Research on Task Allocation of Crowdsensing User Activity Based on the ResNet Neural Network

Authors

  • Li Zhang Yangzhou Polytechnic Institute, Yangzhou, Jiangsu 215006, China
  • Shukui Zhang School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China
  • Ye Tao School of Computer Science and Technology, Soochow University, Suzhou, Jiangsu 215006, China
  • Pingquan Wang Yangzhou Polytechnic Institute, Yangzhou, Jiangsu 215006, China
  • Hao Long Xuzhou College of Industrial Technology, Xuzhou, Jiangsu 221140, China

Abstract

Currently, there is a lack of multi-dimensional research on sensing task allocation in mobile crowdsensing networks. This paper proposes a task allocation algorithm based on the positive association between sensing entities. First, sensing activity is measured by the number of successful completions of sensing tasks by participating users, divided into direct and indirect activities. Meanwhile, a correlation model is constructed by combining direct and indirect activities. Furthermore, to improve the success rate of sensing task allocation, the ResNet neural network is trained to eliminate the gradient vanishing problem. Moreover, the AM Softmax cross-entropy loss function is adopted to narrow the gap between peers and expand the gap between different classes, thereby improving the accuracy of sensing task allocation. Finally, the constructed association model and the classification neural network are integrated for sensing task allocation. Experimental verification indicates that the proposed algorithm has significantly enhanced the accuracy of task allocation and can better provide accurate task allocation services.

Keywords: mobile crowdsensing; mobile users; activate; task allocation

L. Zhang, S. Zhang, Y. Tao, P. Wang, H. Long, "Research on Task Allocation of Crowdsensing User Activity Based on the ResNet Neural Network", Engineering Intelligent Systems, vol. 34 no. 4, pp. 545-557, 2026.

Downloads

Published

2026-07-01

Issue

Vol. 34 No. 4 (2026): International Journal of Engineering Intelligent Systems

Section

Article

License

The submission of a paper implies that, if accepted for publication, it will not be published elsewhere in the same form, in any language, without the prior consent of the publisher. Before publication, authors are requested to assign copyright to CRL Publishing Ltd. This allows CRL to sanction photocopying, and to authorize the reprinting of issues or volumes according to demand. Authors' traditional rights will not be jeopardized by assigning Copyright in this way, as they retain the right to reuse the material following publication, and to veto third-party publication.