A method of user recruitment and adaptation degree improvement via community collaboration in sparse mobile crowdsensing systems

The task allocation problem in sparse mobile crowdsensing is simplified as a subarea selection problem. How-ever, the lack of participants in some high-value subareas leads to the low quality of the final inferred sensing map. To solve this problem, a method of user recruitment and adaptation degree improvement via community collaboration is proposed. Firstly, the adjacency matrix is constructed based on the social relationship of the participants, and then all the participants are classified into communities by the non-negative matrix factor-ization method of deep autoencoder-like; secondly, the perception platform matches the perception tasks with the centroids of the perception communities based on the different eigenvalues of the classified perception communities and the location characteristics of the perception tasks. After the matching is completed, some participants in the matched communities will be selected to complete the perceptual tasks under the constraint of perceptual cost; finally, the perceptual data provided by the participants is used to obtain the complete perceptual map using the compressed perceptual algorithm. We designed this user recruitment method to obtain high-quality sensing data by recruiting a small number of users after community classification based on their social relationships and then accurately inferring the entire perceptual map. The experimental results based on the Gowalla and U-Air datasets show that the user recruitment method proposed in this paper can infer accurate data with fewer sensing areas, which is significantly better than other comparison methods.

Automated summary

This paper proposes a method of user recruitment and adaptation degree improvement via community collaboration to solve the task allocation problem in sparse mobile crowdsensing. By matching social relationships and perception task characteristics, the entire perceptual map can be accurately inferred.