Abstract
Task allocation and incentive mechanism are two main research challenges of the mobile crowdsensing system (MCS). Most previous researches commonly focus on sensing users’ selection while ignoring the concurrency and spatial-temporal attributes of different tasks performed in the real environment. With the dynamic changes of the opportunity MCS context, the assurance data quality and accuracy tend to be controversial under the heterogeneous characteristics of tasks. To solve this problem, we first elaborate and model the key concepts of the task’s spatial-temporal attributes and sensing user mobility attributes, and then propose a novel framework with two fine-grained algorithms incorporating deep reinforcement learning, named DQN-TAIM. By observing the state of the MCS context, DQN-TAIM enriches and accumulates with more decision transitions, which can learn continuously and maximize the cumulative benefits of the platform from the interaction between users and the MCS environment. Finally, we evaluate the proposed method using a real-world data set, then compare and summarize it with a benchmark algorithm. The results confirm that DQN-TAIM has made excellent results and outperforms the benchmark method under various settings.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Waze. https://www.waze.com/zh/. Accessed 13 Sept 2020
Ganti, R.K., Pham, N., Ahmadi, H., Nangia, S., Abdelzaher, T.F.: GreenGPS: a participatory sensing fuel-efficient maps application. In: Proceedings of the 8th International Conference on Mobile Systems, Applications, and Services, San Francisco, California, USA, pp. 151–164. Association for Computing Machinery (2010)
Makhsous, S., Bharadwaj, M., Atkinson, B.E., Novosselov, I.V., Mamishev, A.V.: Dietsensor: automatic dietary intake measurement using mobile 3D scanning sensor for diabetic patients. Sensors 20(12), 3380 (2020)
Maisonneuve, N., Stevens, M., Niessen, M.E., Steels, L.: NoiseTube: measuring and mapping noise pollution with mobile phones. In: Athanasiadis, I.N., Rizzoli, A.E., Mitkas, P.A., Gómez, J.M. (eds.) Information Technologies in Environmental Engineering, pp. 215–228. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-540-88351-7_16
Nie, J., Luo, J., Xiong, Z., Niyato, D., Wang, P.: A stackelberg game approach toward socially-aware incentive mechanisms for mobile crowdsensing. IEEE Trans. Wirel. Commun. 18(1), 724–738 (2018)
Xu, J., Rao, Z., Xu, L., Yang, D., Li, T.: Incentive mechanism for multiple cooperative tasks with compatible users in mobile crowd sensing via online communities. IEEE Trans. Mob. Comput. 19(7), 1618–1633 (2019)
Wang, N., Da, J., Li, J., Liu, Y.: Influence maximization with trust relationship in social networks. In: 14th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN), Shenyang, China, pp. 61–67. IEEE (2018)
Suliman, A., Otrok, H., Mizouni, R., Singh, S., Ouali, A.: A greedy-proof incentive-compatible mechanism for group recruitment in mobile crowd sensing. Future Gener. Comput. Syst. 101, 1158–1167 (2019)
Neiat, A.G., Bouguettaya, A., Mistry, S.: Incentive-based crowdsourcing of hotspot services. ACM Trans. Internet Technol. (TOIT) 19(1), 1–24 (2019)
Bassem, C.: Mobility coordination of participants in mobile crowdsensing platforms with spatio-temporal tasks. In: Proceedings of the 17th ACM International Symposium on Mobility Management and Wireless Access, Miami Beach, FL, USA, pp. 33–40. Association for Computing Machinery (2019)
Vemula, A., Muelling, K., Oh, J.: Social attention: modeling attention in human crowds. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1–7. IEEE (2018)
Hu, Y., Wang, J., Wu, B., Helal, S.: Participants selection for from-scratch mobile crowdsensing via reinforcement learning. In: 2020 IEEE International Conference on Pervasive Computing and Communications, Austin, TX, USA, pp. 1–10. IEEE (2020)
Baidu Test. https://test.baidu.com/. Accessed 10 Sept 2020
Wang, C., Gaimu, X., Li, C., Zou, H., Wang, W.: Smart mobile crowdsensing with urban vehicles: a deep reinforcement learning perspective. IEEE Access 7, 37334–37341 (2019)
Li, H., Ota, K., Dong, M.: Deep reinforcement scheduling for mobile crowdsensing in fog computing. ACM Trans. Internet Technol. 19(2), 1–18 (2019)
Chen, Y., Wang, H.: IntelligentCrowd: Mobile Crowdsensing via Multi-agent Reinforcement Learning. arXiv preprint arXiv:1809.07830 (2018)
Wang, J., et al.: Multi-task allocation in mobile crowd sensing with individual task quality assurance. IEEE Trans. Mob. Comput. 17(9), 2101–2113 (2018)
Wang, L., Yu, Z., Zhang, D., Guo, B., Liu, C.H.: Heterogeneous multi-task assignment in mobile crowdsensing using spatiotemporal correlation. IEEE Trans. Mob. Comput. 18(1), 84–97 (2018)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Barlacchi, G., et al.: A multi-source dataset of urban life in the city of Milan and the Province of Trentino. Sci. Data 2(1), 1–15 (2015)
Tan, W., Jiang, Z.: A novel experience-based incentive mechanism for mobile crowdsensing system. In: Proceedings of the International Conference on Artificial Intelligence, Information Processing and Cloud Computing, Sanya, China, pp. 1–6 (2019)
Acknowledgement
This work was supported in part by ***.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jiang, Z., Tan, W. (2021). Multi-task Allocation Strategy and Incentive Mechanism Based on Spatial-Temporal Correlation. In: Sun, Y., Liu, D., Liao, H., Fan, H., Gao, L. (eds) Computer Supported Cooperative Work and Social Computing. ChineseCSCW 2020. Communications in Computer and Information Science, vol 1330. Springer, Singapore. https://doi.org/10.1007/978-981-16-2540-4_12
Download citation
DOI: https://doi.org/10.1007/978-981-16-2540-4_12
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-2539-8
Online ISBN: 978-981-16-2540-4
eBook Packages: Computer ScienceComputer Science (R0)
