Spatiotemporal Urban Inference and Prediction in Sparse Mobile CrowdSensing: A Graph Neural Network Approach

Mobile CrowdSensing (MCS) has recently become a promising data acquisition paradigm, which recruits a large number of users to collect data from the target sensing areas. Obviously, with the increase of sensing scale and the decrease of sensing granularity, traditional MCS cannot fully cover the required sensing areas especially the inaccessible areas. As a variant, Sparse MCS can utilize the spatiotemporal correlations in sensing data to infer the whole sensing map only by sensing a few subareas. However, in many real-world scenarios, such as traffic congestion prediction or parking occupancy detection, inferring the current unsensed data may not be the final goal. By comparison, it is more important to get the future information through the sparse sensed data. In this paper, we turn attention from inferring the current unsensed data to predicting the future unknown data and propose an urban inference and prediction framework in Sparse MCS. To deal with the sparse sensed data, we first present a bipartite-graph-based matrix completion algorithm with spatiotemporal constraints to accurately recover the current full map. Then, by exploiting spatiotemporal correlations based on the inferred full map, we present a Graph Convolutional Networks (GCN) with spatiotemporal attention to predict the future maps. Furthermore, we design a spatiotemporal iterative method to repeatedly update the spatiotemporal attentions and constraints, in order to connect the urban inference and prediction to improve the accuracy of the whole framework. Extensive experiments have been conducted on two types of typical urban sensing tasks with four real-world data sets, which verify the effectiveness of our proposed algorithms in improving the inference and prediction accuracy with the sparse sensed data.

1 Introduction

With the rapid development of information society and wireless devices portability, Mobile CrowdSensing (MCS) [2] has become a new data collection mode combined with crowdsensing and mobile devices [3], [4]. It recruits users carrying mobile devices to collect data from target sensing areas in order to perform various sensing tasks, such as environment monitoring [5], traffic controlling [6] and urban sensing [7], etc. To obtain high-quality sensing results, the traditional MCS system usually has to recruit lots of users to cover the entire sensing map. However, considering the costs limitation, it cannot afford too many users. Even if it has recruited enough users with acceptable cost, some sensing subareas may still have no available users due to the users’ uncertain mobility or subareas’ inaccessibility [8]. Therefore, in most cases, the traditional MCS can only collect incomplete or even sparse data, especially facing large-scale and fine-grained urban sensing tasks.