感知质量优化的移动群智感知任务在线分发算法

张伟; 李卓; 陈昕

doi:10.11959/j.issn.2096-3750.2020.00185

您当前的位置：

首页 >

文章列表页 >

感知质量优化的移动群智感知任务在线分发算法

理论与技术 | 更新时间：2024-06-05

- 感知质量优化的移动群智感知任务在线分发算法
- Data quality optimized online task allocation method for mobile crowdsensing
- 物联网学报 2020年4卷第4期页码：91-97
- 作者机构：
  
  1. 网络文化与数字传播北京市重点实验室，北京 100101
  2. 北京信息科技大学计算机学院，北京 100101
- 作者简介：
  
  [ "张伟（1996- ），女，北京人，北京信息科技大学硕士生，主要研究方向为移动群智感知" ]
  [ "李卓（1983- ），男，河南南阳人，博士，北京信息科技大学副教授，主要研究方向为移动无线网络、分布式计算" ]
  [ "陈昕（1965- ），男，江西南昌人，博士，北京信息科技大学教授，主要研究方向为网络性能评价、网络安全" ]
- 基金信息：
  
  国家自然科学基金资助项目;The National Natural Science Foundation of China(61872044);国家自然科学基金资助项目;The National Natural Science Foundation of China(61502040);北京市青年拔尖人才项目、北京市属高校高水平教师队伍建设支持计划青年拔尖人才培育计划资助项目;The Beijing Municipal Program for Top Talent,Beijing Municipal Program for Top Talent Cultivation(CIT＆TCD201804055);网络文化与数字传播北京市重点实验室开放课题资助项目;The Open Program of Beijing Key Laboratory of Internet Culture and Digital Dissemination Research(ICDDXN001);北京信息科技大学“勤信人才”培育计划资助项目;The Qinxin Talent Program of Beijing Information Science and Technology University
- DOI：10.11959/j.issn.2096-3750.2020.00185
  中图分类号： TP393.01
- 纸质出版日期：2020-12-30，
  
  网络出版日期：2020-12，
- 稿件说明：
移动端阅览
张伟, 李卓, 陈昕. 感知质量优化的移动群智感知任务在线分发算法[J]. 物联网学报, 2020,4(4):91-97.

WEI ZHANG, ZHUO LI, XIN CHEN. Data quality optimized online task allocation method for mobile crowdsensing. [J]. Chinese journal on internet of things, 2020, 4(4): 91-97.
张伟, 李卓, 陈昕. 感知质量优化的移动群智感知任务在线分发算法[J]. 物联网学报, 2020,4(4):91-97. DOI： 10.11959/j.issn.2096-3750.2020.00185.

WEI ZHANG, ZHUO LI, XIN CHEN. Data quality optimized online task allocation method for mobile crowdsensing. [J]. Chinese journal on internet of things, 2020, 4(4): 91-97. DOI： 10.11959/j.issn.2096-3750.2020.00185.

摘要

感知质量优化和用户招募是移动群智感知的两个重要问题，随着数据量的大幅度增加，感知内容出现冗余，存在感知质量降低的风险。提出了一种感知质量优化的任务分发机制，在保证覆盖率的情况下，提高群体的感知质量。利用聚类算法评估任务真值，量化用户数据质量；基于汤普森抽样算法和贪婪算法设计并实现了一种用户招募策略，在保证任务空间覆盖率的基础上优化感知质量。针对TSUR（Thompson based user recruit）算法的性能进行仿真分析，并与已有的BBTA（bandit-based task assignment）算法和BUR（basic user recruitment）算法作比较。实验表明，在同一区域进行任务感知，与BBTA算法和BUR算法相比，累计感知质量分别提高了16%和20%，空间覆盖率分别提高了30%和22%。

Abstract

Optimization of the perceived quality and the recruitment of user are two important issues of mobile crowdsensing.As the amount of data increases rapidly

perceived data becomes redundant

and perceived quality is at risk of decreasing.A mechanism of task assignment based on the perceptive quality optimization was proposed to improve the perceived quality under the condition of full coverage.The clustering algorithm was used to evaluate the truth value of the task and quantify the quality of the user data.Based on Thompson sampling algorithm and greedy algorithm

a user recruitment strategy was designed and implemented to optimize the perceived quality on the basis of ensuring the spatial coverage of the task.The performance of Thompson based user recruit (TSUR) algorithm was simulated and analyzed that compared with the existing algorithms of BBTA and basic user recruitment (BUR).Experiments show that in the same area

compared with bandit-based task assignment (BBTA) algorithm and BUR algorithm

the quality of the cumulative sensing data was improved by 16% and 20%

and the spatial coverage was improved by 30% and 22%.

