Quality, Reliability, Security and Robustness in Heterogeneous Systems. 15th EAI International Conference, QShine 2019, Shenzhen, China, November 22–23, 2019, Proceedings

Research Article

Goldilocks: Learning Pattern-Based Task Assignment in Mobile Crowdsensing

  • @INPROCEEDINGS{10.1007/978-3-030-38819-5_5,
        author={Jinghan Jiang and Yiqin Dai and Kui Wu and Rong Zheng},
        title={Goldilocks: Learning Pattern-Based Task Assignment in Mobile Crowdsensing},
        proceedings={Quality, Reliability, Security and Robustness in Heterogeneous Systems. 15th EAI International Conference, QShine 2019, Shenzhen, China, November 22--23, 2019, Proceedings},
        proceedings_a={QSHINE},
        year={2020},
        month={1},
        keywords={Mobile crowdsensing Learning pattern recognition Task assignment},
        doi={10.1007/978-3-030-38819-5_5}
    }
    
  • Jinghan Jiang
    Yiqin Dai
    Kui Wu
    Rong Zheng
    Year: 2020
    Goldilocks: Learning Pattern-Based Task Assignment in Mobile Crowdsensing
    QSHINE
    Springer
    DOI: 10.1007/978-3-030-38819-5_5
Jinghan Jiang1,*, Yiqin Dai2,*, Kui Wu1,*, Rong Zheng3,*
  • 1: University of Victoria
  • 2: National University of Defense Technology
  • 3: McMaster University
*Contact email: jinghanj@uvic.ca, daiyq98@gmail.com, wkui@uvic.ca, rzheng@mcmaster.ca

Abstract

Mobile crowdsensing (MCS) depends on mobile users to collect sensing data, whose quality highly depends on the expertise/experience of the users. It is critical for MCS to identify right persons for a given sensing task. A commonly-used strategy is to “teach-before-use”, i.e., training users with a set of questions and selecting a subset of users who have answered the questions correctly the most of times. This method has large room for improvement if we consider users’ learning curve during the training process. As such, we propose an interactive learning pattern recognition framework, Goldilocks, that can filter users based on their learning patterns. Goldilocks uses an adaptive teaching method tailored for each user to maximize her learning performance. At the same time, the teaching process is also the selecting process. A user can thus be safely excluded as early as possible from the MCS tasks later on if her performance still does not match the desired learning pattern after the training period. Experiments on real-world datasets show that compared to the baseline methods, Goldilocks can identify suitable users to obtain more accurate and more stable results for multi-categories classification problems.