移动群智感知中基于协同排序的任务推荐方法

doi:10.12263/DZXB.20200218

电子学报 ›› 2021, Vol. 49 ›› Issue (10): 2012-2019.DOI: 10.12263/DZXB.20200218

移动群智感知中基于协同排序的任务推荐方法

王健¹, 刘嘉欣¹, 赵国生², 赵中楠¹

^1.哈尔滨理工大学计算机科学与技术学院，黑龙江哈尔滨 150080
^2.哈尔滨师范大学计算机科学与信息工程学院，黑龙江哈尔滨 150025

收稿日期:2020-02-28 修回日期:2020-09-28 出版日期:2021-11-29
- 作者简介:
- 王健女，1979年6月出生，黑龙江哈尔滨人.毕业于哈尔滨工程大学，获得博士学位.现为哈尔滨理工大学教授、博士生导师，主要从事未来网络与认知网络、群智感知、可信计算等方面的研究工作. E-mail：wangjianlydia@163.com
  刘嘉欣女，1996年9月出生，黑龙江哈尔滨人.现为哈尔滨理工大学计算机科学与技术学院硕士研究生，主要从事群智感知、云计算与物联网安全等方面的研究工作.
- 基金资助:
- 国家自然科学基金 (61403109); 高等学校博士学科点专项科研基金 (20112303120007); 黑龙江省自然科学基金 (LH2020F034)

Task Recommendation Method Based on Collaborative Ranking in Mobile Crowd Sensing

WANG Jian¹, LIU Jia-xin¹, ZHAO Guo-sheng², ZHAO Zhong-nan¹

^1.School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, Heilongjiang 150080, China
^2.College of Computer Science and Information Engineering, Harbin Normal University, Harbin, Heilongjiang, 150025, China

Received:2020-02-28 Revised:2020-09-28 Online:2021-11-29 Published:2021-10-25
- Supported by:
- National Natural Science Foundation of China (61403109); Research Fund for the Doctoral Program of Higher Education of China (20112303120007); Natural Science Foundation of Heilongjiang Province, China (LH2020F034)

摘要/Abstract

摘要：

针对移动群智感知中参与者积极性不高导致的数据质量低和激励成本高的问题，本文提出了一种基于混合用户模型与列表级排序学习算法相结合的协同排序任务推荐方法.根据参与者的历史行为对其进行分析，初步过滤掉一些劣质感知用户，同时利用参与者间的相似性构建混合用户模型.利用概率矩阵分解对参与者的意愿值进行预测，并根据排序学习得到一个排序模型.根据排序模型生成任务推荐列表，作为目标参与者的优选任务列表.基于真实数据集的仿真实验结果表明，本文提出的方法有效地提高了任务分配的准确率，与此同时减少了感知用户的移动距离.

Abstract:

To solve the problem of low data quality and high incentive cost caused by the inactivity of participants in mobile crowd sensing, this paper proposes a task recommendation method. We could analyze the participants according to their historical behavior, and filter out low-quality sensing users. Meanwhile, the similarity among the participants was used to build a user-hybrid model. Then, the participants' willingness would be predicted by the probabilistic matrix factorization, and a ranking model was obtained. Finally, a task recommendation list was generated on the basis of ranking model as the preferred task list for the target participants. The simulation experiments based on the real dataset show that the proposed method in this paper can improve the accuracy of task assignment effectively and reduce the moving distance of sensing users simultaneously.

Key words: mobile crowd sensing, task recommendation, collaborative ranking, user-hybrid model, participants' willingness

中图分类号:

TP393

王健, 刘嘉欣, 赵国生, 赵中楠. 移动群智感知中基于协同排序的任务推荐方法[J]. 电子学报, 2021, 49(10): 2012-2019.

WANG Jian, LIU Jia-xin, ZHAO Guo-sheng, ZHAO Zhong-nan. Task Recommendation Method Based on Collaborative Ranking in Mobile Crowd Sensing[J]. Acta Electronica Sinica, 2021, 49(10): 2012-2019.

图/表 13

图1 参与者意愿与MCS任务分配关系实例

图2 MCS任务推荐问题描述

表1 实验数据集信息

Gowalla数据集			交互数据集
Candidates	Tasks	Check-in	Candidates	Tasks	Records
200	1023	9712	200	1000	6580

表2 实验参数设置

Parameter	Setting
c	0~200
t	0~1000
α	0~1
λ	0.001~1
μ	0.001~0.1
iterations	0~200
rank	30