关键词

移动群智感知任务分发数据质量在线学习

Keywords

mobile crowdsensingtask assignmentdata qualityonline learning

references

LEASE M, . On quality control and machine learning in crowdsourcing[C]// The 11th AAAI Workshop on Human Computation. AAAI Press, 2011: 97-102.

赵东, 马华东, 刘亮 . 移动群智感知质量度量与保障[J]. 中兴通讯技术, 2015,21(6): 2-5.

ZHAO D, MA H D, LIU L . Quality measuring and assurance for mobile crowd sensing[J]. ZTE Technology Journal, 2015,21(6): 2-5.

ZHANG H, MA Y, SUGIYAMA M . Bandit-based task assignment for heterogeneous crowdsourcing[J]. Neural Computation, 2015,27(11): 2447-2475.

XIAO M J, WU J, ZHANG S ,et al. Secret-sharing-based secure user recruitment protocol for mobile crowdsensing[C]// IEEE INFOCOM 2017 IEEE Conference on Computer Communications. IEEE, 2017.

GUO B, YU Z W, ZHANG D Q ,et al. From participatory sensing to mobile crowd sensing[C]// 2014 IEEE International Conference on Pervasive Computing and Communication Workshops (PERCOM WORKSHOPS). IEEE, 2014: 593-598.

ZHAO Y R, ZHANG Y, YU T ,et al. CityDrive:a map-generating and speed-optimizing driving system[C]// IEEE INFOCOM 2014 IEEE Conference on Computer Communications. IEEE, 2014: 1986-1994.

KIM S, ROBSON C, ZIMMERMAN T ,et al. Creek watch:pairing usefulness and usability for successful citizen science[C]// SIGCHI Conference on Human Factors in Computing Systems. ACM, 2011: 2125-2134.

MATHUR S, JIN T, KASTURIRANGAN N ,et al. ParkNet:drive-by sensing of road-side parking statistics[C]// The 8th International Conference on Mobile Systems,Applications,and Services. ACM, 2010: 123-136.

SIMOENS P, XIAO Y, PILLAI P ,et al. Scalable crowd-sourcing of video from mobile devices[C]// The 11th Annual International Conference on Mobile Systems,Applications,and Services. ACM, 2013: 139-152.

WANG J T, WANG Y S, ZHANG D Q ,et al. Multi-task allocation in mobile crowd sensing with individual task quality assurance[J]. IEEE Transactions on Mobile Computing, 2018,17(9): 2101-2113.

KO H, PACK S, LEUNG V C M . Coverage-guaranteed and energy-efficient participant selection strategy in mobile crowdsensing[J]. IEEE Internet of Things Journal, 2018:1.

WANG E, YANG Y J, LOU K H ,et al. User selection utilizing data properties in mobile crowdsensing[J]. Information Sciences, 2019,490: 210-226.

MAARRY K E, BALKE W T, CHO H ,et al. Skill ontology-based model for quality assurance in crowdsourcing[C]// International Conference on Database Systems for Advanced Applications. Springer, 2014.

HU X, LI X, NGAI E C H ,et al. Multidimensional context-aware social network architecture for mobile crowdsensing[J]. IEEE Communications Magazine, 2014,52(6): 78-87.

ALLAHBAKHSH M, BENATALLAH B, IGNJATOVIC A ,et al. Quality control in crowdsourcing systems:issues and directions[J]. IEEE Internet Computing, 2013,17(2): 76-81.

LIU S Z, ZHENG Z Z, WU F ,et al. Context-aware data quality estimation in mobile crowdsensing[C]// IEEE INFOCOM 2017 IEEE Conference on Computer Communications. IEEE, 2017.

YANG S, WU F, TANG S J ,et al. On designing data quality-aware truth estimation and surplus sharing method for mobile crowdsensing[J]. IEEE Journal on Selected Areas in Communications, 2017: 832-847.

GUO B, CHEN H H, QI H ,et al. Worker-contributed data utility measurement for visual crowdsensing systems[J]. IEEE Transactions on Mobile Computing, 2017,16(8): 2379-2391.

SALAS O F, ADZIC V, KALVA H . Subjective quality evaluations using crowdsourcing[C]// 2013 Picture Coding Symposium(PCS). IEEE, 2013.

RUSSO D, VAN R B, KAZEROUNI A ,et al. A tutorial on Thompson sampling[J]. Foundations and Trends in Machine Learning, 2017,11(1):112.

KARALIOPOULOS M, TELELIS O, KOUTSOPOULOS I . User recruitment for mobile crowdsensing over opportunistic networks[C]// Computer Communications. IEEE, 2015: 2254-2262.

浏览量

575

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

边缘计算中具有QoS保证的在线能耗感知任务分派