Search

A self-evolving reasoning method for task-user relationships based on the autonomic knowledge graph is proposed for the problem of existing task assignment methods, which cannot cope with dynamic environment changes in mobile crowd sensing. In particular, with the idea of "self-reflection," "self-configuration," and "self-adjustment" from autonomic computing, the concept of the autonomic knowledge graph is proposed for the first time. We apply it to build the complete cycle of the knowledge graph, which ensures the dynamic mapping between the task-user relationships in the mobile crowdsensing system. "Self-reflection" generates real-time responses to changes in the internal and external environment of the system. "Self-configuration" selects high-quality sensing users and filters the mobile crowd sensing knowledge graph paths to ensure the reliability of sensing users. Based on the filtered paths, "self-adjustment" computes the neighbor weight matrix of nodes to update node embeddings and exploit potential connections between task-user nodes. Finally, link prediction between task-user nodes achieves accurate and effective task recommendations. This self-evolving reasoning method of nodal relationships we designed combines autonomic computing with the knowledge graph. It forms a continuously operating loop that the next moment of sensing quality is assured and enhanced in the mobile crowd sensing system. Experiments based on the real-world Gollowa dataset, the public Last-FM dataset, and the Amazon-book dataset show that the proposed method can effectively improve sensing data quality and the accuracy of task recommendations. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low data quality and high incentive costs caused by the low enthusiasm of participants in mobile crowd sensing, a new task recommendation framework is proposed in this paper. First, the participants' historical behaviors are analyzed, assuming that user behaviors can be quantified as the user's willingness to participate, and the cosine similarity theorem is used to calculate the similarity between participants, thereby constructing a user-hybrid model. Secondly, probabilistic matrix factorization is developed to predict the willingness of participants, and a ranking model is obtained through learn-to-rank algorithm. Finally, a task recommendation list is generated according to the ranking model, which serves as the target participant's preferred task list for sensing task recommendation. The experiment in this paper is carried out on the MATLAB platform based on two real check-in datasets, Gowalla and Brightkite. The results show that the average allocation precision rate can reach 96%, and the sensing user participation rate is about 97%. Meantime, the user's mobile cost is reduced, and the overall goal of maximizing accuracy and minimizing perceived cost is achieved. [ABSTRACT FROM AUTHOR]

For task allocation of mobile crowd sensing, aiming at the problem that the task cannot​ be completed normally due to the change of sensing state and the data quality is reduced because the sensor willingness is not satisfied, a task allocation method with active learning ability based on the normal cloud model is proposed. Firstly, the data quality, sensing environment and network state of sensors are evaluated, and the threshold is set according to the power of sensor and the total amount of data sent, and on the basis, the sensor sensing ability is monitored in real time. Then, the multi-granularity standard distribution cloud and sensor state cloud are established through normal cloud model when the sensing state changes. Furthermore, the willingness score of the sensor to the task is obtained by cosine method. Finally, according to the willingness list, tasks are allocated by the maximum sensor willingness and the minimum number of sensors. Simulation experiment verifies that the task can be allocated when the sensing state is changed, and the quality of sensing data is better. Besides, in the incentive effect, the actual proportion of sensing sensors and the average numbers of tasks completed by sensors are better, and the incentive budget is smaller when the same data quality is obtained. [ABSTRACT FROM AUTHOR]