2021-03-24 | 2021-06-25 | 海南大学 | Trust value-based crowd sensing incentive mechanism design method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10559216B2 (en) * | 2013-10-22 | 2020-02-11 | D2L Corporation | Systems and methods for conducting assessments in an electronic learning system |
-
2021
- 2021-07-30 CN CN202110874280.9A patent/CN113705083B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108337656A (en) * | 2018-01-16 | 2018-07-27 | 武汉工程大学 | A kind of mobile intelligent perception motivational techniques |
| CN108600271A (en) * | 2018-05-10 | 2018-09-28 | 重庆邮电大学 | A kind of method for secret protection of trust state assessment |
| CN112153648A (en) * | 2020-09-02 | 2020-12-29 | 大连理工大学 | Mobile crowd sensing reliable data collection method based on D2D communication technology |
| CN113034250A (en) * | 2021-03-24 | 2021-06-25 | 海南大学 | Trust value-based crowd sensing incentive mechanism design method |
Non-Patent Citations (1)
| Title |
|---|
| 基于跨空间多元交互的群智感知动态激励模型;南文倩;郭斌;陈荟慧;於志文;吴文乐;周兴社;;计算机学报(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113705083A (en) | 2021-11-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Din et al. | Machine learning in the Internet of Things: Designed techniques for smart cities | |
| Capponi et al. | A survey on mobile crowdsensing systems: Challenges, solutions, and opportunities | |
| Pouryazdan et al. | Intelligent gaming for mobile crowd-sensing participants to acquire trustworthy big data in the internet of things | |
| Pouryazdan et al. | Anchor-assisted and vote-based trustworthiness assurance in smart city crowdsensing | |
| Chang et al. | A Survey on Intelligent Sensor Network and Its Applications. | |
| Pan et al. | Composite social network for predicting mobile apps installation | |
| Gupta et al. | Cluster-head election using fuzzy logic for wireless sensor networks | |
| Zhang et al. | Fedsens: A federated learning approach for smart health sensing with class imbalance in resource constrained edge computing | |
| Wang et al. | Crowdsensing-based consensus incident report for road traffic acquisition | |
| US9098798B2 (en) | Methods and apparatus for prediction and modification of behavior in networks | |
| CN108171259A (en) | A kind of wisdom tip water quality monitoring system and method based on NB-IoT | |
| US20200213190A1 (en) | Fine grained network management to edge device features | |
| CN113705083B (en) | Participant reliability assessment and true value inference method in mobile crowd sensing | |
| Belapurkar et al. | Building data-aware and energy-efficient smart spaces | |
| CN114418109A (en) | Node selection and aggregation optimization system and method for federal learning under micro-service architecture | |
| Hankare et al. | Trust management approach for detection of malicious devices in siot | |
| Zhu et al. | Cost-effective active sparse urban sensing: Adversarial autoencoder approach | |
| Ding et al. | Dynamic delayed-decision task assignment under spatial-temporal constraints in mobile crowdsensing | |
| CN115580446A (en) | Non-intrusive load detection method based on decentralized federal learning | |
| Muccini et al. | Leveraging machine learning techniques for architecting self-adaptive iot systems | |
| Yang et al. | Atpp: A mobile app prediction system based on deep marked temporal point processes | |
| CN114372680A (en) | Spatial crowdsourcing task allocation method based on worker loss prediction | |
| Zhang et al. | Attack-resistant, energy-adaptive monitoring for smart farms: Uncertainty-aware deep reinforcement learning approach | |
| Fu et al. | ATWR-SMR: an area-constrained truthful worker recruitment based sensing map recovery scheme for sparse MCS in extreme-environment internet-of-things | |
| Mehrani et al. | Deep-learning based forecasting sampling frequency of biosensors in wireless body area networks |
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 |