图3 学习速率对损失函数收敛性的影响

图4 正则化系数对损失函数收敛性的影响

图5 参数α对平均分配准确率的影响

图6 Gowalla数据集：平均分配准确率与候选者和任务数的关系比较

图7 交互数据集：平均分配准确率与候选者和任务数的关系比较

图8 Gowalla数据集：算法运行时间与候选者和任务数的关系比较

图9 交互数据集：算法运行时间与候选者和任务数的关系比较

图10 参与者数量与候选者关系比较

图11 平均移动距离与候选者关系比较

参考文献 21

1	GuoB, WangZ, YuZ W, et al. Mobile crowd sensing and computing: The review of an emerging human-powered sensing paradigm[J]. ACM Computing Surveys, 2015, 48(1): 1－31.
2	ShuL, ChenY F, HuoZ Q, et al. When mobile crowd sensing meets traditional industry[J]. IEEE Access, 2017, 5: 15300－15307.
3	俞东进, 陈聪, 吴建华, 等. 基于隐式反馈数据的个性化游戏推荐[J]. 电子学报, 2018, 46(11): 2626－2632.
	YuD J, ChenC, WuJ H, et al. Personalized game recommendation based on implicit feedback[J]. Acta Electronica Sinica, 2018, 46(11): 2626－2632. (in Chinese)
4	XiongH Y, ZhangD Q, ChenG L, et al. iCrowd: Near-optimal task allocation for piggyback crowdsensing[J]. IEEE Transactions on Mobile Computing, 2016, 15(8): 2010－2022.
5	WangJ T, WangF, WangY S, et al. Social-network-assisted worker recruitment in mobile crowd sensing[J]. IEEE Transactions on Mobile Computing, 2019, 18(7): 1661－1673.
6	LiuY, GuoB, WangY, et al. TaskMe: multi-task allocation in mobile crowd sensing[A]. Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing[C]. New York, NY, USA: ACM, 2016. 403－414.
7	WangL, YuZ W, ZhangD Q, et al. Heterogeneous multi-task assignment in mobile crowdsensing using spatiotemporal correlation[J]. IEEE Transactions on Mobile Computing, 2019, 18(1): 84－97.
8	安健, 彭振龙, 桂小林, 等. 群智感知中基于公交系统的任务分发机制研究[J]. 计算机学报, 2019, 42(2): 65－78.
	AnJ, PengZ L, GuiX L, et al. Research on task distribution mechanism based on public transit system in crowd sensing[J]. Chinese Journal of Computers, 2019, 42(2): 65－78. (in Chinese)
9	YangY J, LiuW B, WangE, et al. A prediction-based user selection framework for heterogeneous mobile CrowdSensing[J]. IEEE Transactions on Mobile Computing, 2019, 18(11): 2460－2473.
10	WangE, YangY J, WuJ, et al. An efficient prediction-based user recruitment for mobile crowdsensing[J]. IEEE Transactions on Mobile Computing, 2018, 17(1): 16－28.
11	景瑶, 郭斌, 陈荟慧, 等. CrowdTracker: 一种基于移动群智感知的目标跟踪方法[J]. 计算机研究与发展, 2019, 56(2): 328－337.
	JingY, GuoB, ChenH H, et al. CrowdTracker: object tracking using mobile crowd sensing[J]. Journal of Computer Research and Development, 2019, 56(2): 328－337. (in Chinese)
12	LiH S, LiT, WangY. Dynamic participant recruitment of mobile crowd sensing for heterogeneous sensing tasks[A]. 2015 IEEE 12th International Conference on Mobile Ad Hoc and Sensor Systems[C]. Dallas, TX, USA: IEEE, 2015. 136－144.
13	PournajafL, XiongL, SunderamV. Dynamic data driven crowd sensing task assignment[J]. Procedia Computer Science, 2014, 29: 1314－1323.
14	WangJ T, WangF, WangY S, et al. Allocating heterogeneous tasks in participatory sensing with diverse participant-side factors[J]. IEEE Transactions on Mobile Computing, 2019, 18(9): 1979－1991.
15	AbououfM, SinghS, OtrokH, et al. Gale-shapley matching game selection—A framework for user satisfaction[J]. IEEE Access, 2019, 7: 3694－3703.
16	YuenM C, KingI, LeungK S. TaskRec: A task recommendation framework in crowdsourcing systems[J]. Neural Processing Letters, 2015, 41(2): 223－238.
17	丁宇新, 燕泽权, 冯威, 等. 基于有监督主题模型的排序学习算法[J]. 电子学报, 2015, 43(2): 333－337.
	DingY X, YanZ Q, FengW, et al. Rank learning based on supervised topic model[J]. Acta Electronica Sinica, 2015, 43(2): 333－337. (in Chinese)
18	任开旭, 王玉龙, 刘同存, 等. 融合多维语义表示的概率矩阵分解模型[J]. 电子学报, 2019, 47(9): 1848－1854.
	RenK X, WangY L, LiuT C, et al. A probabilistic matrix factorization model based on multidimensional semantic representation learning[J]. Acta Electronica Sinica, 2019, 47(9): 1848－1854. (in Chinese)
19	ShiY, LarsonM, HanjalicA. List-wise learning to rank with matrix factorization for collaborative filtering[A]. Proceedings of the fourth ACM conference on Recommender systems - RecSys '10[C]. New York, USA: ACM Press, 2010. 269－272.
20	ChoE, MyersS A, LeskovecJ. Friendship and mobility: User movement in location-based social networks[A]. Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD '11[C]. New York, USA: ACM Press, 2011. 1082－1090.
21	陈家银. 猪八戒众包平台数据分析与众包模式设计[D]. 大连: 大连理工大学, 2016.
	ChenJ Y. Zhubajie crowdsourcing platform data analysis and crowdsourcing model design[D]. Dalian, China: Dalian University of Technology, 2016. (in Chinese)

移动群智感知中基于协同排序的任务推荐方法

Task Recommendation Method Based on Collaborative Ranking in Mobile Crowd Sensing

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 13

参考文献 21

相关文章 1

编辑推荐

Metrics