Home > Research > Publications & Outputs > RL-Recruiter+

Links

Text available via DOI:

View graph of relations

RL-Recruiter+: Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

RL-Recruiter+ : Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing. / Hu, Y.; Wang, J.; Wu, B. et al.

In: IEEE Transactions on Mobile Computing, Vol. 21, No. 12, 31.12.2022, p. 4555-4568.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Hu Y, Wang J, Wu B, Helal S. RL-Recruiter+: Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing. IEEE Transactions on Mobile Computing. 2022 Dec 31;21(12):4555-4568. Epub 2021 May 5. doi: 10.1109/TMC.2021.3077636

Author

Hu, Y. ; Wang, J. ; Wu, B. et al. / RL-Recruiter+ : Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing. In: IEEE Transactions on Mobile Computing. 2022 ; Vol. 21, No. 12. pp. 4555-4568.

Bibtex

@article{53f8cf1626244546b0f9147689d164ee,
title = "RL-Recruiter+: Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing",
abstract = "Participant selection is a fundamental research issue in Mobile Crowdsensing (MCS). Previous approaches commonly assume that adequately long periods of candidate participants' historical mobility trajectories are available to model their patterns before the selection process, which is not realistic for some new MCS applications or platforms. The sparsity or even absence of mobility traces will incur inaccurate location prediction, thus undermining the deployment of new MCS applications. To this end, this paper investigates a novel problem called From-Scratch MCS (FS-MCS for short), in which we study how to intelligently select participants to minimize such cold-start effect. Specifically, we propose a novel framework based on reinforcement learning, named RL-Recruiter+. With the gradual accumulation of mobility trajectories over time, RL-Recruiter+ is able to make a good sequence of participant selection decisions for each sensing slot. Compared to its previous version, RL-Recruiter, Re-Recruiter+ jointly considers both the previous coverage and current mobility predictability when training the participant selection decision model. We evaluate our approach experimentally based on two real-world mobility datasets. The results demonstrate that RL-Recruiter+ outperforms the baseline approaches, including RL-Recruiter under various settings. ",
keywords = "Crowdsensing, Electronic mail, Reinforcement learning, Robot sensing systems, Sensors, Task analysis, Trajectory, Computer networks, Mobile computing, Cold start, Fundamental research, Location prediction, Mobility traces, Real-world, Selection decisions",
author = "Y. Hu and J. Wang and B. Wu and S. Helal",
year = "2021",
month = may,
day = "5",
doi = "10.1109/TMC.2021.3077636",
language = "English",
volume = "21",
pages = "4555--4568",
journal = "IEEE Transactions on Mobile Computing",
issn = "1536-1233",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "12",

}

RIS

TY - JOUR

T1 - RL-Recruiter+

T2 - Mobility-Predictability-Aware Participant Selection Learning for From-Scratch Mobile Crowdsensing

AU - Hu, Y.

AU - Wang, J.

AU - Wu, B.

AU - Helal, S.

PY - 2021/5/5

Y1 - 2021/5/5

N2 - Participant selection is a fundamental research issue in Mobile Crowdsensing (MCS). Previous approaches commonly assume that adequately long periods of candidate participants' historical mobility trajectories are available to model their patterns before the selection process, which is not realistic for some new MCS applications or platforms. The sparsity or even absence of mobility traces will incur inaccurate location prediction, thus undermining the deployment of new MCS applications. To this end, this paper investigates a novel problem called From-Scratch MCS (FS-MCS for short), in which we study how to intelligently select participants to minimize such cold-start effect. Specifically, we propose a novel framework based on reinforcement learning, named RL-Recruiter+. With the gradual accumulation of mobility trajectories over time, RL-Recruiter+ is able to make a good sequence of participant selection decisions for each sensing slot. Compared to its previous version, RL-Recruiter, Re-Recruiter+ jointly considers both the previous coverage and current mobility predictability when training the participant selection decision model. We evaluate our approach experimentally based on two real-world mobility datasets. The results demonstrate that RL-Recruiter+ outperforms the baseline approaches, including RL-Recruiter under various settings.

AB - Participant selection is a fundamental research issue in Mobile Crowdsensing (MCS). Previous approaches commonly assume that adequately long periods of candidate participants' historical mobility trajectories are available to model their patterns before the selection process, which is not realistic for some new MCS applications or platforms. The sparsity or even absence of mobility traces will incur inaccurate location prediction, thus undermining the deployment of new MCS applications. To this end, this paper investigates a novel problem called From-Scratch MCS (FS-MCS for short), in which we study how to intelligently select participants to minimize such cold-start effect. Specifically, we propose a novel framework based on reinforcement learning, named RL-Recruiter+. With the gradual accumulation of mobility trajectories over time, RL-Recruiter+ is able to make a good sequence of participant selection decisions for each sensing slot. Compared to its previous version, RL-Recruiter, Re-Recruiter+ jointly considers both the previous coverage and current mobility predictability when training the participant selection decision model. We evaluate our approach experimentally based on two real-world mobility datasets. The results demonstrate that RL-Recruiter+ outperforms the baseline approaches, including RL-Recruiter under various settings.

KW - Crowdsensing

KW - Electronic mail

KW - Reinforcement learning

KW - Robot sensing systems

KW - Sensors

KW - Task analysis

KW - Trajectory

KW - Computer networks

KW - Mobile computing

KW - Cold start

KW - Fundamental research

KW - Location prediction

KW - Mobility traces

KW - Real-world

KW - Selection decisions

U2 - 10.1109/TMC.2021.3077636

DO - 10.1109/TMC.2021.3077636

M3 - Journal article

VL - 21

SP - 4555

EP - 4568

JO - IEEE Transactions on Mobile Computing

JF - IEEE Transactions on Mobile Computing

SN - 1536-1233

IS - 12

ER -